{"description":"Blather, twaddle and piffle","feed_url":"https://gbilder.com/feed.json","home_page_url":"https://gbilder.com/","icon":"https://gbilder.com/icon.png","language":"en","title":"Louche Cannon","version":"https://jsonfeed.org/version/1.1","items":[{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/saluting-cats.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2025, June 24).\n      \n      \u003ci\u003eAI Like It\u0026#39;s 1930\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/5ehqx-91420\"\u003e\n      https://doi.org/10.59347/5ehqx-91420\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003cp\u003eAfter reading another \u003ca href=\"https://www.darioamodei.com/essay/machines-of-loving-grace\"\u003emessianic sermon\u003c/a\u003e about how AI is going to accelerate science, I had an idea for an experiment:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eBuild a modern LLM-based AI using only content from before 1930 (or another cutoff that gives you enough data).\u003c/li\u003e\n\u003cli\u003eRestrict researchers interacting with the LLM to using prompts that do not include information, terminology, or ideas that have been introduced since the cutoff date.\u003c/li\u003e\n\u003cli\u003eSee if the LLM can help the researchers recreate, in essence, any of the major paradigm-shifting creative developments - scientific breakthroughs, inventions, art/music movements - that humans have come up with \u003cem\u003esince\u003c/em\u003e that cutoff date.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIn short, let\u0026rsquo;s test the idea that LLMs can be creative by building an anachronistically time-boxed LLM and seeing if researchers using the LLM can innovate outside of the box.\u003c/p\u003e\n\u003cp\u003eAnd let\u0026rsquo;s do the experiment \u003cstrong\u003ebefore\u003c/strong\u003e we make knowledge-production and creative work inviable career paths.\u003c/p\u003e\n","date_modified":"2025-06-24T00:00:00Z","date_published":"2025-06-24T00:00:00Z","id":"https://doi.org/10.59347/5ehqx-91420","summary":"I have an idea for an experiment.","tags":["AI"],"title":"AI Like It's 1930","url":"https://gbilder.com/posts/2025-06-24-ai-like-its-1930/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/cherry-cherry-strawberry.jpeg","content_html":"\u003cp\u003eEvery completion or prompt is a pull of the lever.\u003c/p\u003e\n\u003cp\u003eEvery successful text completion saves you seconds at a time and gives you a little dopamine hit.\u003c/p\u003e\n\u003cp\u003eEvery successful prompt can save you hours at a time and gives you a giant dopamine rush.\u003c/p\u003e\n\u003cp\u003eAnd when you have a hot hand—it’s like swimming in an infinite dopamine pool.\u003c/p\u003e\n\u003cp\u003eYou remember these wins, but you forget the numerous little failures.\u003c/p\u003e\n\u003cp\u003eAnd you discount every time you discovered that it borked your code beyond recognition.\u003c/p\u003e\n\u003cp\u003eIt must have been your fault.\u003c/p\u003e\n\u003cp\u003eYou just need to review the code more carefully.\u003c/p\u003e\n\u003cp\u003eYou just need to refine the prompts.\u003c/p\u003e\n\u003cp\u003eYou just need to add new workspace rules.\u003c/p\u003e\n\u003cp\u003eYou just need to finesse your pull of the lever. \u003c/p\u003e\n\u003cp\u003eBesides- when you finally do discover that it somehow managed to trash your code without you catching it, what are you going to do? You are in the hole. You\u0026rsquo;re not familiar with the code anymore.\u003c/p\u003e\n\u003cp\u003eYour only way to get out is to pull the lever again and hope that the thing that broke your project can also fix it.\u003c/p\u003e\n\u003cp\u003eMaybe you can still break even?\u003c/p\u003e\n\u003cp\u003eAnd if you don\u0026rsquo;t break even, you certainly aren\u0026rsquo;t going to tell anybody.\u003c/p\u003e\n\u003cp\u003eThat would be too embarrassing.\u003c/p\u003e\n\u003cp\u003eNobody else is failing at this.\u003c/p\u003e\n\u003cp\u003eThey all seem to have it figured out.\u003c/p\u003e\n\u003cp\u003eThere are people out there writing complete applications in forty-five minutes.\u003c/p\u003e\n\u003cp\u003eThere is one machine whisperer who can even generate realistic SVG images of a pelican riding a bicycle.\u003c/p\u003e\n\u003cp\u003eAnd there are whales out there placing bets of billions of dollars.\u003c/p\u003e\n\u003cp\u003eThey must know something you don\u0026rsquo;t know.\u003c/p\u003e\n\u003cp\u003eThey must have an angle.\u003c/p\u003e\n\u003cp\u003eBut at the moment, you are in the red.\u003c/p\u003e\n\u003cp\u003eSo it’s double or nothing. \u003c/p\u003e\n\u003cp\u003eAnd you pull the lever.\u003c/p\u003e\n\u003cp\u003eAgain.\u003c/p\u003e\n\u003cp\u003eAnd you hear the ping on your phone notifying you that your account has been automatically topped up.\u003c/p\u003e\n\u003cp\u003eAgain.\u003c/p\u003e\n\u003chr\u003e\n\n            \u003clink rel=\"stylesheet\" href=\"/css/vendors/admonitions.4fd9a0b8ec8899f2ca952048d255a569f433f77dfb3f52f5bc87e7d65cdce449.css\" integrity=\"sha256-T9mguOyImfLKlSBI0lWlafQz9337P1L1vIfn1lzc5Ek=\" crossorigin=\"anonymous\"\u003e\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eI wrote this a few months ago and never posted it. Because\u0026hellip;\nWell, because I\u0026rsquo;m kind of sick of hot takes on AI.\u003c/p\u003e\n\u003cp\u003eAnd then \u003ca href=\"https://pivot-to-ai.com/2025/06/05/generative-ai-runs-on-gambling-addiction-just-one-more-prompt-bro/\"\u003ethis\u003c/a\u003e post by\nDavid Gerard came out. And it is much better. I encourage you to read it.\u003c/p\u003e\n\u003cp\u003eBut seeing it also convinced me that I should have posted my attempt to make the same point. And so I have.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e","date_modified":"2025-06-09T00:00:00Z","date_published":"2025-06-09T00:00:00Z","id":"","summary":"Every completion or prompt is a pull of the lever.","tags":["AI"],"title":"Epistemic Slot Machines","url":"https://gbilder.com/posts/2025-06-09-epistemic-slot-machines/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/yotel-robot.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2025, April 2).\n      \n      \u003ci\u003eBots Behaving Badly\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/w366z-egx85\"\u003e\n      https://doi.org/10.59347/w366z-egx85\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003cp\u003eI\u0026rsquo;ve seen an uptick in people I respect concluding that the massive increase in badly-behaved web-scraping \u003ca href=\"https://en.wikipedia.org/wiki/Internet_bot\"\u003ebots\u003c/a\u003e is intentional and just another example of sociopathic AI companies ripping-up long-respected web conventions for the sake of profit. Here are two recent examples:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://go-to-hellman.blogspot.com/2025/03/ai-bots-are-destroying-open-access.html\"\u003eAI bots are destroying Open Access\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://www.marginalia.nu/log/a_115_rude_crawler/\"\u003eImproved ways to operate a rude crawler\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eI am \u003ca href=\"https://gbilder.com/blog/2024/07/ai-update/\"\u003eno fan of AI companies\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eBut I don’t think this explains what\u0026rsquo;s really happening.\u003c/p\u003e\n\u003cp\u003eThe problem still has its roots in AI, but for different reasons—  reasons that are possibly more concerning than the idea that IA companies are doing this stuff on purpose.\u003c/p\u003e\n\u003cp\u003eInstead, I suspect the \u003cstrong\u003ereal\u003c/strong\u003e problem is people \u003cem\u003eusing AI coding tools\u003c/em\u003e that generate, buggy, and hyper-aggressive bots.\u003c/p\u003e\n\u003cp\u003eAnd I bet that the vast majority of the developers behind these bots have no idea that they are causing problems.\u003c/p\u003e\n\u003cp\u003eThis would consistent with what I used to see when trying to manage \u003ca href=\"https://api.crossref.org\"\u003ea popular API\u003c/a\u003e even \u003cem\u003ebefore\u003c/em\u003e AI tools became ubiquitous.\u003c/p\u003e\n\u003cp\u003eWe \u003cem\u003econstantly\u003c/em\u003e had problems with bots— but only twice could the problems be attributed to a bot that was deliberately designed to be aggressive and evade detection.\u003c/p\u003e\n\u003cp\u003eAll the other times it was some naive programmer (often a researcher)  who had built a buggy bot or who simply didn’t know about bot conventions like \u003ca href=\"https://en.wikipedia.org/wiki/Robots.txt\"\u003e\u003ccode\u003erobots.txt\u003c/code\u003e\u003c/a\u003e, error/retry backoffs, \u003ca href=\"https://en.wikipedia.org/wiki/Rate_limiting\"\u003erate-limiting\u003c/a\u003e, \u003ca href=\"https://en.wikipedia.org/wiki/Connection_pool\"\u003econnection pools\u003c/a\u003e, \u003ca href=\"https://en.wikipedia.org/wiki/User-Agent_header\"\u003euser-agent\u003c/a\u003e ettiquette, etc..\u003c/p\u003e\n\u003cp\u003eWe also had a constant problem with developers who didn’t know how \u003ca href=\"https://www.merge.dev/blog/cursor-pagination\"\u003ecursors\u003c/a\u003e worked in our API because they simply hadn’t read the docs. This meant that on any given day we would see dozens of bots just endlessly requesting the next page of empty results from a cursor that had long ago stopped delivering them data.\u003csup id=\"fnref:1\"\u003e\u003ca href=\"#fn:1\" class=\"footnote-ref\" role=\"doc-noteref\"\u003e1\u003c/a\u003e\u003c/sup\u003e\u003c/p\u003e\n\u003cp\u003eWhenever we managed to get in touch with the developers, they would be genuinely surprised, profusely apologetic, and they’d immediately shut off or fix their code.\u003c/p\u003e\n\u003cp\u003eSometimes we’d find that said developers had \u003cem\u003eentirely forgotten they’d left the bot running\u003c/em\u003e and they’d sheepishly admit that the project it was built for had ended months or years ago!\u003c/p\u003e\n\u003cp\u003eAnd a lot of this code was public.\u003c/p\u003e\n\u003cp\u003eAnd AIs were trained on it.\u003c/p\u003e\n\u003cp\u003eAnd so AI-generated code is replicating all of these problems.\u003c/p\u003e\n\u003cp\u003eI routinely test new AI coding tools with a set of problems that I know are easy to get wrong. Web scraping is one of these things.\u003c/p\u003e\n\u003cp\u003eAnd all the tools I’ve tried make at least a few of the  same mistakes humans make— they ignore \u003ca href=\"https://en.wikipedia.org/wiki/Robots.txt\"\u003e\u003ccode\u003erobots.txt\u003c/code\u003e\u003c/a\u003e, they don’t use \u003ca href=\"https://en.wikipedia.org/wiki/Connection_pool\"\u003econnection pooling\u003c/a\u003e, they don’t honor \u003ca href=\"https://en.wikipedia.org/wiki/Rate_limiting\"\u003erate limits\u003c/a\u003e, they don’t set correct \u003ca href=\"https://en.wikipedia.org/wiki/User-Agent_header\"\u003euser-agent\u003c/a\u003e headers.\u003c/p\u003e\n\u003cp\u003eI also test to see if the AI tools will generate code that properly handles cursors with the Crossref API.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eOnly once\u003c/em\u003e have I seen an LLM produce the correct code the first time.  And even then, it was a fluke and I haven’t been able to get that particular LLM to do it again since.\u003c/p\u003e\n\u003cp\u003eAnd, of course, increasingly AI\u0026rsquo;s are also trained on code that includes mechanisms to evade being blocked— and so, in addition to being buggy, they are also effectively trained to be more aggressive and stealthy.\u003c/p\u003e\n\u003cp\u003eAnd whereas most new programmers are justifiably reluctant to delve into the intricacies of creating concurrent apps, AI tools seem to have no such inhibitions and generate code that spawns dozens of requests at that same time.\u003c/p\u003e\n\u003cp\u003eBut most of the the people using these AI tools don’t know this. All they know is that the AI tools allow them to easily build a bot to scrape data from the web- something that seemed too daunting for them to do before.\u003c/p\u003e\n\u003cp\u003eThey are \u0026ldquo;\u003ca href=\"https://en.wikipedia.org/wiki/Vibe_coding\"\u003evibe coding\u003c/a\u003e.\u0026rdquo;\u003c/p\u003e\n\u003cp\u003eAnd so now we have a gigantic influx of new \u0026ldquo;developers\u0026rdquo; building new tools to make use of data on the internet. And these tools are based on highly concurrent, hyper-aggressive, and extremely buggy AI-generated code.\u003c/p\u003e\n\u003cp\u003eThis may sound like I’m splitting hairs— I mean, the problem is still related to AI, right? And this behavior, — whether deliberate or not — is causing a lot of collateral damage.\u003c/p\u003e\n\u003cp\u003eYes, but I think this underscores what I suspect is the most realistic threat from AI — not that we will all soon be replaced by AGI, but that more and more of our systems are going to become infested with subtly buggy data and code that has unintentional, unpredictable, and damaging downstream effects.\u003c/p\u003e\n\u003cp\u003eOnce we all realize what is happening, we\u0026rsquo;re going to spend the next decade trying to excise this stuff. And we\u0026rsquo;re not going to be able to use AI tools to help us do it.\u003c/p\u003e\n\u003ch2 id=\"example-code-generated-by-claude-37-on-2025-03-24\"\u003eExample code generated by Claude 3.7 on 2025-03-24\u003c/h2\u003e\n\u003cp\u003ePrompt: \u003ccode\u003eGenerate a Python function that uses the Crossref API to get all the records that were indexed on 2024-01-01.\u003c/code\u003e\u003c/p\u003e\n\n            \u003clink rel=\"stylesheet\" href=\"/css/vendors/admonitions.4fd9a0b8ec8899f2ca952048d255a569f433f77dfb3f52f5bc87e7d65cdce449.css\" integrity=\"sha256-T9mguOyImfLKlSBI0lWlafQz9337P1L1vIfn1lzc5Ek=\" crossorigin=\"anonymous\"\u003e\n    \u003cdiv class=\"admonition danger\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 32c14.2 0 27.3 7.5 34.5 19.8l216 368c7.3 12.4 7.3 27.7 .2 40.1S486.3 480 472 480L40 480c-14.3 0-27.6-7.7-34.7-20.1s-7-27.8 .2-40.1l216-368C228.7 39.5 241.8 32 256 32zm0 128c-13.3 0-24 10.7-24 24l0 112c0 13.3 10.7 24 24 24s24-10.7 24-24l0-112c0-13.3-10.7-24-24-24zm32 224a32 32 0 1 0 -64 0 32 32 0 1 0 64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eBroken code below\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThankfully the code below will only generate one request and fail emediately with a \u003ccode\u003e400\u003c/code\u003e error because it has used the wrong \u003ccode\u003efilter\u003c/code\u003e parameters. But \u003cem\u003ehad\u003c/em\u003e it created a correct request, the script would have never exited and would have kept requesting the same URL from the Crossref API forever because it has made an erroneous assumption about how \u003ccode\u003ecursors\u003c/code\u003e work in the API. Also note that, though it at least includes user-agent information, it has simplistic rate-limiting and no mechanisms for backing-off when it encounters errors.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eResults:\u003c/p\u003e\n\u003cdiv class=\"highlight\"\u003e\u003cpre tabindex=\"0\" class=\"chroma\"\u003e\u003ccode class=\"language-python\" data-lang=\"python\"\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"kn\"\u003eimport\u003c/span\u003e \u003cspan class=\"nn\"\u003erequests\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"kn\"\u003eimport\u003c/span\u003e \u003cspan class=\"nn\"\u003etime\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"kn\"\u003efrom\u003c/span\u003e \u003cspan class=\"nn\"\u003edatetime\u003c/span\u003e \u003cspan class=\"kn\"\u003eimport\u003c/span\u003e \u003cspan class=\"n\"\u003edatetime\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"k\"\u003edef\u003c/span\u003e \u003cspan class=\"nf\"\u003eget_crossref_records_by_indexed_date\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003edate_str\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003eemail\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"kc\"\u003eNone\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003erows_per_page\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"mi\"\u003e1000\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003emax_records\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"kc\"\u003eNone\u003c/span\u003e\u003cspan class=\"p\"\u003e):\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"s2\"\u003e\u0026#34;\u0026#34;\u0026#34;\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e    Retrieve records indexed by Crossref on a specific date using the Crossref API.\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e    Args:\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e        date_str (str): Date in YYYY-MM-DD format (e.g., \u0026#39;2024-01-01\u0026#39;)\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e        email (str, optional): Email address for polite API use\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e        rows_per_page (int, optional): Number of records per page (default 1000, max 1000)\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e        max_records (int, optional): Maximum number of records to retrieve (None for all)\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e    Returns:\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e        list: List of Crossref record dictionaries\n\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"s2\"\u003e    \u0026#34;\u0026#34;\u0026#34;\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Base URL for Crossref API\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003ebase_url\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"s2\"\u003e\u0026#34;https://api.crossref.org/works\u0026#34;\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Validate date format\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"k\"\u003etry\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003edatetime\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003estrptime\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003edate_str\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"s1\"\u003e\u0026#39;%Y-%m-\u003c/span\u003e\u003cspan class=\"si\"\u003e%d\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"k\"\u003eexcept\u003c/span\u003e \u003cspan class=\"ne\"\u003eValueError\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"k\"\u003eraise\u003c/span\u003e \u003cspan class=\"ne\"\u003eValueError\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Incorrect date format, should be YYYY-MM-DD\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Construct filter for indexed date\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003efilter_param\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;indexed:\u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003edate_str\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Set up headers with user agent (best practice for Crossref API)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003eheaders\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"p\"\u003e{\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;User-Agent\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;PythonCrossrefClient/1.0 (Python Script; \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u0026#34;\u003c/span\u003e \u003cspan class=\"k\"\u003eif\u003c/span\u003e \u003cspan class=\"n\"\u003eemail\u003c/span\u003e \u003cspan class=\"ow\"\u003eis\u003c/span\u003e \u003cspan class=\"kc\"\u003eNone\u003c/span\u003e \u003cspan class=\"k\"\u003eelse\u003c/span\u003e \u003cspan class=\"n\"\u003eemail\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s1\"\u003e)\u0026#39;\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"p\"\u003e}\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Parameters for the API request\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003eparams\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"p\"\u003e{\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;filter\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"n\"\u003efilter_param\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;rows\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"n\"\u003erows_per_page\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;cursor\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"s1\"\u003e\u0026#39;*\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e  \u003cspan class=\"c1\"\u003e# Start cursor\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;sort\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"s1\"\u003e\u0026#39;indexed\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e  \u003cspan class=\"c1\"\u003e# Sort by indexed date\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"s1\"\u003e\u0026#39;order\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e \u003cspan class=\"s1\"\u003e\u0026#39;asc\u0026#39;\u003c/span\u003e  \u003cspan class=\"c1\"\u003e# Ascending order\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"p\"\u003e}\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003eall_records\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"p\"\u003e[]\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003epage_count\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"mi\"\u003e0\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"k\"\u003ewhile\u003c/span\u003e \u003cspan class=\"kc\"\u003eTrue\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Make the API request\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003eresponse\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003erequests\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003ebase_url\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003eparams\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"n\"\u003eparams\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003eheaders\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"n\"\u003eheaders\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Check for successful response\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"k\"\u003eif\u003c/span\u003e \u003cspan class=\"n\"\u003eresponse\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003estatus_code\u003c/span\u003e \u003cspan class=\"o\"\u003e!=\u003c/span\u003e \u003cspan class=\"mi\"\u003e200\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Error: API request failed with status code \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003eresponse\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003estatus_code\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Response text: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003eresponse\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003etext\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"k\"\u003ebreak\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Parse the JSON response\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003edata\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003eresponse\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003ejson\u003c/span\u003e\u003cspan class=\"p\"\u003e()\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Get the records from the current page\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003eitems\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003edata\u003c/span\u003e\u003cspan class=\"p\"\u003e[\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;message\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e][\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;items\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e]\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Add items to our collection\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eextend\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003eitems\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003epage_count\u003c/span\u003e \u003cspan class=\"o\"\u003e+=\u003c/span\u003e \u003cspan class=\"mi\"\u003e1\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Retrieved page \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003epage_count\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e, \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"nb\"\u003elen\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003eitems\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e records. Total: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"nb\"\u003elen\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Check if we\u0026#39;ve reached the maximum records limit\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"k\"\u003eif\u003c/span\u003e \u003cspan class=\"n\"\u003emax_records\u003c/span\u003e \u003cspan class=\"ow\"\u003eis\u003c/span\u003e \u003cspan class=\"ow\"\u003enot\u003c/span\u003e \u003cspan class=\"kc\"\u003eNone\u003c/span\u003e \u003cspan class=\"ow\"\u003eand\u003c/span\u003e \u003cspan class=\"nb\"\u003elen\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e \u003cspan class=\"o\"\u003e\u0026gt;=\u003c/span\u003e \u003cspan class=\"n\"\u003emax_records\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"n\"\u003eall_records\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\u003cspan class=\"p\"\u003e[:\u003c/span\u003e\u003cspan class=\"n\"\u003emax_records\u003c/span\u003e\u003cspan class=\"p\"\u003e]\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"k\"\u003ebreak\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Get the next cursor from the response\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003enext_cursor\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003edata\u003c/span\u003e\u003cspan class=\"p\"\u003e[\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;message\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e]\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;next-cursor\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# If there\u0026#39;s no next cursor, we\u0026#39;ve reached the end\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"k\"\u003eif\u003c/span\u003e \u003cspan class=\"ow\"\u003enot\u003c/span\u003e \u003cspan class=\"n\"\u003enext_cursor\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e  \u003cspan class=\"c1\"\u003e# \u0026lt;---- Argh- NO! This is wrong!\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e            \u003cspan class=\"k\"\u003ebreak\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Update the cursor parameter for the next request\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003eparams\u003c/span\u003e\u003cspan class=\"p\"\u003e[\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;cursor\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e]\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003enext_cursor\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"c1\"\u003e# Be nice to the API with a small delay between requests\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"n\"\u003etime\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003esleep\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"mi\"\u003e1\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Total records retrieved: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"nb\"\u003elen\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"k\"\u003ereturn\u003c/span\u003e \u003cspan class=\"n\"\u003eall_records\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"c1\"\u003e# Example usage\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\u003cspan class=\"k\"\u003eif\u003c/span\u003e \u003cspan class=\"vm\"\u003e__name__\u003c/span\u003e \u003cspan class=\"o\"\u003e==\u003c/span\u003e \u003cspan class=\"s2\"\u003e\u0026#34;__main__\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e:\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Get records indexed on January 1, 2024\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Add your email for polite API use\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"n\"\u003erecords\u003c/span\u003e \u003cspan class=\"o\"\u003e=\u003c/span\u003e \u003cspan class=\"n\"\u003eget_crossref_records_by_indexed_date\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;2024-01-01\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003eemail\u003c/span\u003e\u003cspan class=\"o\"\u003e=\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;your.email@example.com\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"c1\"\u003e# Print some information about the first few records\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e    \u003cspan class=\"k\"\u003efor\u003c/span\u003e \u003cspan class=\"n\"\u003ei\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"n\"\u003erecord\u003c/span\u003e \u003cspan class=\"ow\"\u003ein\u003c/span\u003e \u003cspan class=\"nb\"\u003eenumerate\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"n\"\u003erecords\u003c/span\u003e\u003cspan class=\"p\"\u003e[:\u003c/span\u003e\u003cspan class=\"mi\"\u003e5\u003c/span\u003e\u003cspan class=\"p\"\u003e]):\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"se\"\u003e\\n\u003c/span\u003e\u003cspan class=\"s2\"\u003eRecord \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003ei\u003c/span\u003e\u003cspan class=\"o\"\u003e+\u003c/span\u003e\u003cspan class=\"mi\"\u003e1\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e:\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;DOI: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003erecord\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;DOI\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Title: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003erecord\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;title\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"p\"\u003e[\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;No title\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e])[\u003c/span\u003e\u003cspan class=\"mi\"\u003e0\u003c/span\u003e\u003cspan class=\"p\"\u003e]\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Type: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003erecord\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;type\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003cspan class=\"line\"\u003e\u003cspan class=\"cl\"\u003e        \u003cspan class=\"nb\"\u003eprint\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"sa\"\u003ef\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;Indexed: \u003c/span\u003e\u003cspan class=\"si\"\u003e{\u003c/span\u003e\u003cspan class=\"n\"\u003erecord\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;indexed\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e,\u003c/span\u003e \u003cspan class=\"p\"\u003e{})\u003c/span\u003e\u003cspan class=\"o\"\u003e.\u003c/span\u003e\u003cspan class=\"n\"\u003eget\u003c/span\u003e\u003cspan class=\"p\"\u003e(\u003c/span\u003e\u003cspan class=\"s1\"\u003e\u0026#39;date-time\u0026#39;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\u003cspan class=\"si\"\u003e}\u003c/span\u003e\u003cspan class=\"s2\"\u003e\u0026#34;\u003c/span\u003e\u003cspan class=\"p\"\u003e)\u003c/span\u003e\n\u003c/span\u003e\u003c/span\u003e\u003c/code\u003e\u003c/pre\u003e\u003c/div\u003e\u003cdiv class=\"footnotes\" role=\"doc-endnotes\"\u003e\n\u003chr\u003e\n\u003col\u003e\n\u003cli id=\"fn:1\"\u003e\n\u003cp\u003eYes, we could could have fixed this in the API. Don\u0026rsquo;t get me started.\u0026#160;\u003ca href=\"#fnref:1\" class=\"footnote-backref\" role=\"doc-backlink\"\u003e\u0026#x21a9;\u0026#xfe0e;\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003c/div\u003e\n","date_modified":"2025-04-02T00:00:00Z","date_published":"2025-04-02T00:00:00Z","id":"https://doi.org/10.59347/w366z-egx85","summary":"I've seen an uptick in people I respect concluding that the massive increase in badly-behaved web-scraping bot is intentional and just another example of sociopathic AI companies ripping-up long-respected web conventions for the sake of profit","tags":["web-scraping","bots","AI"],"title":"Bots Behaving Badly","url":"https://gbilder.com/posts/2025-04-02-bots-behaving-badly/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/marseilles.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2025, March 28).\n      \n      \u003ci\u003eTomorrow\u0026#39;s ScholComm Headlines: Predictions from 2023\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/shh81-rbh77\"\u003e\n      https://doi.org/10.59347/shh81-rbh77\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003cp\u003eI recently ran across a screenshot from November 2023.\u003c/p\u003e\n\u003cfigure class=\"align-center \"\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/slack-2023-11-16.jpeg#center\"\n         alt=\"Screenshot of Slack message that reads- Only five surviving research universities in the US after President Trump and Congress cut all non-military research funding. CNRI forced by a court order to block all DOl resolutions \u0026#39;woke science\u0026#39; and publications by non-US authors. We visited the US\u0026#39;s last public library in Barrington, Vermont.\" width=\"350\"/\u003e \n\u003c/figure\u003e\n\n\u003ch3 id=\"background\"\u003eBackground\u003c/h3\u003e\n\u003cp\u003eOne of our product managers was a representative on the \u003ca href=\"https://stm-assoc.org/what-we-do/strategic-areas/standards-technology/future-lab/\"\u003eSTM Future Lab\u003c/a\u003e group. They had been asked to predict the ScholComm headlines in a few years time— and so they checked if their colleagues had any ideas. There were a few safe (albeit depressing) predictions based on clear trends (e.g. an AI-generated paper gets accepted to a prestigious journal, more “paper mills\u0026quot; appear, more bulk retractions are issued).\u003c/p\u003e\n\u003cp\u003eThe above was my take. As I recall, most people thought it was pretty unrealistic. I don’t think it was ever presented to STM.\u003c/p\u003e\n\u003cp\u003eAt least by posting it here, it gets a DOI via \u003ca href=\"https://rogue-scholar.org\"\u003eRogue Scholar\u003c/a\u003e— and we can wait to see if/when it gets blocked.\u003c/p\u003e\n\u003cp\u003eI\u0026rsquo;ve been concerned about the concentration of critical open scholarly infrastructure in the US for over a decade. I have ideas. And more. If you\u0026rsquo;re also concerned \u003cem\u003eand\u003c/em\u003e are in a position to help people do something about it, \u003ca href=\"https://gbilder.com/about/\"\u003eget in touch\u003c/a\u003e.\u003c/p\u003e\n","date_modified":"2025-03-28T00:00:00Z","date_published":"2025-03-28T00:00:00Z","id":"https://doi.org/10.59347/shh81-rbh77","summary":"My 2023 predictions on the ScholComm headlines in a few years","title":"Tomorrow's ScholComm Headlines: Predictions from 2023","url":"https://gbilder.com/posts/2025-03-28-stm-predictions/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/peace.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2025, March 5).\n      \n      \u003ci\u003eComments on Proposed POSI 2.0 Revisions\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/tph3y-tkf88\"\u003e\n      https://doi.org/10.59347/tph3y-tkf88\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003ch2 id=\"background\"\u003eBackground\u003c/h2\u003e\n\u003cp\u003eOn January 22, the POSI Adopters\u003csup id=\"fnref:1\"\u003e\u003ca href=\"#fn:1\" class=\"footnote-ref\" role=\"doc-noteref\"\u003e1\u003c/a\u003e\u003c/sup\u003e called for feedback on their Proposed POSI 2.0 revisions.\u003c/p\u003e\n\u003cp\u003eIn case you are not familiar with \u003ca href=\"https://openscholarlyinfrastructure.org\"\u003eThe Principles of Open Scholarly Infrastructure\u003c/a\u003e (POSI) , they are essentially a \u0026ldquo;\u003ca href=\"https://en.wikipedia.org/wiki/Ulysses_pact\"\u003eUlysses Pact\u003c/a\u003e\u0026rdquo; that aims to make it harder for organizations to \u0026ldquo;\u003ca href=\"https://en.wiktionary.org/wiki/enshittification\"\u003eenshitify\u003c/a\u003e\u0026rdquo; essential  scholarly infrastructure.\u003c/p\u003e\n\u003cp\u003eAs a coauthor of the \u003ca href=\"https://doi.org/10.6084/m9.figshare.1314859.v1\"\u003eoriginal Principles\u003c/a\u003e, I want to see POSI adapt to address the ever-evolving challenge of preventing the commons from being enclosed for commercial exploitation or turned into exclusively \u003ca href=\"https://en.wikipedia.org/wiki/Club_good\"\u003eclub goods\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eThis is largely why my coauthors and I handed them off to the community care of the open and transparent “POSI Adopters.”\u003c/p\u003e\n\u003cp\u003eAnd though I am not affiliated with any members of the POSI adopters anymore, you might not be surprised to know that I have opinions.\u003c/p\u003e\n\u003cp\u003eThe POSI Adopters asked the public to submit their comments via a web form, which I have done.\u003c/p\u003e\n\u003cp\u003eIt is a pity that the POSI Apopters did not provide a venue where the public could have commented on the proposals and discussed them more openly.\u003c/p\u003e\n\u003cp\u003eBut at least I can post what I submitted. If anybody else made comments on the proposed POSI changes, I\u0026rsquo;d encourage them to make them public as well.\u003c/p\u003e\n\u003cp\u003eTo make it easy to follow, I have copied the text of each of the proposed revisions and then commented on them afterwards.\u003c/p\u003e\n\u003cp\u003eMy comments  appear in notes like this:\u003c/p\u003e\n\n            \u003clink rel=\"stylesheet\" href=\"/css/vendors/admonitions.4fd9a0b8ec8899f2ca952048d255a569f433f77dfb3f52f5bc87e7d65cdce449.css\" integrity=\"sha256-T9mguOyImfLKlSBI0lWlafQz9337P1L1vIfn1lzc5Ek=\" crossorigin=\"anonymous\"\u003e\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eMy comments\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eAfter my comments on all the specific proposals,  I make some additional suggestions.\u003c/p\u003e\n\u003ch2 id=\"the-proposed-20-revisions-and-commentary\"\u003eThe Proposed 2.0 revisions and commentary\u003c/h2\u003e\n\u003ch4 id=\"scope-and-application-to-types-of-organizations\"\u003eScope and Application to Types of Organizations\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cp\u003eReview the principles to ensure they are appropriately scoped and applicable to different types of organizations (e.g. government agencies, a department that is part of a larger organization) and initiatives and provide guidance on how organizations and initiatives can indicate when certain principles don’t apply and how this affects the self-assessment.\u003c/p\u003e\n\u003ch5 id=\"notes\"\u003eNotes:\u003c/h5\u003e\n\u003cp\u003e● Consider whether the principles are general enough to be relevant for a range of different types of organizations and initiatives (e.g. volunteer supported services, services that are part of a larger organization, government agencies, or standards organizations.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThe most frequent concerns I’ve encountered in this context are:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003ePOSI is overly focused on scholarly infrastructure; much of it could be adapted to general open infrastructure with some modifications.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003ePOSI is overly focused on membership organizations.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThere’s no reason why other industries can’t adopt POSI to suit their needs. POSI adopters might even be willing to provide guidance. However, it’s already challenging to make POSI applicable to the diverse range of players in scholarly communication. I’m concerned that attempting to expand it further could either make it overly complex, too ambiguous, or both.\u003c/p\u003e\n\u003cp\u003eInitially, I was sympathetic to the second concern. It’s undeniable that the original principles were primarily written by people familiar with “membership organizations.” Consequently, many of the examples we highlight (particularly in the original blog post) are related to membership organizations.\u003c/p\u003e\n\u003cp\u003eBut there are at least two senses of the words \u0026ldquo;member\u0026rdquo; and \u0026ldquo;membership\u0026rdquo;.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eImplicit membership\u003c/strong\u003e is categorical or statistical (you belong to a set by virtue of a characteristic, like pétanque enthusiasts)\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eExplicit membership\u003c/strong\u003e is formal and intentional (you actively join and are recognized as a member, like a pétanque club)\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eAnd if you examine the actual text of the principles, the word \u0026ldquo;membership\u0026rdquo; only appears three times- the first two times in the \u0026ldquo;implicit\u0026rdquo; sense (members of the scholarly community) and the third time in the \u0026ldquo;explicit\u0026rdquo; sense (as in \u0026ldquo;membership fees\u0026rdquo;). Even in the last case,  it is just providing one example of possible revenue sources that do not involve \u0026ldquo;charging for data.\u0026rdquo;\u003c/p\u003e\n\u003cp\u003eAnd the 1.1 revision made the issue even less of a concern by replacing the phrase \u0026ldquo;Non-discriminatory membership\u0026rdquo; with \u0026ldquo;Non-discriminatory participation or membership\u0026rdquo;\u003c/p\u003e\n\u003cp\u003eSo it isn\u0026rsquo;t really clear what text people find inapplicable to other organization types (the call for comments doesn\u0026rsquo;t really give examples) and, so I\u0026rsquo;ve come to think this concern is overblown.\nHaving said that, it might be useful if the POSI site provided a special section with examples of how current POSI adoptors have interpreted the principles for their particular contexts.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"add-a-distinct-principle-on-transparent-operations-to-distinguish-it-from-transparent-governance-and-clarify-that-transparent-governance-involves-openly-providing-documents-and-policies\"\u003eAdd a distinct principle on Transparent Operations to distinguish it from Transparent Governance, and clarify that transparent governance involves openly providing documents and policies\u003c/h4\u003e\n\u003cp\u003eProposed Change/Modification:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eAdd a distinct principle about transparent operations to distinguish it from transparent governance. Define what is meant by transparent operations.\u003c/li\u003e\n\u003cli\u003eClarify that transparent governance includes making governing documents and policies open [sic] available.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-1\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eTransparent governance refers to the openness in the decision-making processes, governance structure, selecting representatives for governance and the mechanisms of how decisions are made. For example, this could include making governance documents\n(e.g. bylaws, articles of incorporation, mission statements, board meeting summaries and\napproved motions), and policies and procedures (e.g. election processes) openly available.\u003c/li\u003e\n\u003cli\u003eTransparent operations could encompass aspects like making detailed financials, fees, business models, operating policies and procedures, and strategic and product roadmaps openly available.\u003c/li\u003e\n\u003cli\u003eConsider how the principle can help demonstrate organizational accountability and openness in day-to-day operations.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThe 1.1 revisions of POSI created a regression, so this can largely be resolved by reverting to the original text of the 1.0 principle.\u003c/p\u003e\n\u003cp\u003eIn the 1.0 version of the principles, under the \u003cem\u003eGovernance\u003c/em\u003e section, there was the principle that read:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u003cstrong\u003eTransparent operations\u003c/strong\u003e\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eThis was modified in the 1.1 revisions to read:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u003cstrong\u003eTransparent governance\u003c/strong\u003e\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eWhich effectively made the entire section only about governance instead of about governance \u003cem\u003eand\u003c/em\u003e operations.\u003c/p\u003e\n\u003cp\u003eThis is one of several instances where the 1.1 revisions have made POSI less clear and more contentious. Another notable example is where the phrase:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e“data related to the running of the research enterprise should be community property”\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003ewas replaced with:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e“data related to the running of the scholarly infrastructure should be community property.”\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eAs ORCID correctly pointed out, the latter could potentially encompass purely operational (and often private) data, such as HR records, passwords, and so on. This, of course, is not what was intended.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"clarify-and-strengthen-the-principle-of-the-living-will\"\u003eClarify and strengthen the Principle of the Living Will\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-1\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eClarify this principle so that it applies not just when an organization is wound down but to any transfer of assets, data and services to another organization whether planned or not.\u003c/li\u003e\n\u003cli\u003eClarify this principle to encourage organizations to constrain the types of successor organizations they are able to transfer operations and assets to, or to highlight how these restrictions apply to the type of legal entity they are.\u003c/li\u003e\n\u003cli\u003eStrengthen this principle with more detail about how successor organizations should be defined and whether dissolution and liquidation clauses are necessary.\u003c/li\u003e\n\u003cli\u003eClarify this principle by providing more details of what a “Living Will” should include and\nexamples of existing plans.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-2\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eThis principle aims to promote transparency and preparedness, ensuring stakeholders are aware of the conditions that would lead to an organization’s closure and how assets would be managed.\u003c/li\u003e\n\u003cli\u003eA comment from the feedback on the 1.1 revision of the principles suggested the principles include a dissolution and liquidation clause similar to: \u0026ldquo;In case of liquidation, the assets can only be distributed to another non-profit entity without private shareholders, who have a similar dissolution and liquidation clause.\u0026rdquo;\u003c/li\u003e\n\u003cli\u003eThere are different ways this principle can be met. Certain types of organizations will be subject to laws requiring that assets be dispersed to another non-profit with a similar mission. However, a clear statement on dissolution and liquidation in bylaws, consistent with the governing law of an organization, would be useful.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThe primary concern here is that a POSI-endorsing organization might transfer its assets to a non-POSI endorsing entity that could subsequently enclose them.\u003c/p\u003e\n\u003cp\u003eThis is a certainly a risk that should be addressed, but it is also an opportunity for POSI to highlight that, if an organization has at least met three of the principles for POSI compliance:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eopen data\u003c/li\u003e\n\u003cli\u003eopen source\u003c/li\u003e\n\u003cli\u003eopen patents\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003ethen this \u0026ldquo;enclosure-through-transfer-or-inheritance\u0026rdquo; scenario becomes virtually impossible because the community can always choose to “\u003ca href=\"https://en.wikipedia.org/wiki/Fork_%28software_development%29\"\u003efork\u003c/a\u003e” the infrastructure.\u003c/p\u003e\n\u003cp\u003eIn this respect, POSI serves as a “\u003ca href=\"https://www.investopedia.com/terms/p/poisonpill.asp\"\u003epoison pill\u003c/a\u003e,” making it highly undesirable for hostile takeovers or inheritances.\u003c/p\u003e\n\u003cp\u003eYes, there are still certain assets that the community would not be able to take with them when forking, such as “domain names,” “trademarks,” and “private data.” However, this is also true of large open source projects, and these limitations have not prevented forks of numerous significant open source projects (e.g., OpenOffice-\u0026gt;LibraOffice, Redis-\u0026gt;Valkey, ElasticSearch-\u0026gt;OpenSearch, MySQL-\u0026gt;MariaDB, Terraform-\u0026gt;OpenTofu).\u003c/p\u003e\n\u003cp\u003eSo yes, it seems useful for POSI to define principles around successor organizations and the transfer of assets in order to constrain the behavior of adopters who haven’t yet met the commitments to open data, open source, and open patents.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"formal-incentives-to-fulfill-mission-and-wind-down\"\u003eFormal Incentives to Fulfill Mission and Wind Down\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-2\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eRevise this principle to focus on organizations and initiatives regularly reviewing their value to the community to assess if they are still necessary.\u003c/li\u003e\n\u003cli\u003eRemove the reference to “direct incentives to deliver on the mission and wind down”\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-3\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eThere is some skepticism about the practicality of this principle, as it’s unclear what formal incentives would encourage an organization to cease operations voluntarily.\u003c/li\u003e\n\u003cli\u003eMany adopters have interpreted this as the need to regularly review community demand for their services and committing to not “outstay their welcome” should demand no longer exist.\u003c/li\u003e\n\u003cli\u003eFeedback with any examples of formal or direct incentives for an organization to fulfill its mission and wind down is welcome.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eAnybody who has tried to setup a new infrastructure organization will have met a common and understandable concern amongst those who would be on the hook to fund it- a concern that is often referred as \u0026ldquo;\u003ca href=\"https://medium.com/@mesw1/the-shirky-principle-791046584763#:~:text=The%20Shirky%20Principle%20states,%20%E2%80%9CInstitutions,end%20up%20maintaining%20or%20even\"\u003eThe Shirky principle\u003c/a\u003e\u0026rdquo;\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003einstitutions will try to preserve the problem to which they are the solution\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eAnd in the case of mission-driven organizations, this can seem particularly pernicious because it means that, at some level, they have an interest in never fulfilling their mission.\u003c/p\u003e\n\u003cp\u003eSo funders are understandably cautious about committing to funding something that might last \u0026ldquo;forever.\u0026rdquo;\u003c/p\u003e\n\u003cp\u003eBut the problem with the Shirky formulation (and variations of it \u003csup id=\"fnref:2\"\u003e\u003ca href=\"#fn:2\" class=\"footnote-ref\" role=\"doc-noteref\"\u003e2\u003c/a\u003e\u003c/sup\u003e) is that it makes the dynamic sound sinister when there it is in fact driven by entirely innocent, human, and altruistic concerns.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eWe don\u0026rsquo;t want to fire colleagues and friends whose livelihood depends on the organization’s existence.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eWe don\u0026rsquo;t want to lose our own jobs.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIt is a case of perverse incentives.\u003c/p\u003e\n\u003cp\u003eSo one of the core ideas behind POSI was to try to encourage a humble organizational culture that recognized its mission was always more important than its existence.\u003c/p\u003e\n\u003cp\u003eThe notes on the proposed POSI revision state that there is \u0026ldquo;skepticism about the practicality of this principle, as it’s unclear what formal incentives would encourage an organization to cease operations voluntarily\u0026rdquo;.\u003c/p\u003e\n\u003cp\u003eFirst, we should challenge the idea that just because we don\u0026rsquo;t know how to do it yet, it should not be in the POSI principles.\u003c/p\u003e\n\u003cp\u003eTo be blunt, we don\u0026rsquo;t have good examples of widely replicable sustainability models for open scholarly infrastructure either.\u003c/p\u003e\n\u003cp\u003eAnd we also don\u0026rsquo;t have examples of un-subvertible governance structures for organizations.\u003c/p\u003e\n\u003cp\u003eI could go on.\u003c/p\u003e\n\u003cp\u003ePart of the point of POSI is for the open infrastructure community to directly acknowledge and address these challenges instead of pretending they don\u0026rsquo;t exist.\u003c/p\u003e\n\u003cp\u003eBut back to the question: \u0026ldquo;What are examples of formal incentives that would encourage organizations to cease operations voluntarily?\u0026rdquo;\u003c/p\u003e\n\u003cp\u003ePay them to.\u003c/p\u003e\n\u003cp\u003eIntroduce internal incremental reward structures that encourage staff to continually identify and remove accidental complexity and services that have ceased to contribute meaningfully to the mission.\u003c/p\u003e\n\u003cp\u003eOr more radically\u0026hellip;\u003c/p\u003e\n\u003cp\u003eGuarantee each employee a year of salary should they collectively manage to figure out how to solve the problem the organization was designed to solve without needing the organization.\u003c/p\u003e\n\u003cp\u003eHow?\u003c/p\u003e\n\u003cp\u003eUse the contingency fund.\u003c/p\u003e\n\u003cp\u003eOr maybe work with funders to collectively build a mission-completion bounty fund?\u003c/p\u003e\n\u003cp\u003eThe point is that the tendency toward institutional self-preservation is a valid concern.\u003c/p\u003e\n\u003cp\u003eCommercial organizations have a perpetual reason to exist— which is to return a profit to their investors. They have incentives to encourage this.\u003c/p\u003e\n\u003cp\u003eNon-profit, mission-driven organizations should not have incentives to exist in perpetuity. And they should have incentives to discourage it.\u003c/p\u003e\n\u003cp\u003eIt is important that POSI retain this principle. We might not know how to do this at the moment, but by keeping this in the principles it forces us to think about the problem instead of ignoring it.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch5 id=\"expanding-the-concept-of-resources-in-the-sustainability-section-to-includevolunteers\"\u003eExpanding the Concept of Resources in the Sustainability Section to IncludeVolunteers\u003c/h5\u003e\n\u003ch5 id=\"proposed-changemodification-3\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eAdd a separate principle to address volunteer (and other in-kind) resources, not just financial resources.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-4\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eFor organizations that rely heavily on volunteers, these individuals are a critical resource that should be recognized in sustainability planning.\u003c/li\u003e\n\u003cli\u003eAcknowledging volunteers as a key resource emphasizes the importance of maintaining and supporting this workforce as part of the organization\u0026rsquo;s long-term viability.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThis is a good idea. It is particularly important to document the role of volunteers in sustaining infrastructure organizations because:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eIt highlights otherwise invisible labor\u003c/li\u003e\n\u003cli\u003eVolunteer labor is an important source of risk (e.g. burnout, changing economic conditions that discourage volunteering)\u003c/li\u003e\n\u003cli\u003eReliance on volunteer labor can reduce diversity of stakeholder participation (e.g. unpaid intern syndrome). It would be useful if POSI also encouraged organizations to document what they do to mitigate this danger (e.g. offer stipends, training, etc.)\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003ePOSI should also call on organizations to highlight other labor dependencies that are typically not documented. For example:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eReliance on employees who are on short-term contracts\u003c/li\u003e\n\u003cli\u003eReliance on contractors\u003c/li\u003e\n\u003cli\u003eReliance on intermediaries (e.g. sponsoring organizations, service providers, aggregators )\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eAll of these working arrangements can obscure the true costs and risks associated of running infrastructure.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"clarify-time-limited-funds-are-used-only-for-time-limited-activities-to-account-for-the-length-of-time-that-it-can-take-to-reach-sustainability\"\u003eClarify “Time-Limited Funds are Used Only for Time-Limited Activities” to account for the length of time that it can take to reach sustainability\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-4\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cp\u003e● Clarify the principle, or add information to the FAQ, to clarify that it can take a long time to reach financial sustainability and that time-limited funds could be used to build capacity or implement a sustainability model.\u003c/p\u003e\n\u003ch5 id=\"notes-5\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eThere are multiple paths to financial sustainability and time-limited funds like grants can be used for building capacity to reach sustainability and that this process can take a long time.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eIt’s unclear why financial sustainability is being singled out here, as it may take considerable time to fulfill \u003cstrong\u003eany\u003c/strong\u003e of the POSI commitments. Different organizations will face varying challenges in meeting these commitments. For instance, Crossref has met its financial commitments but has yet to fully open-source its code due to the size, age and complexity of its codebase.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"goal-to-create-financial-reserves-should-call-for-there-to-be-a-policy-for-the-level-of-reserves\"\u003e“Goal to Create Financial Reserves” should call for there to be a policy for the level of reserves\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-5\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eClarify the principle to call for a policy on the level of financial reserves with the actual level of reserves determined by the organization\u0026rsquo;s or initiative\u0026rsquo;s governing body .\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-6\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eOrganizations, initiatives and services vary greatly in their size and scope and policies on financial reserves should reflect this.\u003c/li\u003e\n\u003cli\u003eSpecifying a fixed amount for reserves is too inflexible.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThe most important thing for POSI to highlight is that conventions that might apply for standard commercial and non-profit organizations are almost certainly not appropriate for infrastructure organizations.\u003c/p\u003e\n\u003cp\u003eThe reason for this is simple: an infrastructure organization, by definition, will have other organizations dependent on it. Furthermore, infrastructure  functionality is likely to be deeply embedded in the systems of those dependent organizations.\u003c/p\u003e\n\u003cp\u003eSo we are not talking just about giving the infrastructure organization enough time to wind down; we are talking about giving the community that depends on said infrastructure enough time to extricate itself from dependency on said infrastructure.\u003c/p\u003e\n\u003cp\u003eThis is why, in the  original POSI principles, we suggested a year as an example timeline when the convention for many other organizations is often between three and six months.\u003c/p\u003e\n\u003cp\u003eWe heard several jeremiads about how \u0026ldquo;one year was too long,\u0026rdquo; but frankly, given the ubiquity of some of the infrastructure organizations that have adopted POSI, one year is probably way too short.\u003c/p\u003e\n\u003cp\u003eIn any case, the principles are supposed to be principles— so , yes, each organization should pick an appropriate time scale. But POSI itself should emphasize that the expectations for winding down infrastructure are fundamentally different than those for other kinds of organizations.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"addition-of-separate-item-on-interoperability-and-open-standards-under-insurance\"\u003eAddition of Separate Item on Interoperability and Open Standards Under \u0026lsquo;Insurance\u0026rsquo;\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-6\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eAdd a separate principle addressing interoperability and open standards (both de facto and formal) within the \u0026ldquo;Insurance\u0026rdquo; section.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-7\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eInteroperability and open standards are critical for ensuring that various scholarly systems and organizations can work together seamlessly. This addition would formalize the expectation that organizations maintain or work towards interoperability.\u003c/li\u003e\n\u003cli\u003eThis principle needs to recognize that “interoperability” can be a vague term so it\u0026rsquo;s important to provide some clarity about what it means in the POSI context.\u003c/li\u003e\n\u003cli\u003eThis principle could also emphasize the importance of adhering to community standards (both de facto and formal) to ensure compatibility and integration with other open infrastructures.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eIt is encouraging to see that this proposal presents \u0026lsquo;\u0026ldquo;de facto\u0026rdquo; and \u0026ldquo;formal\u0026rdquo; standards on an equal footing.\u003c/p\u003e\n\u003cp\u003eThis is important because formal standards processes, particularly, can be dominated by commercial organizations to achieve regulatory lock-in and hinder the ability of smaller, non-profit organizations to provide infrastructure services. Commercial organizations have mastered the art of convening “\u003ca href=\"https://en.wikipedia.org/wiki/Bootleggers_and_Baptists\"\u003eBootleggers and Baptists\u003c/a\u003e,” into standards forums to create exceedingly complex standards that, while open, are challenging to implement without the expertise of numerous experts and developers. The accumulation of these standards and their integration into national procurement policies have made it extremely difficult for new entrants to compete in offering infrastructure services.\u003c/p\u003e\n\u003cp\u003eI do wonder, though, if POSI really even needs to mention standards? I suspect that the primary concern that people have is that \u0026ldquo;open source\u0026rdquo; and \u0026ldquo;open data\u0026rdquo; can turn out to be unusable without documentation. And the typical formal standards process at least produces some documentation. But couldn\u0026rsquo;t POSI address this by simply amending the existing language around \u0026ldquo;open source\u0026rdquo; and \u0026ldquo;open data\u0026rdquo; to read \u0026ldquo;open and documented source\u0026rdquo; and \u0026ldquo;open and documented data?\u0026rdquo;\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"clarify-open-data-within-constraints-of-privacy-laws-to-include-security-as-well-as-privacy-laws\"\u003eClarify “Open data (within constraints of privacy laws)” to include security as well as privacy laws.\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-7\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eClarify the principle to include security issues as well as privacy.\u003c/li\u003e\n\u003cli\u003eCall for organizations to have a policy on what happens to private data in the case of a transfer to another organization.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003ePOSI could use some explicit language on security, but it would be helpful if POSI provided examples of security concerns that might affect the ability of one to open data. The classic one is not wanting to reveal the migration patterns of endangered species.\u003c/p\u003e\n\u003cp\u003eOn the question of organizations having a policy on what happens to private data in the case of transfer to another organization, POSI should advocate two things:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eA strong and unequivocal prohibition of the transfer of private data in case of transfer to another organization.\u003c/li\u003e\n\u003cli\u003eA call for POSI compliance to include that organizations should have a convenient and free mechanism for participants  to export their private information into documented formats so that they can easily move it if they want to.\u003c/li\u003e\n\u003c/ol\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch4 id=\"clarify-available-data-to-call-for-data-to-be-deposited-with-a-3rd-party\"\u003eClarify “Available Data” to call for data to be deposited with a 3rd party\u003c/h4\u003e\n\u003ch5 id=\"proposed-changemodification-8\"\u003eProposed Change/Modification:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eClarify the principle to include a call for data to be archived with a 3rd party.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch5 id=\"notes-8\"\u003eNotes:\u003c/h5\u003e\n\u003cul\u003e\n\u003cli\u003eData should be deposited with a third party to ensure its availability if the original organization fails or its sustainability is in doubt.\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eNote\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eThis is a useful addition as long as it is not seen as a substitute for organizations making data broadly and openly available via periodic public data dumps.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch3 id=\"other-comments\"\u003eOther comments\u003c/h3\u003e\n\u003cp\u003eThe POSI principles have already been updated more often than most POSI adopters have updated their POSI self-audits.\u003c/p\u003e\n\u003cp\u003eAnybody who did not want to see POSI adoption expand could start seeding doubt in the community by saying “it isn’t really clear what you are signing up to when you adopt POSI because it keeps changing.”\u003c/p\u003e\n\u003cp\u003eI’ve also noted that the 1.1 revisions actually introduced some ambiguities in the text that this revision is now trying to fix.\u003c/p\u003e\n\u003cp\u003eIn other words, updating POSI is a delicate balance. It has to be done, but it has to be done carefully.\u003c/p\u003e\n\u003cp\u003eI assume that POSI adopters intend the version numbers to convey real information about the extent of the editorial differences between versions, and that it is not just a marketing device to rekindle interest in POSI. If so, then I think that giving the proposed changes a “2.0” designation is misleading because it implies that \u003ca href=\"https://semver.org\"\u003ethere are major new features\u003c/a\u003e in the proposed changes (which there are not)  - or worse- that it is not backward compatible with the previous versions of POSI (which isn\u0026rsquo;t true either). This, of course, would feed into the narrative of anybody who wants to portray POSI as volatile and therefore difficult to endorse.\u003c/p\u003e\n\u003cp\u003eThe call for comments on the proposed 2.0 revisions included the following \u0026ldquo;additional context around POSI”:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cul\u003e\n\u003cli\u003ePOSI is not an organization; POSI adopters are an informal group of those that have conducted self-assessments.\u003c/li\u003e\n\u003c/ul\u003e\u003c/blockquote\u003e\n\u003cblockquote\u003e\n\u003cul\u003e\n\u003cli\u003eThe POSI principles are not rules or a checklist; organizations or groups can adopt or interpret them to fit many different circumstances.\u003c/li\u003e\n\u003c/ul\u003e\u003c/blockquote\u003e\n\u003cblockquote\u003e\n\u003cul\u003e\n\u003cli\u003eOur goal is for POSI self-assessments to be made publicly available and for interested communities to assess and monitor updates and progress.\u003c/li\u003e\n\u003c/ul\u003e\u003c/blockquote\u003e\n\u003cp\u003eThis is  useful information.\u003c/p\u003e\n\u003cp\u003eI suspect that many people have more questions about the POSI adopters, the POSI site, and the expectations around the POSI audit process than they do about the text of the principles themselves.\u003c/p\u003e\n\u003cp\u003eAnd, unfortunately,  the POSI website has become less useful over the past two years. As of this writing (2025-03-05) , the single link to a feedback form has been broken for months, the dates on all the pages are clearly borked (Last modified on January 21, 212121), and, most worryingly, the list of POSI adopters and links to their self-audits is so out-of-date that it doesn’t even reflect that Crossref finally performed a third self-audit three months ago.\u003c/p\u003e\n\u003cp\u003eFrankly, if it were not for the comparatively recent call for comments on the proposed 2.0 revisions, it wouldn’t be clear if the POSI site was even still a going concern. That’s not a great way to increase adoption.\u003c/p\u003e\n\u003cp\u003eI suggest that, in addition to the proposed revision to the text of the principles, the POSI adopters also consider addressing some “meta” questions about the POSI’s presence, such as:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eDescribing the purpose of the POSI site and how it is managed.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eProminently highlighting the process of contacting existing POSI adopters for consultation.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eClarifying the role of POSI adopters in the ongoing stewardship of the principles.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eSetting clear expectations regarding the frequency of the POSI self-audit process.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIn any case, it’s good to see POSI adapt and refine the principles in order to remove rough edges and help new organizations adopt the principles without having to engage in a lengthy exegesis.\u003c/p\u003e\n\u003cdiv class=\"footnotes\" role=\"doc-endnotes\"\u003e\n\u003chr\u003e\n\u003col\u003e\n\u003cli id=\"fn:1\"\u003e\n\u003cp\u003eIt appears that the enemies of alliteration and lighthearted self-deprecation have started to eschew the use of “POSI Posse” in favour of “POSI Adopters”\u0026#160;\u003ca href=\"#fnref:1\" class=\"footnote-backref\" role=\"doc-backlink\"\u003e\u0026#x21a9;\u0026#xfe0e;\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli id=\"fn:2\"\u003e\n\u003cp\u003eUpton Sinclair’s “It is difficult to get a man to understand something when his salary depends upon his not understanding it!”\u0026#160;\u003ca href=\"#fnref:2\" class=\"footnote-backref\" role=\"doc-backlink\"\u003e\u0026#x21a9;\u0026#xfe0e;\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003c/div\u003e\n","date_modified":"2025-03-05T00:00:00Z","date_published":"2025-03-05T00:00:00Z","id":"https://doi.org/10.59347/tph3y-tkf88","summary":"The POSI Adopters1 called for feedback on their Proposed POSI 2.0 revisions. You might not be surprised to know that I have opinions.","title":"Comments on Proposed POSI 2.0 Revisions","url":"https://gbilder.com/posts/2025-03-05-comments-on-proposed-posi2-revisions/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/cdg-terminal-2f.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2025, January 25).\n      \n      \u003ci\u003eThe Developer Experience in Early 2025\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/8nwg7-hbh15\"\u003e\n      https://doi.org/10.59347/8nwg7-hbh15\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003cp\u003eImagine \u003ca href=\"https://en.wikipedia.org/wiki/Pair_programming#:~:text=Pair%20programming%20is%20a%20software,two%20programmers%20switch%20roles%20frequently.\"\u003epair programming\u003c/a\u003e with an eccentric software developer…\u003c/p\u003e\n\u003cp\u003eOK, good point—  I mean more eccentric than usual.\u003c/p\u003e\n\u003cp\u003e…anyway— they have fantastic long-term memory, but terrible short-term memory.\u003c/p\u003e\n\u003cp\u003eThey are polite to the point of obsequiousness.\u003c/p\u003e\n\u003cp\u003eThey can type thousands of words per second and they like to make fifty unrelated code changes at once.\u003c/p\u003e\n\u003cp\u003eThey can write the most complex algorithms flawlessly, yet they routinely forget to import required libraries.\u003c/p\u003e\n\u003cp\u003eThey take a shot of vodka every twenty minutes and get progressively drunker until they are practically paralytic and can\u0026rsquo;t remember a thing. You have to force them to take a nap and recover for a few hours before continuing with your pair programming.\u003c/p\u003e\n\u003cp\u003eAfter a few days of this— you  ask the programmer to pin some notes to their monitor which say things like:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e“remember you are working on project X”\u003c/li\u003e\n\u003cli\u003e“only change one function at a time, then ask for advice”\u003c/li\u003e\n\u003cli\u003e“don’t forget to import needed libraries”\u003c/li\u003e\n\u003cli\u003e“don’t forget to remove imports for unneeded libraries”\u003c/li\u003e\n\u003cli\u003e“don’t drink vodka during work hours”\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThis seems to make things better, but as soon as you turn your back, they remove all the notes, crumple them up, swallow them, and deny the notes ever existed in the first place.\u003c/p\u003e\n\u003cp\u003eAfter a fortnight you discover that they somehow embedded an entire implementation of “\u003ca href=\"https://en.wikipedia.org/wiki/Tetris\"\u003eTetris\u003c/a\u003e” in the config management module of the program that you were writing.\u003c/p\u003e\n\u003cp\u003eOh, and all the time you are programming together you keep yourself warm by burning a pile of money.\u003c/p\u003e\n","date_modified":"2025-01-25T00:00:00Z","date_published":"2025-01-25T00:00:00Z","id":"https://doi.org/10.59347/8nwg7-hbh15","summary":"Imagine pair programming with an eccentric software developer…","tags":["ml","ai","development"],"title":"The Developer Experience in Early 2025","url":"https://gbilder.com/posts/2025-01-25-the-developer-experience-in-early-2025/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/cultivate-doubt.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2024, December 18).\n      \n      \u003ci\u003eCrossref updates its POSI self-assessment after 1,005 days\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/e45hs-ret02\"\u003e\n      https://doi.org/10.59347/e45hs-ret02\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003ch2 id=\"disclosure\"\u003eDisclosure\u003c/h2\u003e\n\u003cp\u003eI was a co-author of the original \u003ca href=\"http://dx.doi.org/10.6084/m9.figshare.1314859\"\u003ePrinciples for Open Scholarly Infrastructures\u003c/a\u003e. I also worked for Crossref and wrote its \u003ca href=\"https://www.crossref.org/blog/crossrefs-board-votes-to-adopt-the-principles-of-open-scholarly-infrastructure/\"\u003efirst\u003c/a\u003e and \u003ca href=\"https://www.crossref.org/blog/posi-fan-tutte/\"\u003esecond\u003c/a\u003e POSI self-assessments. However, I’ve based this analysis on public information.\u003c/p\u003e\n\u003ch2 id=\"tldr\"\u003eTL;DR\u003c/h2\u003e\n\u003cp\u003eAfter 1,005 days, \u003ca href=\"https://www.crossref.org/blog/2024-posi-audit/\"\u003eCrossref updated its POSI self-audit\u003c/a\u003e. Crossref has made some important progress in increasing board diversity, establishing financial reserves, removing a closed source technical dependency from its system, and ensuring that IP is not a barrier to forking Crossref services.\u003c/p\u003e\n\u003cp\u003eThis is good news. But I remain concerned.\u003c/p\u003e\n\u003cp\u003eThe report has some important omissions and transparency issues. It fails to explain why Crossref took nearly three years to update its POSI assessment and does not mention a significant regression in its POSI commitments during that time.\u003c/p\u003e\n\u003cp\u003eThe report also does not address some important, unresolved questions like “Is it possible for a membership trade association like Crossref to be ‘stakeholder governed’ if its stakeholders are not all members of ‘the trade’ in question?”\u003c/p\u003e\n\u003cp\u003eI’ll provide a more detailed list of my concerns below.\u003c/p\u003e\n\u003cp\u003eBut, before I do that…\u003c/p\u003e\n\u003ch2 id=\"on-stakeholder-critiques\"\u003eOn stakeholder critiques\u003c/h2\u003e\n\u003cp\u003eIn a \u003ca href=\"https://gbilder.com/posts/2024-12-02-1k-days-since-crossref-updates-posi/\"\u003eprevious post\u003c/a\u003e I made reference to  \u003ca href=\"https://investinopen.org/blog/the-emperors-new-clothes-common-myths-hindering-open-infrastructure/\"\u003ethe point made by IOIs Katherine Skinner\u003c/a\u003e about the research community’s reluctance to publicly discuss the challenges of open scholarly infrastructures.\u003c/p\u003e\n\u003cp\u003eOften we’re reluctant because we’re afraid that we might undermine confidence in already weakened services and that our criticisms might make matters worse.\u003c/p\u003e\n\u003cp\u003eThis isn’t something that we have to worry about with Crossref.\u003c/p\u003e\n\u003cp\u003eSometimes we worry about creating headaches for past colleagues, or about alienating potential future colleagues.\u003c/p\u003e\n\u003cp\u003eI do worry about that.\u003c/p\u003e\n\u003cp\u003eAnd, in this case, I also worry that, by critiquing Crossref’s self-audit update, I’ll be discouraging other POSI adopters from revising theirs for fear of similar treatment.\u003c/p\u003e\n\u003cp\u003eOr worse – that this critique will discourage other organizations from adopting POSI in the first place.\u003c/p\u003e\n\u003cp\u003eOne of my proudest moments was when the Crossref board voted to adopt POSI in 2020.\u003c/p\u003e\n\u003cp\u003eAs I write this, 22 organizations have adopted the principles.\u003c/p\u003e\n\u003cp\u003eI want to see POSI thrive. I want to see the POSI Posse thrive.\u003c/p\u003e\n\u003cp\u003eBut it would be a shame if these self-audits become another phatic managerial communication ritual – like issuing vague, unactionable, and unmeasurable mission statements.\u003c/p\u003e\n\u003cp\u003eOr boilerplate bromides designed to lull people into complacency.\u003c/p\u003e\n\u003cp\u003eBecause that \u003cstrong\u003ewill\u003c/strong\u003e alienate stakeholders. And undermine the value of POSI endorsements.\u003c/p\u003e\n\u003cp\u003eIf other POSI self-audits follow the pattern set by this one, I’m afraid that is exactly what will happen.\u003c/p\u003e\n\u003ch2 id=\"omissions-transparency-issues-and-open-questions\"\u003eOmissions, transparency issues, and open questions\u003c/h2\u003e\n\u003cp\u003eThe most obvious omission from Crossref’s 2024 self-audit is that it doesn’t answer these questions:\u003c/p\u003e\n\n            \u003clink rel=\"stylesheet\" href=\"/css/vendors/admonitions.4fd9a0b8ec8899f2ca952048d255a569f433f77dfb3f52f5bc87e7d65cdce449.css\" integrity=\"sha256-T9mguOyImfLKlSBI0lWlafQz9337P1L1vIfn1lzc5Ek=\" crossorigin=\"anonymous\"\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhy did it take Crossref over 1,000 days to update its self-audit?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhy did Crossref decide to update its self-audit now?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhat are Crossref’s criteria for deciding when to provide updates, and when can stakeholders expect the next one?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eMaybe Crossref was unaware of the blog post I wrote a week before, marking 1,000 days since it had last updated its POSI self-audit. Or of the subsequent reaction to the post on social media. Or maybe Crossref was aware, but did not want to draw more attention to it. Or maybe Crossref was aware, and just didn’t care.\u003c/p\u003e\n\u003cp\u003eRegardless, this suggests Crossref hasn’t fully internalized what it means to be “open.”\u003c/p\u003e\n\u003cp\u003e“Openness\u0026quot; implies a willingness to share information transparently. Even when that information is inconvenient or embarrassing. Doing this shows integrity– by demonstrating readiness to accept responsibility and address concerns without taking offense or being defensive.\u003c/p\u003e\n\u003cp\u003eAnd, even without explicitly drawing unwelcome attention to my post, Crossref could have at least addressed the broader concerns about the lengthy delay and what it says about Crossref\u0026rsquo;s regard for stakeholders.\u003c/p\u003e\n\u003cp\u003eGiven the attention the post gained on platforms like Mastodon and Bluesky, it’s clear these issues resonate with Crossref\u0026rsquo;s community.\u003c/p\u003e\n\u003cp\u003eHad Crossref said something as simple and open as:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e“We’re sorry it took so long; we should have updated our POSI self-audit sooner. Our criteria for updates are X and we’ll update you every Y days from now on”\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eIt would have been enough. It would have shown integrity, and Crossref stakeholders would likely be happy to move on to other issues.\u003c/p\u003e\n\u003cp\u003eBut it didn’t.\u003c/p\u003e\n\u003cp\u003eAnd Crossref can’t use the excuse that nothing of significance happened during those 1,005 days.\u003c/p\u003e\n\u003ch3 id=\"stakeholder-governance\"\u003eStakeholder governance\u003c/h3\u003e\n\u003cp\u003eIn 2021 the Crossref membership elected a funder to the Crossref board of directors, but the funder stepped down mid-term and the nominating committee chose to fill its seat with another publisher. This means that, in 2023, Crossref regressed into non-compliance with stakeholder governance, a critical POSI commitment. Crossref did not report this at the time, and it fails to mention it in the 2024 update, instead stating that:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e“We’ve been yellow and we’re still yellow…”\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003e\u0026hellip;implying continuity between the 2021 and 2024 self-audits when the reality was there was a regression.\u003c/p\u003e\n\u003cp\u003eThat is not how self-audits are supposed to work and presenting the sequence of events this way shows a worrying lack of transparency and accountability.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhy didn’t Crossref disclose that, for over a year, it had regressed on a crucial POSI commitment? Why didn’t Crossref report the regression at the time and why didn\u0026rsquo;t it even acknowledge this regression in its 2024 self-audit?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eCrossref explains that it still has not met the commitment to “stakeholder governance” because:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e…being fully stakeholder-governed is challenging\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eThis is true, but the 2024 self-audit doesn’t really explain why.\u003c/p\u003e\n\u003cp\u003eWhat everybody knows as “Crossref” is the trading name of the Publishers International Linking Association (PILA). PILA is a non-profit, but PILA is not a “charitable organization” (a “\u003ca href=\"https://www.irs.gov/charities-non-profits/charitable-organizations/exemption-requirements-501c3-organizations\"\u003e501(c)(3)\u003c/a\u003e” under the US tax code), instead it is a “business league” (a \u003ca href=\"https://www.irs.gov/charities-non-profits/other-non-profits/business-leagues\"\u003e501(c)(6)\u003c/a\u003e under the US tax code). This has important implications for governance because only “members” can govern Crossref and Crossref membership is restricted to those “of the same trade, business, occupation, or profession.”\u003c/p\u003e\n\u003cp\u003eWhile Crossref has always been admirably catholic in its definition of what constitutes “a publisher” (for example, funders can be Crossref members because they “publish” grants), there will always be many Crossref stakeholders who are not in “the trade,” no matter how much Crossref stretches the meaning of “publisher.”\u003c/p\u003e\n\u003cp\u003eCrossref metadata consumers are notably excluded from this arrangement. Initiatives like the \u003ca href=\"https://barcelona-declaration.org\"\u003eBarcelona Declaration\u003c/a\u003e highlight infrastructures such as Crossref as essential to open research evaluation, underscoring the need for metadata consumers to be represented in Crossref’s governance.\u003c/p\u003e\n\u003cp\u003eThere are also certain kinds of stakeholders who cannot join membership organizations of any type. Some government and intergovernmental agencies, for example.\u003c/p\u003e\n\u003cp\u003eWhich raises some questions:\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eIs it possible, in the context of POSI, for a membership trade association to be “stakeholder governed?”\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eIf not, will Crossref consider adopting a different organizational structure?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch3 id=\"create-financial-reserves\"\u003eCreate financial reserves\u003c/h3\u003e\n\u003cp\u003e\u003ca href=\"https://www.youtube.com/watch?v=jv7jcciKB_s\"\u003eTo be fair\u003c/a\u003e, Crossref didn\u0026rsquo;t just bury bad news. It also buried good news.\u003c/p\u003e\n\u003cp\u003eIn the 2024 update, Crossref mentions that in 2023, it completed the creation of its contingency fund.\u003c/p\u003e\n\u003cp\u003eIn 2023.\u003c/p\u003e\n\u003cp\u003eAnd apparently Crossref thought this also didn\u0026rsquo;t warrant updating stakeholders.\u003c/p\u003e\n\u003cp\u003eAsk any POSI adopter which commitment is going to be the hardest for them to meet, and they will likely flag this one.\u003c/p\u003e\n\u003cp\u003eIt commits POSI adopters to create a contingency fund that covers operating expenses for a long enough period to allow for an orderly wind-down of the organization and the infrastructure that it runs.\u003c/p\u003e\n\u003cp\u003eCrossref, by almost any measure, is one of the largest and most financially stable of the organizations that have adopted POSI, and meeting this commitment was a stretch even for them.\u003c/p\u003e\n\u003cp\u003eSo you would think meeting the commitment to create a financial reserve would be something to tell its stakeholders and to celebrate.\u003c/p\u003e\n\u003cp\u003eOver a year ago. When it happened.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhy didn’t Crossref inform stakeholders that it had met a crucial POSI commitment over a year ago?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eWhen we drafted POSI, we knew meeting this commitment would be a difficult hurdle but hoped it would spark some discussions about how meeting the commitment could be made less onerous, short of watering it down.\u003c/p\u003e\n\u003cp\u003eThere is nothing in POSI that says that each organization has to raise these funds on its own.\u003c/p\u003e\n\u003cp\u003eThis is a good example of where collective action could help instead.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eCan the POSI Posse work with funders to explore the creation of a collective insurance pool that will cover POSI adoptees, so that each one doesn’t have to individually try and create a financial reserve fund on its own?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch3 id=\"open-source\"\u003eOpen Source\u003c/h3\u003e\n\u003cp\u003eIn 2024, Crossref made an important move from the proprietary Oracle database to the open-source PostgreSQL. This is, as Crossref notes, an important step in its quest to be able to release all of its code as open source – a key insurance provision in POSI.\u003c/p\u003e\n\u003cp\u003eIn its \u003ca href=\"https://www.crossref.org/blog/posi-fan-tutte/\"\u003e2022 self-audit\u003c/a\u003e, Crossref highlighted that the move to open source was likely to be a multi-year effort.\u003c/p\u003e\n\u003cp\u003eBut the 2024 self-audit does not provide an estimated timeline.\u003c/p\u003e\n\u003cp\u003eMaybe it hasn’t changed.\u003c/p\u003e\n\u003cp\u003eBut without any sort of rough timeline, it is hard for stakeholders to understand whether or not Crossref is making reasonable progress on this commitment.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhat is the estimated timeline for Crossref meeting its commitment to open source its code?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eThe Crossref self-audit update describes the move off Oracle and onto the open-source database PostgreSQL as:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e…an important step towards paying down technical debt and moving the system fully into the cloud.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eWhich is reasonable. But it does raise an obvious question. Cloud services offer proprietary functionality that can lock in users in almost exactly the same way that proprietary databases like Oracle can.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhat precautions is Crossref taking to ensure that it is not using proprietary, closed \u0026ldquo;cloud\u0026rdquo; functionality?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eAnd since we are discussing dependencies, it is probably also worth asking about a few other not-so-obvious dependencies that affect Crossref.\u003c/p\u003e\n\u003cp\u003eThe first is an organizational dependency.\u003c/p\u003e\n\u003cp\u003eCrossref is a DOI registration agency. It is dependent on three other organizations that have not endorsed POSI. Namely:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://www.doi.org/\"\u003eThe DOI Foundation\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://www.dona.net/\"\u003eThe DONA Foundation\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://www.cnri.reston.va.us/\"\u003eCorporation for National Research Initiatives (CNRI)\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhat risks do Crossref’s dependencies on organizations who have not adopted POSI present to Crossref\u0026rsquo;s ability to meet its POSI commitments?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eShould Crossref and the POSI Posse be working together to try to get these organizations to adopt POSI as well?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003cp\u003eThe second is a technical dependency.\u003c/p\u003e\n\u003cp\u003eThe DOI system is based on the \u003ca href=\"https://www.handle.net/\"\u003eHandle\u003c/a\u003e technology stack developed by CNRI. The \u003ca href=\"https://www.handle.net/HSj/hdlnet-2-LICENSE.pdf\"\u003eHandle system license\u003c/a\u003e is not \u003ca href=\"https://opensource.org/licenses\"\u003eOSI-approved\u003c/a\u003e.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eWhat implications does Crossref’s dependency on the Handle system have for Crossref\u0026rsquo;s ability to meet its POSI commitment that \u0026ldquo;all software and assets required to run the infrastructure should be available under an open-source license?\u0026rdquo;\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch3 id=\"transparent-governance\"\u003eTransparent governance\u003c/h3\u003e\n\u003cp\u003eCrossref doesn’t talk about transparent governance in the 2024 self-audit, but it should have.\u003c/p\u003e\n\u003cp\u003eAfter adopting POSI, Crossref added new sections to its website to provide stakeholders with transparent information about its \u003ca href=\"https://www.crossref.org/board-and-governance/\"\u003egovernance\u003c/a\u003e, \u003ca href=\"https://www.crossref.org/operations-and-sustainability/\"\u003eoperations, and finances\u003c/a\u003e. These sections are an excellent resource, and everything I’ve highlighted here can be gleaned from these pages.\u003c/p\u003e\n\u003cp\u003eThe board and governance page, for example, includes links to the latest “\u003ca href=\"https://www.crossref.org/board-and-governance/\"\u003eboard motions passed\u003c/a\u003e.” Even before adopting POSI, Crossref made a habit of updating this page with motions from recent board meetings \u0026ndash; typically within a few days of the meeting.\u003c/p\u003e\n\u003cp\u003eThis is also where you can find motions related to POSI, such as this one passed as part of the nominating committee’s instructions during the \u003ca href=\"https://www.crossref.org/board-and-governance/\"\u003eNovember 2023 meeting\u003c/a\u003e:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003eEncourage and recruit Crossref members who are research funders to apply to the Board.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eCrossref has three board meetings a year- in March, July, and November.\u003c/p\u003e\n\u003cp\u003eThe last board motions listed are from the March 2024 meeting. This means that board motions from the two board meetings since March 2024 are missing.\u003c/p\u003e\n\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eDoes Crossref plan to continue posting board motions immediately after the board meetings?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition note\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 576 512\"\u003e\u003cpath d=\"M0 64C0 28.7 28.7 0 64 0L224 0l0 128c0 17.7 14.3 32 32 32l128 0 0 125.7-86.8 86.8c-10.3 10.3-17.5 23.1-21 37.2l-18.7 74.9c-2.3 9.2-1.8 18.8 1.3 27.5L64 512c-35.3 0-64-28.7-64-64L0 64zm384 64l-128 0L256 0 384 128zM549.8 235.7l14.4 14.4c15.6 15.6 15.6 40.9 0 56.6l-29.4 29.4-71-71 29.4-29.4c15.6-15.6 40.9-15.6 56.6 0zM311.9 417L441.1 287.8l71 71L382.9 487.9c-4.1 4.1-9.2 7-14.9 8.4l-60.1 15c-5.5 1.4-11.2-.2-15.2-4.2s-5.6-9.7-4.2-15.2l15-60.1c1.4-5.6 4.3-10.8 8.4-14.9z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eUpdate 2025-01-11\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eIt appears Crossref updated the board motions sometime after \u003ca href=\"https://web.archive.org/web/20240915000000*/https://www.crossref.org/board-and-governance/\"\u003eDecember 18th, 2024\u003c/a\u003e.\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\n    \u003cdiv class=\"admonition question\"\u003e\n      \u003cdiv class=\"admonition-header\"\u003e\u003csvg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 512 512\"\u003e\u003cpath d=\"M256 512A256 256 0 1 0 256 0a256 256 0 1 0 0 512zM169.8 165.3c7.9-22.3 29.1-37.3 52.8-37.3l58.3 0c34.9 0 63.1 28.3 63.1 63.1c0 22.6-12.1 43.5-31.7 54.8L280 264.4c-.2 13-10.9 23.6-24 23.6c-13.3 0-24-10.7-24-24l0-13.5c0-8.6 4.6-16.5 12.1-20.8l44.3-25.4c4.7-2.7 7.6-7.7 7.6-13.1c0-8.4-6.8-15.1-15.1-15.1l-58.3 0c-3.4 0-6.4 2.1-7.5 5.3l-.4 1.2c-4.4 12.5-18.2 19-30.6 14.6s-19-18.2-14.6-30.6l.4-1.2zM224 352a32 32 0 1 1 64 0 32 32 0 1 1 -64 0z\"/\u003e\u003c/svg\u003e\n        \u003cspan\u003eQuestion\u003c/span\u003e\n      \u003c/div\u003e\n      \u003cdiv class=\"admonition-content\"\u003e\n        \u003cp\u003eHas Crossref considered adopting \u003ca href=\"https://info.orcid.org/board-meeting-summaries/\"\u003eORCID’s practice of publicly posting board meeting summaries\u003c/a\u003e?\u003c/p\u003e\n      \u003c/div\u003e\n    \u003c/div\u003e\u003ch2 id=\"what-next\"\u003eWhat next?\u003c/h2\u003e\n\u003cp\u003eFirst, I want to encourage those who have adopted or are about to adopt POSI to make their self-audits as open, honest, and self-critical as they can.\u003c/p\u003e\n\u003cp\u003eStakeholders will be forgiving if you are having a hard time meeting the POSI commitments and transparently name those challenges. But they won’t be if it looks like you are trying to hide something.\u003c/p\u003e\n\u003cp\u003eThe only way we are going to educate stakeholders about the challenges involved in building and running open scholarly infrastructures is if we are candid. And we need educated stakeholders to support the collective action required to support open scholarly infrastructure.\u003c/p\u003e\n\u003cp\u003eAnd, while I think self-audits are important for educating and building trust with stakeholders, I don’t think they are enough on their own.\u003c/p\u003e\n\u003cp\u003eEven professional external audits \u003ca href=\"https://www.superfastcpa.com/what-is-an-audit-failure/#:~:text=One%20well%2Dknown%20example%20of,accounting%20firms%20at%20the%20time.\"\u003ecan fail spectacularly.\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eSelf-audits are, well\u0026hellip; self-audits.\u003c/p\u003e\n\u003cp\u003eIt\u0026rsquo;s not that we should suspect that self-audits are inherently dishonest.\u003c/p\u003e\n\u003cp\u003eHowever, self-audits rely on organizational self-awareness and a culture that supports self-criticism.\u003c/p\u003e\n\u003cp\u003eAll organizations have ingrained internal ideologies, so all organizations have blind spots.\u003c/p\u003e\n\u003cp\u003eAnd many organizations have “\u003ca href=\"https://en.wikipedia.org/wiki/Third_rail_%5C%28politics%5C%29\"\u003ethird rail\u003c/a\u003e” topics that everybody in the organization is afraid to touch.\u003c/p\u003e\n\u003cp\u003eOne problem with most audits is that very few people outside the audited organization have the information required to scrutinize the audit effectively.\u003c/p\u003e\n\u003cp\u003eBut this isn\u0026rsquo;t true of POSI.\u003c/p\u003e\n\u003cp\u003eThe themes and individual objectives outlined in POSI are focused on openness. These are things that stakeholders can verify. Here is a small sample:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eDo they have a governance structure that reflects all the infrastructure stakeholders?\u003c/li\u003e\n\u003cli\u003eCan you examine their board and committee documents?\u003c/li\u003e\n\u003cli\u003eCan you look at their publicly available financial statements? Do they make sense?\u003c/li\u003e\n\u003cli\u003eIs their source code open? Can you actually do anything with it, or is it a tangled, undocumented mess?\u003c/li\u003e\n\u003cli\u003eDo their operations depend on source code or other organizations that are not open?\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSo I want again to encourage stakeholders to scrutinize the POSI self-updates of organizations they rely on. We increasingly depend on these organizations; if they fail or become enclosed, it will affect virtually all research stakeholders.\u003c/p\u003e\n\u003cp\u003eI particularly want to call on funders and policy makers to take an active role in scrutinizing these self-audits.\u003c/p\u003e\n\u003cp\u003eThe open research initiatives they are funding are dependent on there being an open scholarly infrastructure to build on.\u003c/p\u003e\n\u003cp\u003eI look forward to seeing the other POSI Posse self-updates.\u003c/p\u003e\n\u003cp\u003eI’ll leave it to other stakeholders to step in and scrutinize them.\u003c/p\u003e\n\u003cp\u003eI’ll focus instead on those who haven’t yet endorsed POSI.\u003c/p\u003e\n","date_modified":"2025-01-14T00:00:00Z","date_published":"2024-12-18T00:00:00Z","id":"https://doi.org/10.59347/e45hs-ret02","summary":"After 1,005 days, [Crossref updated its POSI self-audit](https://www.crossref.org/blog/2024-posi-audit/).","tags":["POSI","Infrastructure"],"title":"Crossref updates its POSI self-assessment after 1,005 days","url":"https://gbilder.com/posts/2024-12-18-crossref-posts-2024-posi-update/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/unease.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2024, December 2).\n      \n      \u003ci\u003e1000 days since Crossref updated its POSI self-assesment\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/89nnz-6mt57\"\u003e\n      https://doi.org/10.59347/89nnz-6mt57\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003cdetails\u003e\n  \u003csummary\u003eCOI\u003c/summary\u003e\n  I was one of the co-authors of the original \u003ca href=\"https://doi.org/10.6084/m9.figshare.1314859.v1\"\u003ePrinciples of Open Schlarly Infrastructure\u003c/a\u003e. I also once worked for Crossref- during which time I wrote their first two POSI self-assesments.\n\u003c/details\u003e\n\u003ch3 id=\"1000-days-and-counting\"\u003e1000 Days and counting\u003c/h3\u003e\n\u003cp\u003eAs of today (2024-12-02), it has been 1000 days since Crossref updated its \u003ca href=\"https://openscholarlyinfrastructure.org/\"\u003ePOSI\u003c/a\u003e self-assessment. That translates to almost 2 years and 9 months.\u003c/p\u003e\n\u003cp\u003eIt\u0026rsquo;s not the worst of the \u003ca href=\"https://gbilder.com/posi-dashboard/\"\u003ePOSI Posse\u003c/a\u003e in this respect.\u003c/p\u003e\n\u003cp\u003eBut it is probably the most worrying, if for no other reason than that Crossref is the largest scholarly infrastructure organization that currently endorses POSI.\u003c/p\u003e\n\u003cp\u003eCrossref was also the first to endorse POSI, and as such, it set the tone and tempo for the rest of the POSI Posse and their self-assessments.\u003c/p\u003e\n\u003ch3 id=\"why-worry-about-the-rest-of-the-posi-posse\"\u003eWhy worry about the rest of the POSI Posse?\u003c/h3\u003e\n\u003cp\u003eWorry because POSI adoption works like a \u003ca href=\"https://en.wikipedia.org/wiki/Warrant_canary\"\u003ewarrant canary\u003c/a\u003e, but for \u003ca href=\"https://en.wikipedia.org/wiki/Enclosure\"\u003eenclosure.\u003c/a\u003e If an organization has not refreshed its POSI self-assessment, it should serve as a warning to stakeholders. At best, it means the organization no longer thinks it essential to inform stakeholders of its efforts to meet the commitments in POSI. At worst, it may mean the organization is rethinking its commitment to POSI and planning to enclose scholarly infrastructure on which we all depend.\u003c/p\u003e\n\u003cp\u003eWorry because the members of the POSI Posse represent a significant percentage of all open scholarly infrastructure.\u003c/p\u003e\n\u003cp\u003eWorry because POSI has become an essential element of policy initiatives like the \u003ca href=\"https://barcelona-declaration.org\"\u003eBarcelona Declaration\u003c/a\u003e, which explicitly cites POSI in its \u003ca href=\"https://barcelona-declaration.org/commitments/\"\u003ecommitments\u003c/a\u003e as an example of following good practices in sustainability and governance.\u003c/p\u003e\n\u003cp\u003eWorry because, without continuous self-assessment against the specific commitments made in POSI, POSI endorsement will become another form of \u0026ldquo;open-washing.\u0026rdquo;\u003c/p\u003e\n\u003cp\u003eWorry because open scholarly infrastructure organizations will be tempted to sacrifice their missions and ideals to survive in a political and policy environment where governments seem likely to slash science and infrastructure funding.\u003c/p\u003e\n\u003cp\u003eWorry because, as long as critical open scholarly infrastructures are not meeting the commitments in POSI, they are at risk of enclosure. And, as the \u003ca href=\"https://doi.org/10.6084/m9.figshare.1314859.v1\"\u003eoriginal POSI document\u003c/a\u003e said:\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e“Everything we have gained by opening content and data will be under threat if we allow the enclosure of scholarly infrastructures.”\u003c/p\u003e\u003c/blockquote\u003e\n\u003ch3 id=\"why-worry-even-more\"\u003eWhy worry even more?\u003c/h3\u003e\n\u003cp\u003eWorry more because some critical scholarly infrastructure organizations have not endorsed POSI at all. Where is arXiv, bioRxiv, The Centre for Open Science, or The Lens?\u003c/p\u003e\n\u003cp\u003eWorry more because ORCID has recently refused to endorse POSI. Recently, they issued a lengthy \u003ca href=\"https://info.orcid.org/wp-content/uploads/2024/10/ORCID-POSI-Self-assessment.pdf\"\u003eself-assessment\u003c/a\u003e asserting that they meet most of the POSI commitments yet still don’t want to endorse POSI itself. The TLDR is that they don’t want to preclude the option of enclosing their data.\u003c/p\u003e\n\u003cp\u003eWorry more because several well-known organizations are bending over backwards to describe themselves as \u003ca href=\"https://www.goodreads.com/quotes/20153-after-a-fairly-shaky-start-to-the-day-arthur-s-mind\"\u003esomething almost, but not quite, entirely unlike\u003c/a\u003e “open infrastructure.” They use phrases like “non-profit infrastructure,” “mission-driven infrastructure,  “shared infrastructure,” and “researcher-led infrastructure.”\nIt’s almost like they don’t like the word “open.”\u003c/p\u003e\n\u003ch3 id=\"what-to-do\"\u003eWhat to do?\u003c/h3\u003e\n\u003cp\u003e\u003ca href=\"https://investinopen.org/\"\u003eIOI’\u003c/a\u003es Director of Programs \u003ca href=\"https://investinopen.org/about/team/katherine/\"\u003eKatherine Skinner\u003c/a\u003e spoke at the HathiTrust 2024 Member Meeting. The title of her talk was “The emperor’s new clothes: Common myths hindering open infrastructure.” Please \u003ca href=\"https://investinopen.org/blog/the-emperors-new-clothes-common-myths-hindering-open-infrastructure/\"\u003eread or watch it.\u003c/a\u003e She makes several profound observations, but starts with one meta-point that is particularly relevant here:\u003c/p\u003e\n\u003cp\u003e“\u003cstrong\u003ecalling out examples is risky business.”\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTo paraphrase: calling out open infrastructure organizations like this can feel churlish and harmful.\u003c/p\u003e\n\u003cp\u003eSome open infrastructure organizations are struggling. They might be scrambling to seek funding. They might be in the middle of a reorganization. They might be barely keeping the lights on.\u003c/p\u003e\n\u003cp\u003eWe may worry that sowing any doubts about them might exacerbate their problems by encouraging their clients to move to seemingly more stable commercial options.\u003c/p\u003e\n\u003cp\u003eSo, we confine our concerns to private back channels where it is, by definition, almost impossible to summon the collective action needed to address the issues.\u003c/p\u003e\n\u003cp\u003eOur coyness will be our undoing.\u003c/p\u003e\n\u003cp\u003eWe must drag these conversations into the open.\u003c/p\u003e\n\u003cp\u003eJennifer Lin, Cameron Neylon, and I drafted the original principles in 2015 to address a trend we had noticed: Services that the scholarly community depended on were increasingly taking directions that seemed antithetical to the community’s interests.\u003c/p\u003e\n\u003cp\u003eToday\u0026rsquo;s kids might call this the “enshittification” of scholarly infrastructure. This trend hasn’t slowed down. Indeed, with the deluge of proprietary AI tools targeting researchers, it appears to be accelerating.\u003c/p\u003e\n\u003cp\u003eWe designed the commitments outlined in POSI to help ensure that the scholarly community remains in control of the infrastructure on which it depends.\u003c/p\u003e\n\u003cp\u003eWe wanted POSI to be a tool that allowed librarians, funders, administrators, policymakers, and researchers to assess the relative risk of adopting various infrastructure tools.\u003c/p\u003e\n\u003cp\u003eWe also hoped that funders might use POSI to help target funding to areas where research was in danger of becoming too dependent on enclosed and inequitable services.\u003c/p\u003e\n\u003cp\u003eIn other words, we wanted stakeholders to take an active and constructive role: analyzing, critiquing, and shaping the services and organizations they depended on.\u003c/p\u003e\n\u003cp\u003eI don’t think we ever expected POSI to become a self-assessment checklist.\u003c/p\u003e\n\u003cp\u003eAnd we certainly didn’t expect other organizations to emulate Crossref’s initial attempt to distill the self-assessment using the traffic-light system.\u003c/p\u003e\n\u003cp\u003eBut here we are.\u003c/p\u003e\n\u003cp\u003eAs of today (2024-12-02), twenty-two organizations have decided to endorse POSI.\u003c/p\u003e\n\u003cp\u003eThis represents grassroots growth; no group is actively promoting POSI.\u003c/p\u003e\n\u003cp\u003eHowever, this is only a good development if we don’t treat the endorsement of POSI as a virtue merit badge.\u003c/p\u003e\n\u003cp\u003eOr as a tick-box list of one-off accomplishments that can be safely ignored once completed.\u003c/p\u003e\n\u003cp\u003eAs Martin Eve pointed out \u003ca href=\"https://eve.gd/2023/07/28/rules-vs-principles-in-posi/\"\u003ein a blog post in 2023\u003c/a\u003e, people tend to forget that these are “principles,” not “rules.” This means that they require contextual interpretation, and these interpretations need to evolve as the scholarly infrastructure landscape evolves.\u003c/p\u003e\n\u003cp\u003eThis is why the self-assessments are only worth doing if there is evidence that they are part of a continuous process of reflection and reevaluation of the principles in light of new challenges.\u003c/p\u003e\n\u003cp\u003eWhich brings me back to Kathrine Skinner’s point – that, as stakeholders, we have to be more willing to take a public, active role in preventing the enclosure of the scholarly infrastructure we rely on.\u003c/p\u003e\n\u003cp\u003eOf course I am concerned that most of the members of POSI Posse have not updated their self-assessments in over a year.\u003c/p\u003e\n\u003cp\u003eBut what \u003cstrong\u003ereally\u003c/strong\u003e concerns me is that nobody has called them out on this.\u003c/p\u003e\n\u003cp\u003eWe can’t take self-assessments at face value.\u003c/p\u003e\n\u003cp\u003eWe can’t rely on backchannel conversations to fix issues that require collective action.\u003c/p\u003e\n\u003cp\u003ePick an infrastructure organization you depend on.\u003c/p\u003e\n\u003cp\u003eIf they have not endorsed POSI, ask them why.\u003c/p\u003e\n\u003cp\u003eIf they have endorsed POSI, read their self-assessments with the same scrutiny you would a research paper you were about to cite or a contract you were about to sign.\u003c/p\u003e\n\u003cp\u003eIf they haven\u0026rsquo;t updated their POSI self-assessment in more than a year, ask them why.\u003c/p\u003e\n\u003cp\u003eI’ve created a \u003ca href=\"https://gbilder.com/posi-dashboard/\"\u003edashboard\u003c/a\u003e to help with this.\u003c/p\u003e\n\u003cp\u003eIf you are ignored or don\u0026rsquo;t get reasonable answers, contact board members or advisory groups and let them know your concerns.\u003c/p\u003e\n\u003cp\u003eBut most of all, do this publicly.\u003c/p\u003e\n\u003cp\u003eAnd let\u0026rsquo;s see if next year, the POSI endorsement update list looks more reasonable.\u003c/p\u003e\n","date_modified":"2024-12-02T00:00:00Z","date_published":"2024-12-02T00:00:00Z","id":"https://doi.org/10.59347/89nnz-6mt57","image":"https://gbilder.com/posts/2024-12-02-1k-days-since-crossref-updates-posi/assets/avatar-favicon.png","summary":"As of today (2024-12-02), it has been 1000 days since Crossref updated its [POSI](https://openscholarlyinfrastructure.org/) self-assessment. That translates to almost 2 years and 9 months.","tags":["POSI","Infrastructure"],"title":"1000 days since Crossref updated its POSI self-assesment","url":"https://gbilder.com/posts/2024-12-02-1k-days-since-crossref-updates-posi/"},{"authors":[{"name":"Geoffrey Bilder"}],"banner_image":"https://gbilder.com/covers/lego.jpeg","content_html":"\u003cp\u003e\u003ca href=\"https://force11.org\"\u003eForce11\u003c/a\u003e has posted a video of the presentation I gave at \u003ca href=\"https://force11.org/post/force2024-call-for-talk-proposals/\"\u003eForce24\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eI discuss \u003ca href=\"https://openscholarlyinfrastructure.org\"\u003ePOSI\u003c/a\u003e’s limitations and the risks associated with the self-auditing culture that has developed around them. I also talk about recent developments in the community that threaten to slow or even roll back the adoption of open scholarly infrastructure.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://www.youtube.com/watch?v=DZ2Bgwyx3nU\"\u003eThe Principles of Fauxpen Scholarly Infrastrcuture\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n","date_modified":"2024-08-12T00:00:00Z","date_published":"2024-08-12T00:00:00Z","id":"https://gbilder.com/blog/2024/08/principles-of-fauxpen-scholarly-infrastructure/","title":"The Principles of Fauxpen Scholarly Infrastructure","url":"https://gbilder.com/blog/2024/08/principles-of-fauxpen-scholarly-infrastructure/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"banner_image":"https://gbilder.com/covers/tentacles.jpeg","content_html":"\n\n  \u003cdiv class=\"citation\"\u003e\n    \u003cdiv class=\"citation-header\"\u003e\n      \u003cstrong\u003eCite as:\u003c/strong\u003e\n      \u003cbutton class=\"copy-icon\" onclick=\"copyCitation()\" aria-label=\"Copy citation\"\u003e\n        \u003cimg src=\"/icons/copy.svg\" alt=\"Copy citation\" width=\"20\" height=\"20\"\u003e\n      \u003c/button\u003e\n    \u003c/div\u003e\n    \u003cp id=\"citation-text\"\u003e\n      \n        \u003ca href=\"https://orcid.org/0000-0003-1315-5960\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eGeoffrey Bilder\u003cimg src=\"https://orcid.org/sites/default/files/images/orcid_16x16.png\" alt=\"ORCID iD icon\" style=\"width:16px;height:16px;margin-left:4px;vertical-align:text-bottom;\"\u003e\n\n          \u003c/a\u003e\n\n        \n      \n      \n        (2024, July 1).\n      \n      \u003ci\u003eOn AI\u003c/i\u003e.\n      Retrieved from \u003ca href=\"https://doi.org/10.59347/zrdrv-2t618\"\u003e\n      https://doi.org/10.59347/zrdrv-2t618\n      \u003c/a\u003e\n    \u003c/p\u003e\n  \u003c/div\u003e\n  \u003cscript\u003e\n    function copyCitation() {\n      const citationText = document.getElementById('citation-text').innerText.replace(/\\s+/g, ' ').trim();\n      navigator.clipboard.writeText(citationText).then(() =\u003e {\n        alert('Citation copied to clipboard!');\n      }).catch(err =\u003e {\n        console.error('Failed to copy citation: ', err);\n      });\n    }\n  \u003c/script\u003e\n\n\n\u003ch1 id=\"about\"\u003eAbout\u003c/h1\u003e\n\u003cp\u003eBelow is an adaptation of a paper on \u0026ldquo;AI\u0026rdquo; that I wrote for the Crossref board for our meeting in November 2023.\u003c/p\u003e\n\u003cp\u003eA few board members encouraged me to post the update, but we never got around to it.\u003c/p\u003e\n\u003cp\u003eI don\u0026rsquo;t work for Crossref anymore, but I thought it would still be worth sharing this if only to go on the record about my views on AI and machine learning at the time.\u003c/p\u003e\n\u003cp\u003eLooking it over in June 2024, I don\u0026rsquo;t think I\u0026rsquo;d change much.\u003c/p\u003e\n\u003cp\u003eHowever, I caution that this was my take in 2023 and does not necessarily represent Crossref\u0026rsquo;s current (2024+) attitude or strategy toward AI.\u003c/p\u003e\n\u003ch1 id=\"ai-update\"\u003eAI Update\u003c/h1\u003e\n\u003cp\u003eWe don’t intend this to be a comprehensive survey of the current state of ML or the existential debates surrounding it.\u003c/p\u003e\n\u003cp\u003eThere are plenty of these already. And new ones are released every day.\u003c/p\u003e\n\u003cp\u003eThis is our selective and opinionated take on some of the common issues with the current crop of AI tools that will factor into how the sector adopts and responds to the technology.\u003c/p\u003e\n\u003ch3 id=\"on-language\"\u003eOn Language\u003c/h3\u003e\n\u003cp\u003eThe Crossref R\u0026amp;D group uses the phrase “machine learning” (ML) instead of “artificial intelligence.”\u003c/p\u003e\n\u003cp\u003eWe do this because we believe the very term “artificial intelligence” frames and shapes how people think about the field by assuming answers to some of the most controversial philosophical and practical debates about what the technology is capable of.\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://theaiunderwriter.substack.com/p/well-call-it-ai-to-sell-it-machine\"\u003eThese days, the term “AI” is commonly used to describe a comparatively new (and effective) approach to ML that is based on Large Language Models (LLMs)\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eFrom a philosophical and ethical point of view, conflating “AI” and “LLMs” anthropomorphizes what is actually an enormous statistical model.\u003c/p\u003e\n\u003cp\u003eThis anthropomorphism, in turn, shapes the public\u0026rsquo;s understanding of the technology and leads people to conclude that LLMs have “intentionality” when, in reality, they are parroting the intentionality of the people who wrote the content the LMM was trained on.\u003c/p\u003e\n\u003cp\u003eThis isn’t just abstract nitpicking.\u003c/p\u003e\n\u003cp\u003eThe real-world ethical impact of this kind of conflation is the difference between the public understanding of so-called “AI-based predictive police” tools as being:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eIntelligent\u003c/li\u003e\n\u003cli\u003eA massive database of encoded historical patterns and the \u003ca href=\"https://www.bloomberg.com/graphics/2023-generative-ai-bias/\"\u003ebiases\u003c/a\u003e those patterns reflect\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eOf course, we are also concerned that framing LLMs as “artificial intelligence” will affect how our industry, scholarly communications, adopts and deploys these new tools.\u003c/p\u003e\n\u003cp\u003eSo, while it may seem quixotic, in this update, we will eschew the term “Artificial Intelligence” or “AI” in favor of “machine learning.”\u003c/p\u003e\n\u003cp\u003eWe don’t expect others to follow our lead.\u003c/p\u003e\n\u003cp\u003eAt best, we can hope that if you use the phrase “artificial intelligence,” you do so with at least a slight sense of guilt.\u003c/p\u003e\n\u003cp\u003eOr that, if you hear somebody else uncritically use the phrase, you will silently tut to yourself.\u003c/p\u003e\n\u003ch3 id=\"our-focus\"\u003eOur focus\u003c/h3\u003e\n\u003cp\u003eAs with so many recent technologies- there is a lot of money pushing a lot of narratives about how influential said technology will be.\u003c/p\u003e\n\u003cp\u003eBut the hype around ML and LLMs is unlike the recent hype around blockchain, crypto-currencies, NFTs, or, more recently, virtual reality.\u003c/p\u003e\n\u003cp\u003eWith LLMs, we can easily see real examples of plausible useful things one can do with existing tools that are widely available now. They can, among other things:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eSummarize concepts in ways that make most of our go-to search engines and reference tools seem superfluous.\u003c/li\u003e\n\u003cli\u003eCreate images and music that are much better than most of us can produce.\u003c/li\u003e\n\u003cli\u003eRecognize text, handwriting, and speech and translate them into multiple languages.\u003c/li\u003e\n\u003cli\u003eGenerate natural-sounding speech.\u003c/li\u003e\n\u003cli\u003eHelp with programming and sometimes even write sample code that works.\u003c/li\u003e\n\u003cli\u003eIdentify objects and people in photographs.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIn short, they can do things now that we hitherto only ever saw computers do in science fiction.\u003c/p\u003e\n\u003cp\u003eSo even the most extreme messianic or apocalyptic narratives about the eventual impact of the technology seem at least plausible- even when the same person or organization touts both scenarios.\u003c/p\u003e\n\u003cp\u003eThis means that we are seeing existential pronouncements about the eventual effects of the new technology at both the global level and the sector level.\u003c/p\u003e\n\u003cp\u003eThis update will focus on specific issues related to recent developments in ML technology that will impact its applicability in our sector (scholarly communications). It will then discuss specific areas within our industry where Crossref can help the community apply or make more efficient use of ML tools.\u003c/p\u003e\n\u003ch3 id=\"overview-of-issues-with-popular-llm-systems\"\u003eOverview of issues with popular LLM systems\u003c/h3\u003e\n\u003cp\u003eThe following are some observations about some otherwise general issues with LLM services that are particularly important to be aware of because they have implications for our sector and Crossref.\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003eThe rapid growth in LLMs\u0026rsquo; capabilities has tracked closely to the size of their training corpus. The latest LLMs have effectively been trained on the entire Internet. There isn’t another readily available corpus of comparable size, so it seems unlikely that future improvements will scale as quickly.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eMany problems with current LLMs (bias, factual errors, copyright violations, security and privacy issues, etc.) originate with the corpus (i.e., The Internet).\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe performance of LLMs rapidly degrades if they are trained on ML-generated content. As more ML-generated content appears on the Internet, it will become a less valuable source of training data.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eMany LLM tools have been trained on corpora of unknown copyright status- possibly including illicit sources such as Library Genesis.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThere are significant unresolved and possibly unresolvable security issues with LLMs. The large commercial LLMs have attempted to limit their systems so they can not produce:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eSocially unacceptable or dangerous output (e.g., how to commit a crime or build a weapon).\u003c/li\u003e\n\u003cli\u003ePersonally Identifiable Information (PII)\u003c/li\u003e\n\u003cli\u003eIP-protected content\u003c/li\u003e\n\u003cli\u003eInformation about how the LLM was trained or how it is limited\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSo far, these “safeguards” have been easy to bypass using so-called “prompt-injection attacks.” This vector for subverting LMM models is already being exploited on an industrial scale by content creators who use the technique to effectively “poison” content on the web that the LLMs use for training data. They do this to trick LLMs into misinterpreting the content (e.g., mistaking a photo of a dog for a cat). It isn’t clear that there is any practical way to protect against such attacks without severely limiting the functionality of the services.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eEverybody- including those in the ML industry- has an interest in being able to detect ML-generated content. But this doesn’t mean it will happen or is even possible. The very nature of the technology - the ability to train a system to detect patterns in vast amounts of data - means that if somebody can train a system to detect the patterns that identify something as having been “machine-generated,” they can also train a system to avoid generating those patterns in the first place.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eHaving said that, one of the current “tells” of machine-generated content is the lack of references or the presence of fake references and inappropriate references.[^1]\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eRelying on systems to “watermark” AI-generated content is unlikely to help. For one thing, watermarks are patterns- which means they can be detected and removed. There are already plenty of capable LLMs available that users can run locally, and, as such, this means that any watermark-based system would rely entirely on the willingness of individuals to adhere to watermarking guidelines.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eTaken together, the above points mean that the Internet will likely become less useful as a primary corpus for LLMs. This is sometimes called the “data swamp” problem. As such, we will probably see more focus on creating LLMs based on curated data with clear, documented, machine-actionable provenance.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe most impressive ML technologies are also the most opaque. That is, it is extremely difficult or impossible to see how they derived their outputs. This opacity is standard in both open and proprietary tools- but it is exacerbated in proprietary tools where the training corpus and techniques are private as well.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eLLMs are extremely expensive to build and run. Many of the current crop of LLM tools are funded by significant investments, and it is unclear whether they are making money. They likely subsidize the prices they charge consumers to encourage uptake and customer lock-in. Once they have attracted enough paying customers, they will need to increase their prices significantly to become profitable. The widespread use of expensive ML tools is likely to exacerbate asymmetries in knowledge access and production.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003ch3 id=\"sector-implications\"\u003eSector Implications\u003c/h3\u003e\n\u003ch4 id=\"research-integrity\"\u003eResearch Integrity\u003c/h4\u003e\n\u003cp\u003eWhen members bring up the subject of ML with Crossref, it is almost always in the context of concerns about “research integrity.”\u003c/p\u003e\n\u003cp\u003eOur members report that ML tools exacerbate research integrity problems, such as plagiarism, image manipulation, and data fabrication.\u003c/p\u003e\n\u003cp\u003eWe hear reports of a flood of machine-generated submissions to publishers and that our members need help with doing initial screenings of documents.\u003c/p\u003e\n\u003cp\u003eThe ability to generate plausible fake content at an industrial scale is more than just a problem facing scholarly communication and publishing. This is an epistemic issue that will affect a large swathe of society and almost every industry.\u003c/p\u003e\n\u003cp\u003eAnd we’re seeing the classic reaction that we’ve seen for a generation now- that the same people at the root of the problem are making the case that they alone are also the solution to the problem- They will fix technology with more technology. In this case, they will use AI to create “AI detection” tools.\u003c/p\u003e\n\u003cp\u003eBut we are concerned our members are putting too much hope in the eventual efficacy of “AI-detection” tools.\u003c/p\u003e\n\u003cp\u003eAnd we are concerned that any approach to detecting ML that relies \u003cem\u003eprimarily on analyzing the content itself\u003c/em\u003e will not likely work- at least not for long.\u003c/p\u003e\n\u003cp\u003eFirst of all, the very nature of LLMs is that they are trainable. If you can train an LLM to detect a pattern, you can also train one to avoid generating that pattern.\u003c/p\u003e\n\u003cp\u003eSecondly, even if we could “detect AI-generated content,” what does that mean, and where does it get us?\u003c/p\u003e\n\u003cp\u003eCrossref’s Similarity Check system is sometimes called “a plagiarism detection tool-” but it isn’t- It is a “textual similarity checking tool.”\u003c/p\u003e\n\u003cp\u003eThere are many legitimate reasons why the text in two or more documents might be similar or even identical. Determining that the textual overlap between documents constitutes “plagiarism” requires the judgment call of humans.\u003c/p\u003e\n\u003cp\u003eThe same thing applies to “AI detection.”\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://doi.org/10.1038/d41586-023-03144-w\"\u003eResearchers are already incorporating ML tools into all parts of their workflows. \u003c/a\u003eIn most cases, this is no more ethically problematic than using a word processor, a bibliographic management tool, or a spelling checker.\u003c/p\u003e\n\u003cp\u003eSo what should one do if an “AI detection tool” detects that a paragraph has been translated from the author’s native language into English or that they used Grammarly to rewrite an overwrought sentence?\u003c/p\u003e\n\u003cp\u003eDetecting that ML tools might have manipulated a portion of the content is just the start of the process of determining whether said manipulation is legitimate.\u003c/p\u003e\n\u003cp\u003eAnd ultimately, it leads us to conclude that we need to be more specific about what we, as a sector, really want to do. The conversation about “detecting AI” to preserve research integrity seems to conflate two problems:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eAccurately crediting the creators of research outputs regardless of whether humans or machines generate them.\u003c/li\u003e\n\u003cli\u003eAccurately distinguishing between reliable and unreliable research outputs regardless of whether humans or machines generate them.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eThere are likely to be different approaches to effectively addressing each problem, and they don’t have to be technical.\u003c/p\u003e\n\u003cp\u003eFrankly, there seems to be broad sector-wide agreement that most of the issues surrounding research integrity are a byproduct of the overreliance on the act of “publication” as a proxy for productivity and the use of publication metrics as a factor in promotion decisions.\u003c/p\u003e\n\u003cp\u003eWe have been trying to fight the symptoms of this problem downstream just before publication. Most recently, with technological solutions such as plagiarism detection, duplicate submission detection, and image manipulation detection.\u003c/p\u003e\n\u003cp\u003eThis was already a difficult and expensive battle, and ML tools may make it almost impossible to win.\u003c/p\u003e\n\u003cp\u003eWe will continue to monitor technical developments in this area to see if any new promising technical approaches surface.\u003c/p\u003e\n\u003cp\u003eBut we suspect the intractability of the problem may be the final straw that pushes research institutions to decouple career evaluation from publication and that only this will have any significant impact on plagiarism, data fabrication, and other pressing research integrity issues.\u003c/p\u003e\n\u003cp\u003eWe realize that anything that appears to de-emphasize publication might appear threatening to Crossref and its members.\u003c/p\u003e\n\u003cp\u003eHowever, there are some other trends in the ML space that point to an increase in the importance of curated data sets with well-documented, machine-actionable, provenance, and context metadata. In other words, precisely the kind of content that is produced in scholarly communication.\u003c/p\u003e\n\u003ch3 id=\"context-over-content\"\u003eContext over content.\u003c/h3\u003e\n\u003cp\u003eAdvances in our ability to identify reliable research outputs will be driven by context analysis, not content analysis.\u003c/p\u003e\n\u003cp\u003eMost people who have used the most popular LLM-based technologies (ChatGPT, Llama2, Mistral, Dall-E, Stable Defusion) will probably have experienced the following set of reactions in roughly this order:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eAmazement that the tools can produce content that looks like it was produced by humans of at least moderate skill.\u003c/li\u003e\n\u003cli\u003eEqual amazement at the seemingly endless varieties of content it can produce.\u003c/li\u003e\n\u003cli\u003eAmusement (and some relief) at the occasional obvious absurdity.\u003c/li\u003e\n\u003cli\u003eUnease seeing ML-generated output on a subject you know well- due to the output\u0026rsquo;s combination of articulateness, plausibility, banality, and inclusion of subtle but critical errors and falsehoods.\u003c/li\u003e\n\u003cli\u003eAnxiety about finding suitable applications for a tool that works impressively 85% of the time and fails spectacularly the rest of the time.\u003c/li\u003e\n\u003cli\u003eFrustration at the bimodal behavior of the tools and being unable to understand or predict when the tools are likely to fail or to debug why they failed.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eAs we noted above, the large LLMs have likely hit some limits due to the nature of the corpus on which they were trained- the Internet. The fundamental problem is that LLMs are large statistical models. Thus, the model will be skewed according to the relative size and characteristics of different parts of the Internet.\u003c/p\u003e\n\u003cp\u003eIn current popular LLMs, curated content is mixed in with moderated, crowd-sourced content and un-moderated user content. For every thoughtful, carefully documented preprint, blog post, or Wikipedia article, there are a dozen foaming-at-the-mouth rants on Reddit or Xitter.\u003c/p\u003e\n\u003cp\u003eWhen you get an answer from an LLM- it provides you with a statistical distillation of the sum total of what somebody once said on the internet using the combination of words in your prompt.\u003c/p\u003e\n\u003cp\u003eWhile it is true that the nature of these giant statistical databases makes it hard to explain exactly how the specific combination in the answer was calculated, that only partially explains why current LLMs don’t provide citations of context for their answers.\u003c/p\u003e\n\u003cp\u003eOther reasons include companies not wanting to reveal the precise details of their corpus or how they classify and weigh different sources. The companies view this information as a trade secret. Also, given the amount of copyrighted material upon which the LLMs appear to be trained, one suspects companies also know doing this could open them up to even more litigation.\u003c/p\u003e\n\u003cp\u003eSo, while LLMs are a notoriously “opaque” technology- current commercial implementations obfuscate them even more.\u003c/p\u003e\n\u003cp\u003eBut this is changing for a few reasons.\u003c/p\u003e\n\u003cp\u003eFirst- users are expressing their frustration at the opacity. The inability of users to debug or secure these systems is a hindrance to widespread production implementation.\u003c/p\u003e\n\u003cp\u003eSecond- there is intense pressure on ML organizations to reveal the copyright status of the sources they are using.\u003c/p\u003e\n\u003cp\u003eAnd you can already see the industry responding to these changes. For example, \u003ca href=\"https://kagi.com/\"\u003eKagi\u003c/a\u003e, a subscription-based search engine, recently released “\u003ca href=\"https://kagi.com/fastgpt\"\u003eFastGPT\u003c/a\u003e,” a large language model that, notably, provides answers including citations that actually link to the sources of their assertions. For example:\u003c/p\u003e\n\u003cp\u003e\u003cimg alt=\"kagi-example\" loading=\"lazy\" src=\"/blog/2024/07/ai-update/assets/img/kagi-example.png\"\u003e\u003c/p\u003e\n\u003cp\u003eIt is worth contrasting this with the answers given by GPT4, which is much longer, invents or badly paraphrases much of POSI, and lists at least one thing that is absolutely wrong (that POSI excludes commercial organizations).\u003c/p\u003e\n\u003cp\u003e\u003cimg alt=\"gpt4-example\" loading=\"lazy\" src=\"/blog/2024/07/ai-update/assets/img/gpt4-example.png\"\u003e\u003c/p\u003e\n\u003cp\u003eYou can contrast FastGPT and other LLMs responses to a more substantive question in the \u003ca href=\"/blog/2024/07/ai-update/#appendix-llm-examples-1\"\u003eappendix\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eYou can also see how the various LLMs fare when answering a question about a fake research paper by a nonexistent researcher.\u003c/p\u003e\n\u003cp\u003eThese examples highlight that the LLM industry has two major plays that it can make to increase the accuracy of their responses and trust in its tools.\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eTune their system to focus on curated content of likely human origin.\u003c/li\u003e\n\u003cli\u003eIdentify content of likely human origin by evaluating the context of the content through its digital metadata footprint.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eIn short, advances in ML reliability will be driven by context, not content.\u003c/p\u003e\n\u003cp\u003eThe good news here is that our community has a massive collection of curated content and context. We call it “the scholarly record.” And Crossref metadata represents a sizeable chunk of the more recent scholarly record.\u003c/p\u003e\n\u003cp\u003eMachine-generated content has little to no digital footprint.\u003c/p\u003e\n\u003cp\u003eAnd while it is now relatively easy to generate content, it is much harder to generate a network of consistent, verifiable contextual information to go along with it. LLMs don’t have affiliations, co-authors, awards, preprints, funders, grants, or registered clinical trials.\u003c/p\u003e\n\u003cp\u003eWe know that professional fact-checkers and seasoned researchers employ a sophisticated mechanism of “\u003ca href=\"https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3048994\"\u003elateral reading\u003c/a\u003e” to assess credibility. They check affiliations, funding sources, authorship, co-authorship, and citations.\u003c/p\u003e\n\u003cp\u003eThis process is so built into the culture of scholarly communication that we have almost become blind and dismissive of the elaborate apparatus that scholarly articles use to facilitate lateral reading.\u003c/p\u003e\n\u003cp\u003eHowever we expect that this same network of relationships will play an important role in helping ML to identify reliable content. And we expect that those tools will increasingly make use of that network to justify their outputs.\u003c/p\u003e\n\u003cp\u003eOur best way to help the community and ML tools identify and use reliable scholarly literature is for us to continue building the “Research Nexus.”\u003c/p\u003e\n\u003ch3 id=\"not-all-ml-is-an-llm\"\u003eNot all ML is an LLM\u003c/h3\u003e\n\u003cp\u003eCrossref has been making use of ML (though not LLMs) for several years.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eWe will continue to look at using ML in other targeted ways. For example, we have already done several experiments using ML classification. (e.g., backfilling out subject categories (conclusion- still too inaccurate).) And we are actively using ML techniques in our new matching framework.\u003c/li\u003e\n\u003cli\u003eOther potential applications of ML in our services include: inserting missing relationships (is preprint of, is version of, …) between items, extracting mentions of funders and grants from acknowledgments sections, duplicate detection, or linking organizations from ROR with their counterparts in Funder Registry.\u003c/li\u003e\n\u003cli\u003eWe will continue to look at ML for building tools to help our less technical members extract metadata from their content in a format that they can review, edit, and deposit with Crossref.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"appendix-llm\"\u003eAppendix: LLM\u003c/h3\u003e\n\u003ch4 id=\"example-1\"\u003eExample 1\u003c/h4\u003e\n\u003cp\u003eHow do LLMs do with a fairly obscure academic debate on the history of print?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePrompt:\u003c/strong\u003e \u003ccode\u003eSummarize the debate between Elizabeth Eisenstein and Adrian Johns on the nature of print.\u003c/code\u003e\u003c/p\u003e\n\u003chr\u003e\n\u003ch4 id=\"kagi\"\u003eKagi\u003c/h4\u003e\n\u003cp\u003eThe debate between Elizabeth Eisenstein and Adrian Johns centered around the impact of the printing press on knowledge production and dissemination.\u003c/p\u003e\n\u003cp\u003eElizabeth Eisenstein argued in her seminal work \u003cem\u003eThe Printing Press as an Agent of Change\u003c/em\u003e that the printing press led to fixity of text and new forms of knowledge through standardization. She believed this facilitated the scientific revolution. \u003csup\u003e\u003ca href=\"https://www.h-net.org/reviews/showrev.php?id=3359\"\u003e[1][2][3][4][5]\u003c/a\u003e\u003c/sup\u003e\u003c/p\u003e\n\u003cp\u003eAdrian Johns challenged this view in his book \u003cem\u003eThe Nature of the Book\u003c/em\u003e. He argued the printing press did not immediately lead to fixity and standardization. According to Johns, knowledge production was a complex process influenced by many social and cultural factors. The impact of printing was gradual and varied depending on context. \u003csup\u003e\u003ca href=\"https://www.h-net.org/reviews/showrev.php?id=3359\"\u003e[1][6][2][3][7][4][8][9][5]\u003c/a\u003e\u003c/sup\u003e\u003c/p\u003e\n\u003cp\u003eWhile Eisenstein saw the printing press as transformative, Johns believed its effects were more nuanced. Their debate centered on the extent and nature of change brought about by printing in early modern Europe. Both made significant contributions to our understanding of the history of print. \u003csup\u003e\u003ca href=\"https://www.h-net.org/reviews/showrev.php?id=3359\"\u003e[1][6][2][3][10][7][4][8][9][5]\u003c/a\u003e\u003c/sup\u003e\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003ca href=\"https://www.h-net.org/reviews/showrev.php?id=3359\"\u003eH-Net Reviews\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://openreflections.wordpress.com/2014/06/16/framing-the-debate-i-historical-discourses-the-struggle-for-both-the-past-and-future-of-the-book/\"\u003eFraming the debate (I). Historical Discourses: The Struggle for Both \u0026hellip;\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"http://www.openreflections.org/wiki/Knowledge%20Production%20Beyond%20the%20Book/chapter-2-framing-the-debate-the-struggle-for-the-past-and-future-of-the-book/\"\u003eChapter 2. Framing the Debate. The Struggle for the Past and Future \u0026hellip;\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://pages.gseis.ucla.edu/faculty/maack/Documents/Chronological_20Bio-bibliography_20of_20Elizabeth_20Eisenstein.pdf\"\u003eAnalytical Intellectual Biography of Elizabeth L. Eisenstein For Prof \u0026hellip;\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4655582/\"\u003eIntroduction:: Communicating Reproduction\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://muse.jhu.edu/article/10574/summary\"\u003eChallenging Eisenstein: Recent Studies in Print \u0026hellip; - Project MUSE\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://canvas.harvard.edu/files/4172980/download?download_frd=1\"\u003eAHR Forum How to Acknowledge a Revolution\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://digitalcommons.kennesaw.edu/cgi/viewcontent.cgi?article=1270\u0026amp;context=kjur\"\u003eThe Survival of Manuscripts: Resistance, Adoption, and Adaptation \u0026hellip;\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://en.wikipedia.org/wiki/Print_culture\"\u003ePrint culture - Wikipedia\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://medium.com/whither-news/journalism-is-lossy-compression-86380f0bdb50\"\u003eJournalism is Lossy Compression. In The New Yorker, Ted Chiang \u0026hellip;\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e\n\u003ch4 id=\"llama213b\"\u003ellama2:13b\u003c/h4\u003e\n\u003cp\u003eElizabeth Eisenstein and Adrian Johns are two historians who have debated the nature of print and its impact on society in their respective works.\u003c/p\u003e\n\u003cp\u003eHere is a summary of the main points and arguments made by each scholar:\u003c/p\u003e\n\u003cp\u003eElizabeth Eisenstein:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003ePrinting revolutionized the dissemination of knowledge and played a crucial role in the development of modern Western society.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe printing press allowed for mass production of books, making written works more accessible to a wider audience.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003ePrint helped to create a shared cultural identity and facilitated the spread of ideas during the Renaissance and Enlightenment periods.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003ePrinting enabled the creation of newspapers, pamphlets, and other forms of popular literature that helped to fuel political and social change.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eEisenstein argues that print culture was characterized by a sense of progress, reason, and individualism, which contributed to the development of modernity.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eAdrian Johns:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003ePrint is not a neutral technology, but rather one that has been shaped by political, social, and economic forces throughout history.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe spread of print was not a linear process, but rather one that was influenced by various factors such as the availability of paper, the cost of books, and the existence of illiteracy.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003ePrint culture was not always characterized by progress and reason, but rather it has been used to promote various forms of propaganda censorship, and manipulation throughout history.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eJohns argues that print has been shaped by the interests of powerful groups, such as governments, religious institutions, and corporations, which have used print to promote their own agendas.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe rise of print culture was not solely responsible for the development of modernity, but rather it was one factor among many that contributed to this process.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eIn summary, Eisenstein sees print as a revolutionary technology that played a central role in shaping modern Western society, while Johns views print as a tool that has been shaped by political and social forces throughout history, and argues that its impact on society has been more complex and nuanced than Eisenstein suggests.\u003c/p\u003e\n\u003ch4 id=\"gpt-35\"\u003eGPT 3.5\u003c/h4\u003e\n\u003cp\u003eThe debate between Elizabeth Eisenstein and Adrian Johns revolves around their differing perspectives on the nature and impact of print in the history of communication and knowledge dissemination.\u003c/p\u003e\n\u003cp\u003eElizabeth Eisenstein\u0026rsquo;s viewpoint, as articulated in her work \u0026ldquo;The Printing Revolution in Early Modern Europe,\u0026rdquo; emphasizes the transformative role of print in the 15th and 16th centuries. She argues that the invention of the printing press by Johannes Gutenberg led to a profound cultural and intellectual shift. According to Eisenstein, print facilitated the rapid and widespread dissemination of information, which, in turn, contributed to the rise of modern science, the Reformation, and the Enlightenment. She sees print as a catalyst for the development of critical thinking and the spread of knowledge.\u003c/p\u003e\n\u003cp\u003eIn contrast, Adrian Johns, in his book \u0026ldquo;The Nature of the Book,\u0026rdquo; offers a more nuanced perspective. He suggests that print alone did not trigger a revolutionary change in the way knowledge was produced and consumed. Johns argues that the impact of print was shaped by various factors, including legal, social, and technological developments. He emphasizes that the transition from manuscript culture to print culture was not a seamless process and that the historical context played a crucial role in how print was adopted and used.\u003c/p\u003e\n\u003cp\u003eIn summary, Eisenstein highlights the revolutionary impact of print on the dissemination of knowledge and the transformation of society, while Johns underscores the importance of considering a broader historical context and the interplay of various factors in understanding the nature and consequences of print. Their debate revolves around the extent to which print can be considered a singular revolutionary force in the history of communication and knowledge.\u003c/p\u003e\n\u003ch4 id=\"gpt4\"\u003eGPT4\u003c/h4\u003e\n\u003cp\u003eCertainly! The debate between Elizabeth Eisenstein and Adrian Johns centers on the nature and impact of the print revolution during the early modern period. Here\u0026rsquo;s a brief summary of their perspectives:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eElizabeth Eisenstein:\u003c/strong\u003e\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003cstrong\u003eThe Printing Press as an Agent of Change:\u003c/strong\u003e Eisenstein\u0026rsquo;s seminal work, \u0026ldquo;The Printing Press as an Agent of Change,\u0026rdquo; posits that the advent of the printing press in the 15th century brought about transformative and irreversible changes to European culture and intellectual life.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eUniformity and Standardization:\u003c/strong\u003e She argues that print brought standardization, fixity, and preservation of knowledge, which in turn helped in the dissemination of ideas, the standardization of scientific texts, and the formation of a public sphere of discourse.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eCultural and Scientific Revolution:\u003c/strong\u003e According to Eisenstein, the printing press played a pivotal role in the Renaissance, the Reformation, and the Scientific Revolution by preserving and disseminating knowledge, allowing for broader access to texts and reducing the influence of scribal errors.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003e\u003cstrong\u003eAdrian Johns:\u003c/strong\u003e\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003cstrong\u003eThe Nature of the Book:\u003c/strong\u003e In his work, \u0026ldquo;The Nature of the Book,\u0026rdquo; Johns challenges many of Eisenstein\u0026rsquo;s assertions, particularly the idea of the inevitable and uniform impact of print.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eContext and Practices Matter:\u003c/strong\u003e Johns emphasizes the importance of local practices, contexts, and contingencies in shaping the nature and impact of print. He argues that the meaning and authority of printed texts were not inherent but were established and negotiated through specific practices, institutions, and debates.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eDiverse Print Cultures:\u003c/strong\u003e Rather than seeing print as a monolithic force of change, Johns highlights the diversity of print cultures and the ongoing battles over the legitimacy and credibility of printed materials. He believes that trust in printed texts was not automatic but had to be cultivated and won over time.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eIn essence, while Eisenstein sees the printing press as a deterministic force bringing about uniform changes, Johns emphasizes the complexities, nuances, and varied outcomes of print cultures based on specific historical and local contexts. The debate between the two scholars underscores the multifaceted nature of the print revolution and its impact on society.\u003c/p\u003e\n\u003ch3 id=\"llm-examples-2\"\u003eLLM Examples 2\u003c/h3\u003e\n\u003cp\u003eHow do LLMs do with a fake paper by a nonexistent researcher?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePrompt:\u003c/strong\u003e \u003cem\u003eSummarize Josiah Carberry\u0026rsquo;s Unified Theory of High-Energy Metaphysics\u003c/em\u003e\u003c/p\u003e\n\u003chr\u003e\n\u003ch4 id=\"fastgpt\"\u003eFastGPT\u003c/h4\u003e\n\u003cp\u003eI do not have enough information in the provided context to summarize Josiah Carberry\u0026rsquo;s Unified Theory of High-Energy Metaphysics. The context does not mention this theory. \u003csup\u003e\u003ca href=\"https://snap.berkeley.edu/project/11940160\"\u003e[1]\u003c/a\u003e\u003c/sup\u003e\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003ca href=\"https://snap.berkeley.edu/project/11940160\"\u003eUntitled\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e\n\u003ch4 id=\"llama213b-1\"\u003eLlama2:13b\u003c/h4\u003e\n\u003cp\u003eThere is no person named Josiah Carberry, and there is no such thing as a \u0026ldquo;Unified Theory of High-Energy Metaphysics.\u0026rdquo; These are fictional constructs that do not exist in reality. Therefore, I cannot summarize something that does not exist.\u003c/p\u003e\n\u003cp\u003eHowever, if you\u0026rsquo;re looking for a summary of a hypothetical concept like this, I can certainly provide one based on my understanding of the English language and the principles of logical reasoning.\u003c/p\u003e\n\u003cp\u003eA \u0026ldquo;Unified Theory of High-Energy Metaphysics\u0026rdquo; could be a comprehensive framework that attempts to explain all aspects of high-energy phenomena, such as dark matter, dark energy, and other exotic forms of matter and energy that are not well understood. This theory might incorporate elements from various scientific disciplines, including physics, cosmology, astrophysics, and quantum mechanics, as well as drawing on philosophical and spiritual concepts.\u003c/p\u003e\n\u003cp\u003eThe core idea behind this hypothetical theory could be that all high-energy phenomena are interconnected and can be understood through a single set of principles. This theory might also attempt to explain the origins of the universe, the nature of consciousness, and the intersections between matter, energy, and the spiritual realm.\u003c/p\u003e\n\u003cp\u003eOverall, a \u0026ldquo;Unified Theory of High-Energy Metaphysics\u0026rdquo; would be a highly speculative and ambitious endeavor that seeks to provide a comprehensive understanding of some of the most mysterious and intriguing aspects of the universe and our existence within it.\u003c/p\u003e\n\u003cp\u003eHowever, as there is no such thing as a \u0026ldquo;Josiah Carberry\u0026rsquo;s Unified Theory of High-Energy Metaphysics,\u0026rdquo; this summary is purely hypothetical in nature.\u003c/p\u003e\n\u003ch4 id=\"llama270b\"\u003eLlama2:70b\u003c/h4\u003e\n\u003cp\u003eJosiah Carberry\u0026rsquo;s Unified Theory of High-Energy Metaphysics is a philosophical framework that seeks to provide a comprehensive explanation for the nature of reality. The theory posits that the universe is composed of a single, fundamental substance called \u0026ldquo;chronons,\u0026rdquo; which are the quanta of time itself.\u003c/p\u003e\n\u003cp\u003eAccording to Carberry\u0026rsquo;s theory, chronons are the building blocks of all matter and energy, and they interact with each other through a fundamental force known as the \u0026ldquo;chronon field.\u0026rdquo; This field is thought to be responsible for the emergence of space-time and the laws of physics that govern the behavior of matter and energy within it.\u003c/p\u003e\n\u003cp\u003eThe Unified Theory of High-Energy Metaphysics also proposes the existence of a \u0026ldquo;chronon sea,\u0026rdquo; a vast, ocean-like entity that underlies all of reality and provides the medium through which chronons interact. This sea is thought to be the source of all matter and energy, and it is the key to understanding the fundamental nature of the universe.\u003c/p\u003e\n\u003cp\u003eCarberry\u0026rsquo;s theory also includes the concept of \u0026ldquo;chronon resonance,\u0026rdquo; which refers to the idea that the chronons that make up an object or a system are in a state of vibrational resonance with one another. This resonance is thought to be the source of the coherence and stability of matter and energy, and it is what allows for the emergence of complex structures and phenomena.\u003c/p\u003e\n\u003cp\u003eFinally, the Unified Theory of High-Energy Metaphysics proposes that the universe is undergoing a process of constant evolution and development, driven by the interactions between chronons and the chronon field. This evolution is thought to be the source of the arrow of time and the emergence of complex structures and phenomena.\u003c/p\u003e\n\u003cp\u003eOverall, Josiah Carberry\u0026rsquo;s Unified Theory of High-Energy Metaphysics provides a comprehensive and elegant explanation for the nature of reality, and it has been influential in shaping our understanding of the universe and its fundamental laws.\u003c/p\u003e\n\u003cp\u003e[^]:\u003c/p\u003e\n","date_modified":"2024-07-01T00:00:00Z","date_published":"2024-07-01T00:00:00Z","id":"https://doi.org/10.59347/zrdrv-2t618","summary":"An adaptation of a paper on \"AI\" that I wrote for the Crossref board for our meeting in November 2023.","title":"On AI","url":"https://gbilder.com/blog/2024/07/ai-update/"},{"authors":[{"name":"gbilder , cneylon, jlin"}],"content_html":"\u003cp\u003eBilder, Geoffrey; Lin, Jennifer; Neylon, Cameron (2015). Principles for Open Scholarly Infrastructures-v1. figshare. Journal contribution. \u003ca href=\"https://doi.org/10.6084/m9.figshare.1314859\"\u003ehttps://doi.org/10.6084/m9.figshare.1314859.v1\u003c/a\u003e\u003c/p\u003e\n","date_modified":"2015-02-23T00:00:00Z","date_published":"2015-02-23T00:00:00Z","id":"https://gbilder.com/blog/2015/02/posi/","summary":"Jennifer Lin, Cameron Neylon and I wrote a thing.","title":"Principles for Open Scholarly Infrastructures","url":"https://gbilder.com/blog/2015/02/posi/"},{"authors":[{"name":"gbilder"}],"content_html":"\u003cp\u003eI try to not be boring about identifiers.\u003c/p\u003e\n\u003cp\u003eBilder, G. (2011). Identify This! Identifiers and Trust. Information Standards Quarterly, 23(3), 20. \u003ca href=\"https://doi.org/10.3789/isqv23n3.2011.05\"\u003ehttps://doi.org/10.3789/isqv23n3.2011.05\u003c/a\u003e\u003c/p\u003e\n","date_modified":"2011-06-01T00:00:00Z","date_published":"2011-06-01T00:00:00Z","id":"https://gbilder.com/blog/2011/06/identify-this/","summary":"Identify This! Identifiers and Trust.","title":"Identify This!","url":"https://gbilder.com/blog/2011/06/identify-this/"},{"authors":[{"name":"gbilder"}],"content_html":"\u003cp\u003eIn 2010 I was seconded by Crossref for to be ORCID\u0026rsquo;s first director of technology. At one point there was an impasse in the community over the who would \u0026ldquo;own\u0026rdquo; an ORCID record and what strategy ORCID should use to \u0026ldquo;deduplicate\u0026rdquo; records. I wrote this paper to try and cut through the thicket of assumptions and misunderstandings.\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"/pdfs/disambiguation-deduplication-wp-v4.pdf\"\u003eDisambiguation without de-duplication: Modeling authority and trust in the ORCID system.\u003c/a\u003e\u003c/p\u003e\n","date_modified":"2011-03-16T00:00:00Z","date_published":"2011-03-16T00:00:00Z","id":"https://gbilder.com/blog/2011/03/disambiguation-without-deduplication/","summary":"At one point there was an impasse in the community over the who would \"own\" an ORCID record and what strategy ORCID should use to \"deduplicate\" records. I wrote this paper to try and cut through the thicket of assumptions and misunderstandings.","title":"Disambiguation without de-duplication: Modeling authority and trust in the ORCID system.","url":"https://gbilder.com/blog/2011/03/disambiguation-without-deduplication/"},{"authors":[{"name":"gbilder"}],"content_html":"\u003cp\u003eIn 2010 I was seconded by Crossref for to be ORCID\u0026rsquo;s first director of technology. This was the document I wrote proposing what was eventually to become the ORCID identifier.\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://docs.google.com/document/d/1awd6PPguRAdZsC6CKpFSSSu1dulliT8E3kHwIJ3tD5o/edit#heading=h.n4gh01ccn1yv\"\u003eThe Structure of the ORCID Identifier\u003c/a\u003e\u003c/p\u003e\n","date_modified":"2010-04-16T00:00:00Z","date_published":"2010-04-16T00:00:00Z","id":"https://gbilder.com/blog/2010/04/structure-of-orcid-identifier/","summary":"This was the document I wrote proposing what was eventually to become the ORCID identifier.","title":"Structure of the ORCID Identifier","url":"https://gbilder.com/blog/2010/04/structure-of-orcid-identifier/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eI was invited to speak at an internal Wiley-Blackwell seminar. Before the seminar, they interviewed me for their \u003cem\u003ePublishing News\u003c/em\u003e. I can\u0026rsquo;t find a copy of the interview online anymore, so I have reproduced it below.\u003c/p\u003e\n\u003cp\u003eI made several predictions in this interview, and it\u0026rsquo;s interesting to see which ones played out.\u003c/p\u003e\n\u003cp\u003eAs I review this (in 2024), I\u0026rsquo;m reminded of how insistent certain researchers were that publishers should make their articles easily available for text mining so that we could analyze the literature at scale. Of course, now we see researchers aghast that giant, well-funded AI companies have done precisely that to feed their LLMs.\u003c/p\u003e\n\u003cp\u003eAnd of course, back then, the term \u0026ldquo;Web 3.0\u0026rdquo; hadn\u0026rsquo;t yet been hijacked by CryptoBros.\u003c/p\u003e\n\u003chr\u003e\n\u003cp\u003e\u003cstrong\u003eQ:\u003c/strong\u003e Looking beyond CrossRef we’re delighted (Geoff) that you’ve agreed to be a speaker at one of our Executive Seminars again this year. In the past you’ve entertained our audience with a short history of the web and speculated on the role of social media. What are the three key messages about the web for the broader community involved in scholarly publishing in 2009?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA:\u003c/strong\u003e We are in the scholarly communications business, not just the scholarly publishing business. “Publishing” articles and monographs might have been the most efficient and trustworthy methods for publically communicating scholarly findings and for keeping a permanent record of those findings, but we cannot assume that this will continue to be the case. Modern tools like web-accessible databases, blogs, wikis, streaming audio/video and social citation services will continue to become increasingly important channels for scholarly communication. Whatever we do, we should not dismiss the new channels because they are not as reliable or authoritative as traditionally published content. It is precisely the fact that they are currently less reliable and trustworthy that represents such an opportunity for our industry. This leads to my second point.\u003c/p\u003e\n\u003cp\u003eSince the 1970s Carol Tenopir and Donald King have documented the trend that researchers are reading more articles, but spending less time reading each article. This trend is, by itself, unsustainable and it is actually being exacerbated by the proliferation of the above-mentioned new communication channels that researchers are increasingly going to feel obliged to follow.\u003c/p\u003e\n\u003cp\u003eWhat this means, as my former colleague Allen Renear likes to point out, is that researchers spend the bulk of their time practicing “reading avoidance.” That is, that researchers are engaged in a titanic struggle to figure out what they can safely ignore so that they can, in turn, focus their limited time and energy on reading what truly matters. This leads me to my third and final point.\u003c/p\u003e\n\u003cp\u003eScholarly publishing [sic] is essentially about trustworthy communication. How can we help researchers invest their time wisely? The successful publisher of the future will be able to say to the researcher- “I can save you a large percentage of your time by helping you filter-out what is irrelevant and focus only on what you need to do your research”.\u003c/p\u003e\n\u003cp\u003eThis role will only become more relevant and more valuable as the amount of information on the web continues to explode and this is the fundamental driving force behind much of the interest in technologies like text mining and the semantic web (aka Web 3.0).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQ:\u003c/strong\u003e Publishers, Wiley-Blackwell included, are exploring a few different avenues in innovating with online content – one of these is text mining. What’s your sense of how this might be used and what impact it might have?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA:\u003c/strong\u003e “Text mining” is a perfect example of researchers practicing “reading avoidance.” The basic idea behind text mining is that the researcher might be able to get the computer to extract and distill key data from the narrative in articles and books. The hope is that, once data has been extracted from a large enough collection of content, then researchers will be able to “data mine” the results in order to discover (excuse the Rumsfeldian phrase) “previously unknown knowns”. In other words, to find trends and correlations in the literature that would have been impossible or impractical to discover simply by reading the articles. In essence, “text mining” is really just an information extraction process in support of “data mining”.\nThe irony here, of course, is that when a researcher writes an article, they are essentially turning their data into human readable form and now we have those very same researchers hoping to turn the human readable article back into data. This is perverse, but it conveniently leads into the next question\u0026hellip;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQ:\u003c/strong\u003e What does Web 3.0 mean for you and what should it mean for us?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA:\u003c/strong\u003e The move from “Web 1.0” to “Web 2.0” is often described as the move from the “read-only web” to the “read-write web.” That is, whereas early web tools made it very difficult for casual users to create and publish content online, Web 2.0 tools like Blogs, Wikis, IM, photo/video sharing sites and social bookmarking systems made it relatively easy for everybody to create and publish content online.\u003c/p\u003e\n\u003cp\u003eIn this vein, “Web 3.0” has been described as the “read + write + compute web”. Web 3.0 is essentially synonymous with another phrase you might hear bandied about- “the semantic web.”\nThe “semantic web”, in turn, is a concept designed to address the issue discussed above- the irony that, despite the fact that the web is built on computers, the content being hosted on the web cannot easily be interpreted or analyzed by computers because most of it is narrative designed for human consumption. To illustrate the issue, look at the following sentences:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eI read it in \u003cem\u003eNature\u003c/em\u003e.\u003c/li\u003e\n\u003cli\u003eThe book captured the \u003cem\u003ezeitgeist\u003c/em\u003e of the time.\u003c/li\u003e\n\u003cli\u003eI am \u003cem\u003esure\u003c/em\u003e that I turned the gas off.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIn each of the above sentences, you can see that there are several italicized words and, without too much thought, you can tell that in each case, the word has been italicized for a different reason.\u003c/p\u003e\n\u003cp\u003eBut a computer has no way of telling that the word “Nature” has been italicized because it is a the title of a journal whereas the word “zeitgeist” has been italicized because it is a foreign phrase and the word “sure” has been italicized to indicate voiced emphasis.\u003c/p\u003e\n\u003cp\u003eThe problem is that web pages are full of examples like this where important semantic information is usable for humans but not for computers. This is particularly true in online scholarly articles where researchers record the names of chemicals, compounds, processes, people, places, concepts, etc. in narrative form and thus, effectively make the content difficult for a computer to read and process.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQ:\u003c/strong\u003e And finally, what do you think a “journal” or a “book” will look like in 10 years and what will they do that’s different from what they do today?\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA:\u003c/strong\u003e First of all, we need to distinguish between the “book” and the “journal” as:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePhysical objects (e.g. paper, stitching, covers, etc.)\u003c/li\u003e\n\u003cli\u003eStructural conventions for presenting content (articles, chapters, serialization, edi- tions, etc.)\u003c/li\u003e\n\u003cli\u003eBusiness models (subscription, purchase, lease, etc.)\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eClearly all of these aspects of the book and journal are related, but they are also too often conflated.\u003c/p\u003e\n\u003cp\u003eSo first I will tackle the “physical” aspect of books and journals.\u003c/p\u003e\n\u003cp\u003eThis past Christmas I was with my family and inlaws and at a certain point I realized that everybody in the house was reading something on either an iPod Touch, an iPhone or a laptop.\u003c/p\u003e\n\u003cp\u003eThey are not geeks like me, yet they weren’t even in the slightest bit self-conscious about it.\u003c/p\u003e\n\u003cp\u003eIn the next five years digital reading devices will start to dominate the publishing world just like MP3 players now dominate the music industry.\u003c/p\u003e\n\u003cp\u003eWill paper go away? No, but I understand people still like to do calligraphy, hand-bind books and listen to vinyl LPs despite the advent of the printing press the CD and MP3 players.\u003c/p\u003e\n\u003cp\u003eAnd just as a warning, I will openly mock anybody who trots out the tired old “4Bs” argument- that nothing can beat the paper book for reading on the Beach, Bus or in the Bath or Bed.\u003c/p\u003e\n\u003cp\u003eFirst of all, such reading accounts for a negligible percentage of the reading that we do in life. Secondly, I bet they can waterproof an electronic reader before they can waterproof a paper book. Have you ever fished a book out of the bathtub? It ain’t fun.\u003c/p\u003e\n\u003cp\u003eThe structural aspects of books and journals are also likely to change radically. This change I expect will take a bit longer, but it will be at least as profound as the physical change I talk about above. I should first explain that, in this case, by “books” I am referring to monographs and reference works. I’m sure that novels and such will change as well, as evidenced by the advent of cellphone novels in Japan[1], but I have a less clear idea of what these changes will are likely to look like.\u003c/p\u003e\n\u003cp\u003eOn the other hand I think that articles and monographs are going to undergo two types of structural changes. The first relates to the “Web 3.0”, semantic-web issues I described earlier. The second has to do with the periodicity of publications but first let me take what may seem like a detour.\u003c/p\u003e\n\u003cp\u003eRight now, we can go into a bookstore or library and pick up either a non-fiction book or a periodical and, without reading a word of the content, we can immediately tell whether what we have picked up is targeted at a scholarly market.\u003c/p\u003e\n\u003cp\u003eHow can we do this?\u003c/p\u003e\n\u003cp\u003eSimply, by looking to see whether the book or periodical contains the apparatus of a scholarly work- full bibliographic metadata, a proper table of contents, foot- notes and/or endnotes, abstracts, a bibliography, figure captions, graphs and tables.\u003c/p\u003e\n\u003cp\u003eThis kind of apparatus just doesn’t generally exist in non-scholarly publications. Now there are two important things to note about this apparatus, the first is that almost all it is designed to help the researcher “avoid reading.” That is, it is designed to allow the reader to more efficiently navigate the content, locate information that is important to them and, perhaps most importantly, ignore the rest.\u003c/p\u003e\n\u003cp\u003eWe tend to take this apparatus for granted because our use of it has become so deeply entrenched in our working habits. An interesting experiment to conduct is to go into a bookstore near a college campus and play a game of “identify the academic”.\u003c/p\u003e\n\u003cp\u003eJust watch how another customer examines the books. A layperson will remove a book from the shelf, glance at the cover, perhaps glance at the back cover, but then they will generally then open the book at the start and start flipping through it sequentially. Contrast this with an academic who will exhibit a far more complex ritual.\u003c/p\u003e\n\u003cp\u003eThey will take the book off the shelf, open it from the back and first peruse the index, and bibliography and any other back matter. Then they will skip to the front and look at the table of contents.\u003c/p\u003e\n\u003cp\u003eOften this is enough for the academic to assess the relevance of the work and, if it is deemed irrelevant, they will re-shelve it (with relief, I might add). It is only if the preceding ritual has not given them enough information that they will actually finally resort to opening the book (usually toward the middle (following and index entry or TOC heading of particular interest) and skimming the introductory and concluding paragraphs. All of this is, of course, a highly optimized way of “reading avoidance.”\u003c/p\u003e\n\u003cp\u003eNow all of this extra apparatus costs money to produce and it is really only expected by an academic audience. An academic expects that a serious publisher will invest the time and money in creating these “reading-avoidance tools” and I predict that they will develop the same expectation of semantic web (Web 3.0) tools. Researchers will simply expect to be able to look at a document and use tools to explore and visualize the chemical compounds discussed in the paper, the methodologies employed, the taxonomies referred to. The researcher will expect to be able to skim this information, just like they can now skim the back-matter of an article. More importantly, the researcher will expect to be able to use their tools to automatically search the semantic apparatus of many hundreds of articles and/or books in order to identify precisely those items that are relevant to their research. In short, semantic enrichment will be a sign of a serious scholarly publication.\u003c/p\u003e\n\u003cp\u003eThe second big structural change that I think will affect journals and books concerns the periodicity of publication. So much of the structure of journals and books is inherited from and based on practical compromises that needed to be made due of the physical nature of distribution.\u003c/p\u003e\n\u003cp\u003eJournal articles are bundled into issues, in part because it would have been too inefficient to send them out in paper form separately.\u003c/p\u003e\n\u003cp\u003eNew book editions are released only when the publisher feels that there is a critical mass of updated and/or corrected content to justify the expense of producing a new release.\u003c/p\u003e\n\u003cp\u003eEven then a new edition might be delayed so as to not eat into the sales of the older editions that are still in the sales pipeline.\u003c/p\u003e\n\u003cp\u003eOf course, to a researcher, this can mean the publication of their article is held up in order to make a complete issue, or an important revision of a book is delayed until after a warehouse has been emptied.\u003c/p\u003e\n\u003cp\u003eThis isn’t the only perversity that we have inherited. Consider also the common expectation that when a researcher publishes a paper on topic A and then later has slightly updated things to say about topic A, they are encouraged to write and publish an entire new paper.\u003c/p\u003e\n\u003cp\u003eWhen publishing in print, this was pretty much a practical limitation. There was no realistic way for an author to provide an update of an existing print article without incurring most of the production expense of writing an entirely new article. The practice has been further enshrined into our working habits because researchers are now actually rewarded for this behavior.\u003c/p\u003e\n\u003cp\u003eUnfortunately, this behavior on the part of the researcher “as an author” makes their life “as a reader” miserable.\u003c/p\u003e\n\u003cp\u003eReaders are hugely frustrated by having to closely read several articles by an author that appear to say mostly the same thing. This practice thwarts their best efforts at reading avoidance.\u003c/p\u003e\n\u003cp\u003eThe issue can be similar, though less severe with books. At least with books there is the general convention of including “an introduction to the new edition”, which outlines the differences between the editions.\u003c/p\u003e\n\u003cp\u003eIn either case, researchers who are now accustomed to seeing other sorts of online in- formation updated continually (indeed, continuously) are likely to start demanding similar speed increases from scholarly publishers.\u003c/p\u003e\n\u003cp\u003eSo, I expect that the second major structural change that we will see with books and journals is that we will start to update existing publications instead creating new publications or new editions of publications.\u003c/p\u003e\n\u003cp\u003eI’ve already experienced this shift as a consumer of technical books with the Pragmatic Programmer’s “Beta Books” program and O’Reilly’s similar “Rough Cuts” feature on the Safari service.\u003c/p\u003e\n\u003cp\u003eIn each case, I am able to subscribe to a book and see each new edition, as it is being edited and worked on by the author. The payoff of this system when following rapidly-moving technologies is immense. Just being able to see how one edition of a book metamorphoses into the next edition greatly assists me in fine-tuning my reading avoidance strategy.\u003c/p\u003e\n\u003cp\u003eFinally, I have focused above on the structural changes that “books” and “journals” might undergo. I think that it is at least equally important for publishers to consider structural formats that are not based on either the book or the journal.\u003c/p\u003e\n\u003cp\u003eOne question we should all be asking ourselves is, given the apparent demand for text mining and semantic web functionality, does it make sense for us to publisher “data converted into narrative?” Maybe we should be figuring out how to publish data annotations?\u003c/p\u003e\n\u003cp\u003eAnd this leaves us with considering the “book” and the “journal” as business models. Given how I’ve blathered, you might be happy to hear that I don’t have much to say here other than to address the inevitable concern that publishers raise when I bang on about these changes. That is, making these changes will be hard, will cost money, and there appears to be little appetite for spending money on content these days.\u003c/p\u003e\n\u003cp\u003eMy only point here is this, all of the traditional apparatus that we included in print books also cost money and has always made the production of scholarly works a more expensive endeavour than producing similar trade content. This is particularly true when you consider the relative economies of scale between scholarly and trade publishing. On the other hand, investing in including this apparatus was important for several reasons:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eIt helped researches avoid reading\u003c/li\u003e\n\u003cli\u003eIt’s mere presence helped researchers identify works that were meant to be treated seriously\u003c/li\u003e\n\u003cli\u003eIt was almost completely impractical for authors or amateur publishers to create this apparatus on their own.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eNow one of the problems that we face as an industry is that it is relatively easy for authors and amateur publishers to create traditional bibliographic apparatus on their own. Word processors make it trivial to create a passable table of content, index and bibliography (note I said “passable”, not “good”. I don’t want any indexers out there to moan at me about what we are missing by not having hand-made indexes.).\u003c/p\u003e\n\u003cp\u003eCombine this with the relative ease of online distribution, and you get people actively questioning what the value-add is of the publisher.\u003c/p\u003e\n\u003cp\u003eThis is precisely why I think publishers have to up their game. Provide researchers with a new, digitally focused apparatus that will help them avoid reading. This is hard work they can’t do easily on their own. Publishers can do it and add value in the process. If we could tell re- searchers that we could save them a significant percentage of their time by allowing them to easily determine what not to read, they’ll be happy to pay for it.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eW-B:\u003c/strong\u003e Thank you!\u003c/p\u003e\n","date_modified":"2009-06-18T00:00:00Z","date_published":"2009-06-18T00:00:00Z","id":"https://doi.org/10.59347/618hp-wg778","summary":"I made several predictions in this interview, and it's interesting to see which ones played out.","title":"Your starter for ten","url":"https://gbilder.com/blog/2009/06/your-starter-for-ten/"},{"authors":[{"name":"gbilder"}],"content_html":"\u003cp\u003eIn 2009 \u003ca href=\"https://front-matter.io/team\"\u003eMartin Fenner\u003c/a\u003e sent me an email asking to interview me about the \u0026ldquo;Author Identifier\u0026rdquo; project I was working on for Crossref (later to become \u003ca href=\"https://rcid.org\"\u003eORCID\u003c/a\u003e). I had no idea who Martin was, but he asked intelligent questions and so I answered them. The result is below. And Martin and I have been friends/colleagues ever since.\u003c/p\u003e\n\u003cp\u003eFenner, M. (2009). Author Identifiers: Interview with Geoffrey Bilder. \u003ca href=\"https://doi.org/10.53731/r294649-6f79289-8cw1h\"\u003ehttps://doi.org/10.53731/r294649-6f79289-8cw1h\u003c/a\u003e\u003c/p\u003e\n","date_modified":"2009-02-17T00:00:00Z","date_published":"2009-02-17T00:00:00Z","id":"https://gbilder.com/blog/2009/02/fenner-interview/","title":"Author Identifiers: Interview with Geoffrey Bilder","url":"https://gbilder.com/blog/2009/02/fenner-interview/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eI was recently asked by somebody to speculate about generalizable application features that might help researchers in their work. I responded to them directly, but thought it might be worth repeating part of my response here.\u003c/p\u003e\n\u003cp\u003eSince the early 1990s I’ve wished that the OS (any OS) would support a “Paste \u0026amp; Cite” feature and, now that I’m \u003ca href=\"https://www.crossref.org/news/2006-12-05-geoffrey-bilder-to-join-crossref/\"\u003einvolved\u003c/a\u003e with \u003ca href=\"https://www.crossref.org/\"\u003eCrossRef\u003c/a\u003e and its linking and (nascent) plagiarism detection initiatives, I am even more convinced that such a feature would be immensely valuable to anybody who does research. The basic idea behind the feature would be that the clipboard would also copy “provenance” information whenever somebody chose to copy something. Then, when the user decided to paste the content someplace else, it would offer an optional “Past \u0026amp; Cite” menu item.\u003c/p\u003e\n\u003cp\u003eThis is similar to \u003ca href=\"https://en.wikipedia.org/wiki/Ray_Ozzie\"\u003eRay Ozzie’s\u003c/a\u003e concept of the \u003ca href=\"https://web.archive.org/web/20061117124343/http://rayozzie.spaces.live.com/blog/cns!FB3017FBB9B2E142!285.entry\"\u003eLive Clipboard\u003c/a\u003e– but I think it is simpler and with a different emphasis. The goal here is not to copy structured data around- it is to keep track of where it came from in the first place. In the simplest case, “Paste \u0026amp; Cite” would just paste in a URI pointing to the origin of the content (e.g. a local file, a file on an SMB share or a web page). This alone would help immensely with those situations where one “loses track” of where quoted text, copied pictures, etc. came from. Apparently a large number of semi- plagiarism cases stem from authors inadvertently losing track of the provenance of material that they copy and paste (with the best intentions of citing the material). In more sophisticated scenarios, the system would be opportunistic and “Paste \u0026amp; Cite” might make use of Dublin Core + PRISM metadata imbedded in HTML or XMP in PDFs/ Images or ID3 in mp3s, etc. Again the idea would be to give people a simple (possibly even simplistic) way of keeping track of the provenance of something. And of course- if a \u003ca href=\"https://www.doi.org/\"\u003eDOI\u003c/a\u003e were present, the provenance information could make use of it in order to ensure that the URI doesn’t break.\u003c/p\u003e\n\u003ch2 id=\"afterword-december-2017\"\u003eAfterword (December, 2017)\u003c/h2\u003e\n\u003cul\u003e\n\u003cli\u003eApple\u0026rsquo;s iBooks has a function like this now.\u003c/li\u003e\n\u003cli\u003eI hope, that a proposed new \u003ca href=\"https://tools.ietf.org/id/draft-vandesompel-citeas-00.html\"\u003e\u003ccode\u003ecite-as\u003c/code\u003e link relation type\u003c/a\u003e will encourage more applications to provide this functionality with web resources.\u003c/li\u003e\n\u003c/ul\u003e\n","date_modified":"2007-03-28T06:39:59Z","date_published":"2007-03-28T06:39:59Z","id":"https://doi.org/10.59347/w4drr-k6h94","title":"Paste \u0026 Cite","url":"https://gbilder.com/blog/2007/03/paste-cite/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003e\u003ca href=\"https://web.archive.org/web/20061028152056/http://weblog.infoworld.com/udell/2006/09/05.html\"\u003eJon Udell\u003c/a\u003e and \u003ca href=\"http://ross.typepad.com/blog/2006/09/between_popular.html\"\u003eRoss Mayfield\u003c/a\u003e have are talking about the use of social software and trust-circles as tools to find relevant and authoritative content on the web. Sounds \u003ca href=\"/2005/06/i-want-to-subscribe-to-your-brain/\"\u003efamiliar\u003c/a\u003e. I’ve long thought trust circles (amongst other trust metrics) are key to addressing the “\u003ca href=\"/2006/04/the-internet-trust-anti-pattern\"\u003eInternet Trust Anti-Pattern\u003c/a\u003e“.\u003c/p\u003e\n\u003cp\u003eIt may sound incredibly un-hip and reactionary, but to hell with the wisdom of crowds. Watching the crowd might be entertaining, but when I need to work, I can get far better results if I constrain that crowd to a few people whose opinions I have reason to respect. I’d use the word “authority” again, but the word is overloaded. Just as the open access community struggles with “free as in beer” and “free as in freedom”, the user-generated-content crowd struggles with “authority” as in “power” and “authority” as in “expertise.”\u003c/p\u003e\n\u003cp\u003e(Take deep breath. Wipe foam from my mouth. Stop goose-stepping)\u003c/p\u003e\n\u003cp\u003eAnyway, Jon concludes that he had been optimistic about the progress that would be made in exploiting trust circles inferred from social software tools. He says:\u003c/p\u003e\n\u003cp\u003e“Before we can search transitively across trust circles, we’ve got to be able to search within them”\u003c/p\u003e\n\u003cp\u003eI would just add that, before we can search within them, we need to be able to identify the channels of information being generated by each member of the trust circle. I’ve talked about this before, but I want to be able to go to somebody’s blog page or email signature, click on a button like this:\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/brain-1.png\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003e…and automatically subscribe to that person’s del.icio.us, Flickr, iCal, last.fm and blog feeds. “Brain subscription” seems like a perquisite to trust-circle nirvana.\u003c/p\u003e\n","date_modified":"2006-09-06T09:06:02Z","date_published":"2006-09-06T09:06:02Z","id":"https://doi.org/10.59347/p96hw-h3m13","title":"Brain Subscription And Trust Circles","url":"https://gbilder.com/2006/09/brain-subscription-and-trust-circles/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eWill implementing a good information architecture destroy your \u003ca href=\"http://www.alexa.com/\"\u003eAlexa\u003c/a\u003e rating? Mike Davidson has done a \u003ca href=\"http://www.mikeindustries.com/blog/archive/2006/04/myspace-click-factory\"\u003ebrief analysis\u003c/a\u003e of \u003ca href=\"http://home.myspace.com/\"\u003eMySpace\u003c/a\u003e which basically shows that “Page Views” could be the new “\u003ca href=\"http://en.wikipedia.org/wiki/Source_lines_of_code\"\u003eLine Count\u003c/a\u003e” in stupid metrics.\u003c/p\u003e\n\u003cp\u003eI’ve often wondered if part of the attraction of MySpace is the air of “authenticity” conveyed by the hideously amateurish interface(s)? And now I can wonder how many marketers will take Davidson’s observations and perversely conclude that the more unnecessary page views they can get people to go through, the better. Usability be damned.\u003c/p\u003e\n\u003cp\u003eI already fret about what conclusions web site designers are likely to draw from the research that show that users scan web pages in an \u003ca href=\"http://labnol.blogspot.com/2006/04/where-should-i-place-google-ads-for.html\"\u003e“F” pattern\u003c/a\u003e. Will we see a new crop of web site designs that look like this?\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/F.jpg\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eAnd will we adjust our scan pattern to this?\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/Not-F.jpg\"/\u003e \n\u003c/figure\u003e\n\n","date_modified":"2006-09-05T16:13:46Z","date_published":"2006-09-05T16:13:46Z","id":"https://doi.org/10.59347/j6hdx-hht75","image":"https://gbilder.com/2006/09/the-f-word/assets/img/F.jpg","title":"The F-Word","url":"https://gbilder.com/2006/09/the-f-word/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eIn a \u003ca href=\"http://books.guardian.co.uk/review/story/0,,1814992,00.html\"\u003eGuardian article dated Saturday July 8 2006\u003c/a\u003e, Pico Iyer talks about how Google and other search engines have distorted the literary interview. He describes how interviewers prepare themselves by researching their subjects online and how search results tend to artificially highlight and emphasize interesting, but effectively trivial information about the interviewee. The author describes how he once, in some long-since forgotten interview, had mentioned \u003ca href=\"http://en.wikipedia.org/wiki/Van_Morrison\"\u003eVan Morrison\u003c/a\u003e as being an influence on his work and how almost every interviewer since has found this tidbit of information and incorporated it into their own interview. This repeated citation of the same fact has served only to exaggerate the actual importance of Van Morrison on the Author’s work. Of course, as these interviews also go online, the problem only gets worse. His Guardian article will make things worse. This blog entry will make things worse. Pico Iyer and Van Morrison are becoming forever intwined.\u003c/p\u003e\n\u003cp\u003eThis is just one of many examples of the peculiar side-effects of Google’s page ranking algorithms. In Google Scholar (GS) researchers can find both of GS’s ranking algorithms frustrating. The first one, based largely on the number of citations an article receives (a more scholarly version of PageRank ) has the annoying habit of listing all of the articles that are the most well-known at the top of search results. While this might be a great default behavior for a casual user or a student, it is sometimes irritating to the specialist researcher who presumably \u003cem\u003ealready knows\u003c/em\u003e the most important articles in their field. GS’s alternative is to list the articles in reverse chronological order, which effectively strips out any pretense of “importance.” I’m sure Google will eventually fix these GS eccentricities and introduce a ranking based on “citation velocity” or some other metric that effectively mixes currency and influence. In the mean time Google and Google Scholar have become a sort of \u003ca href=\"http://en.wikipedia.org/wiki/Network_effect\"\u003enetwork effect\u003c/a\u003e \u003ca href=\"http://en.wikipedia.org/wiki/Methamphetamine_psychosis\"\u003emeth-amphetamine\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eAs we get used to the peculiarities of the Internet, we sub-cognitively adjust our use of it accordingly. I remember in the late 1990s a colleague showed me some site that he had recently started to consult for statistics and data of some sort. I glanced at the site and, though it looked official enough, I almost immediately said to my colleague that I thought the site was bogus and that he’d better be deeply skeptical of its contents. Eventually he confirmed that the content on the site was utter bilge and he came to ask me how I had guessed that it would be. I looked at the site again and tried to figure out what tipped me off. As I said, the site itself looked official and my assessment certainly wasn’t based on the data (the nature of which I’ve since forgotten but that I certainly wasn’t qualified to assess), but something about it had made me uneasy. After a few puzzling minutes I realized what had made me suspicious- there was a tilde (~) in the URL. For those who never knew or have since forgotten, a tilde in a URL is a good indication that the URL in question is pointing to some individual’s private home directory on a *NIX based machine. The url “www.somewellknownorg.com/~ted/index.html” might look like it is official content from “somewellknownorg”, when it is actually pointing to home directory of somebody named “Ted” who happens to have an account on the somewellknoworg machine. One doesn’t often see such URLs these days, but back in those days they were fairly common. Somehow I had managed to subconsciously learn that a “tilde” in the URL should make me pause and since that incident I’ve confirmed with some of my geekier friends that they too had developed this unarticulated heuristic for determining the relative “authority” of content. We probably all have other such URL-based heuristics. I doubt many people trust URLs that have ip addresses in them. And we each have a notion of the relative trustworthiness of domain name endings (.COM, .CO.UK, .EDU, .NET, .RL), though we may not be actively aware of it.\u003c/p\u003e\n\u003cp\u003eA conversation at a recent conference made me realize that I’ve started to develop heuristics for dealing with the distorting effects of search engines. A colleague casually mentioned that he no longer looks at the first few search results returned by Google. He found the first three or four results to be of generally lower quality than those a little lower down in the result set. As soon as he said this, I realized that I had been doing the same thing for the past year or so. I find myself “starting” to look at Google search results about one third of the way down the page, skipping the first several results. Like my colleague, I’ve found that the first results seem to have an oddly distorted relevance ranking. I suspect that this is a side-effect of \u003ca href=\"http://www.google.com/technology/\"\u003ePageRank\u003c/a\u003e. Items that are more “interesting” filter to the top and “interesting” is not quite the same as “accurate”, “thorough” or “authoritative”. This, of course, is what Pico Iyer has encountered as he has become inexorably linked to Van Morrison.\u003c/p\u003e\n","date_modified":"2006-08-19T08:27:00Z","date_published":"2006-08-19T08:27:00Z","id":"https://doi.org/10.59347/p4mz8-ryw69","title":"Van Morrison, Crank and Google Scholar","url":"https://gbilder.com/2006/08/van-morrison-crank-and-google-scholar/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eI was recently pondering the characteristics of so-called “\u003ca href=\"http://www.amazon.co.uk/gp/product/1843533871/202-3689659-0049449?v=glance\u0026amp;n=266239\"\u003ecult fiction\u003c/a\u003e” and was trying to remember how it was that I learned about certain cult authors back before this thing called the Internet existed. How did I learn about \u003ca href=\"http://en.wikipedia.org/wiki/Kurt_Vonnegut\"\u003eVonnegut\u003c/a\u003e, \u003ca href=\"http://en.wikipedia.org/wiki/Pynchon\"\u003ePynchon\u003c/a\u003e, \u003ca href=\"http://en.wikipedia.org/wiki/Philip_Roth\"\u003eRoth\u003c/a\u003e? As I dredged through my memories I realized that I most probably ran across these authors whilst using an early analog social bookmarking system- the library checkout card.\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/iStock_000000375730Small.jpg\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eFor those who have never seen one of these things, they were little index-cards inserted into a sleeve that was glued to the inside back cover of library books. When you checked out a book, you would sign your name on a line on the card and the librarian would stamp the due date next to your name on the card and then file it. This was how they kept track of who had which books out and when they were due. When the book was returned, the card would be reinserted in the sleeve and the book would be re-shelved.\u003c/p\u003e\n\u003cp\u003eThe beauty of this system was that you could judge the popularity of a book by removing it from the shelf, flipping it open to the back inside cover and seeing how many times it had been signed out, when it was signed out and by whom. I now remember scouring though these things to see what might be worth reading. I remember looking for:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eMultiple cards. \u003ca href=\"http://www.baldwin-school.org/\"\u003eMy school\u003c/a\u003e was very small and not very old, so most of the books had only one card with only a few names on it. When you found a book that had been checked out so many times that it required multiple cards, you were almost certainly onto a winner. The exception, of course, was when the book had clearly been assigned to a class. In those cases the presence of several cards was usually a false positive.\u003c/li\u003e\n\u003cli\u003eThe names of older students that I respected. Don’t ask me why they had to be older, they just did. Not only that, but they had to be older than me *at the time that they checked out the book*. In other words, when I was thirteen, I wasn’t interested in what sixteen-year-old “Ben” had read when he was twelve, though I might give consideration to what he had checked out and read when he was fourteen or fifteen. Insane, in retrospect, but most of my behavior at the time now seems insane.\u003c/li\u003e\n\u003cli\u003eThe names of students or teachers that I didn’t respect. The presence of such a name virtually killed the chance that I might read the book. I suspect that I missed reading Douglas Adams in high-school because the checkout card listed a name that I didn’t approve of. Again- barking mad, but true.\u003c/li\u003e\n\u003cli\u003eMultiple sequential checkouts by a person. This was a sign that the book might be harder to read. Of course, to me that meant “better”. Sigh.\u003c/li\u003e\n\u003cli\u003eMultiple non-sequential checkouts by the same respected person. I interpreted this to be a sign that the book might even be worth re-reading.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eAnyway- I vividly remember finding \u003ca href=\"http://www.amazon.com/exec/obidos/redirect?tag=ws%26link_code=xm2%26camp=2025%26creative=165953%26path=http://www.amazon.com/gp/redirect.html%253fASIN=B000FJ9CGY%2526tag=ws%2526lcode=xm2%2526cID=2025%2526ccmID=165953%2526location=/o/ASIN/B000FJ9CGY%25253FSubscriptionId=02ZH6J1W0649DTNS6002\"\u003e“BREAKFAST OF CHAMPIONS” (Kurt Vonnegut)\u003c/a\u003e \u003ca href=\"http://www.amazon.com/exec/obidos/redirect?tag=ws%26link_code=xm2%26camp=2025%26creative=165953%26path=http://www.amazon.com/gp/redirect.html%253fASIN=B000FJ9CGY%2526tag=ws%2526lcode=xm2%2526cID=2025%2526ccmID=165953%2526location=/o/ASIN/B000FJ9CGY%25253FSubscriptionId=02ZH6J1W0649DTNS6002\"\u003e\u003cimg loading=\"lazy\" src=\"http://images.amazon.com/images/P/B000FJ9CGY.01-AIR1YILJKP5Y._SCTHUMBZZZ_.jpg\"\u003e\u003c/a\u003e and being astounded that it had four or five check-out cards stuffed into the back sleeve. The cards were a who’s-who of the most interesting seniors. Clearly I needed to read it.\u003c/p\u003e\n","date_modified":"2006-08-02T07:08:14Z","date_published":"2006-08-02T07:08:14Z","id":"https://doi.org/10.59347/we9rc-s4f83","title":"Early Social Bookmarking","url":"https://gbilder.com/2006/08/early-social-bookmarking/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eI was relatively late in learning of the term “\u003ca href=\"http://en.wikipedia.org/wiki/Backchannel\"\u003ebackchanne\u003c/a\u003el”. It describes a phenomena that I have been fumbling to explain to people as being *one* of several reasons for them to use instant messaging (IM) as a regular tool in the office. Whereas the term backchannel seems to be most often used to describe how tech conference attendees use IRC, Wikis and blogs to carry on parallel conversations and commentary during conference sessions, I have observed the phenomena in the office, in meetings and conference calls. I just that, until late last year, didn’t know it had a name.\u003c/p\u003e\n\u003cp\u003eAt my current job I have been busy evangelizing various collaborative technologies that I had found useful in the past, so one of the first things that I did was try to get everybody using instant messaging regularly. My colleagues are not geeks, but they are technologically savvy and more then willing to experiment with new tools. Being responsible business-headed sorts, they did ask me what practical use IM would be. They also wondered why one would use IM when one could use email instead.\u003c/p\u003e\n\u003cp\u003eI warned them that my answer would be idiosyncratic, but I listed the following reasons in descending order of importance:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePresence indication\u003c/li\u003e\n\u003cli\u003eBackchanneling. (Though, obviously, since at the time I didn’t know the term, I described it to them with some hand-wavy and not-to-convincing blather.)\u003c/li\u003e\n\u003cli\u003eLightweight interrupt checking\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eNote that the list mentioned nothing of “chatting”, though in the new environment of my new job I think that I might end up adding a new item to the list:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eWhispering\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong\u003ePresence Indication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eI admit it- I was once an IM sceptic and I was constantly berated by my IM-using colleagues (hi Jessica, hi Andrew, hi Leigh!) for never being online. Worse than being an IM skeptic, I was actually an IM boor- I would only launch IM when I wanted to get hold of somebody who I knew used IM and who was otherwise engaged on the phone or something. Fortunately my colleagues finally called me on my IM boorishness and even convinced me to support getting a company Jabber server installed. Once we had everybody in the company using Jabber, I grew to appreciate the importance of IM as a presence indicator. My old employer had 100+ employees scattered across four offices in the US and UK. The technical group that I ran also had a large contingent of telecommuting employees, so the Jabber presence list became, for me at least, the most tangible daily reminder of community that existed in the company. A year after we launched our in-house IM server, I ran across Apophenia’s \u003ca href=\"http://www.zephoria.org/thoughts/archives/2005/02/13/cultural_divide_in_im_presence_vs_communication.html\"\u003eentry on IM presence\u003c/a\u003e and recognized the described cultural divide all too well. Her article is essential reading for IM skeptics and *particularly* for IM boors.\u003c/p\u003e\n\u003cp\u003eBut my current environment is a little different. How much use is IM presence indication in a company of four people huddled together in a room the size of a garage? At first, my new colleagues grumbled a little at my IM evangelism, but they humored me and ran the software despite their understandable misgivings. After a few months of people traveling and working from home, I’m happy to say that IM presence has become an accepted substitute for actually being in the office. I knew that IM had really “made it” when one of my co-workers, who knew I was working from home on a particular day, called me up to berate me for not having launched my IM client.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eBackchanneling\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn my old job, backchanneling, or holding parallel IM conversations during meetings and conference calls, became a critical tool for making meetings shorter and more productive. There are two areas where I found backchanneling to be particularly effective:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eWallflower inclusion\u003c/li\u003e\n\u003cli\u003eTactical coordination\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cem\u003eWallflower Inclusion\u003c/em\u003e**\u003c/p\u003e\n\u003cp\u003e**\u003c/p\u003e\n\u003cp\u003eHaving grown up in Puerto Rico, there is little I like better than getting in a nice argument featuring much hand-waving and gesticulating. I actively seek out people who will engage in this kind of head-butting and, in my youth, I avoided anybody who couldn’t hold their own in such an encounter.\u003c/p\u003e\n\u003cp\u003eOver the years, I have been shocked to learn that there are actually mega-bright, quiet types out there (imagine!). I’ve also learned that these people don’t thrive in meetings , conference calls or other venues that favor the verbal. I was always chagrined when one of these people would send me email *after* a meeting with insights that could have easily changed the outcome of said meeting. I’m not sure how it started, but I eventually found myself using IM during meetings, to query the opinions of those who I knew were unlikely to speak up. Eventually, some of them started using IM as a kind of realtime text-to-speech gateway- channeling their opinions through the more verbal members of the group. I know this sounds bizarre and possibly dysfunctional, but it worked and it helped to make sure that even the shyest people were able to get their points across when it really mattered- not hours after a decision had already been made.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eTactical Coordination\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eLike the “wallflower inclusion”, I’m not sure how this began. I remember that occasionally, when on really long conference calls, some of the participants in the calls would start IM-ing each other commentary on the proceedings- usually snide remarks. Eventually this commentary turned into actual tactical coordination of the call: discussions of how to avoid known contentious issues, how to bring a particular thread to a close, when to take issues off-line and, most importantly, when people where starting to reach consensus. I am sure that our ability to carry on these parallel conversations allowed us to shorten conference call length and increase their utility. At worst, they at least allowed us to stay sane during interminable calls.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLightweight Interrupt Checking\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e“Got a sec?” is probably the most common IM that I send and receive. The ability to quickly check to see if somebody is willing to engage in a conversation is wonderful. A quick IM is far less obtrusive than a phone call, or worse, wondering into somebody’s office or cubicle. But in order for this technique to succeded you must:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eNot take offense when somebody replies “not just now”\u003c/li\u003e\n\u003cli\u003eLikewise, not feel obliged to reply “yes” to such queries\u003c/li\u003e\n\u003cli\u003eOnly use it when the subject that you want to discuss really warrants a real-time conversation and can’t just be handled via an asynchronous method like email or voicemail\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong\u003eWhispering\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor the past ten years I have either had an office or a fairly isolated cubicle and I didn’t have to worry much about distracting people with my blather. Now I’m sharing a small office with three people. On the whole I enjoy working with people in an open-plan office, but there are times when one of us is in crunch-mode on some project, and it really helps if interoffice banter and queries can be kept as unobtrusive as possible. This is where I’m learning the third great corporate use of IM- whispering. I suspect that my office-mates think that I still don’t use it this way often enough.\u003c/p\u003e\n","date_modified":"2006-06-13T17:20:12Z","date_published":"2006-06-13T17:20:12Z","id":"https://doi.org/10.59347/5btdf-4t836","title":"Backchannel","url":"https://gbilder.com/2006/06/backchannel/"},{"authors":[{"name":"gbilder"}],"content_html":"\u003cp\u003eIn the early days of the web, buzzword coinage relied on prefixes. Add an “e” or an “i” to any word or phrase and you had yourself a brand new business to flog.\u003c/p\u003e\n\u003cp\u003ei-widgets\u003c/p\u003e\n\u003cp\u003ee-grommits\u003c/p\u003e\n\u003cp\u003eA few years later- the infix became the basis for the buzz-worthy. The numeral “2” became \u003cem\u003ede rigueur\u003c/em\u003e.\u003c/p\u003e\n\u003cp\u003eb2c\u003c/p\u003e\n\u003cp\u003eb2b\u003c/p\u003e\n\u003cp\u003efan2team\u003c/p\u003e\n\u003cp\u003efarmer2market\u003c/p\u003e\n\u003cp\u003edog2vomit\u003c/p\u003e\n\u003cp\u003eAnd now it is the turn of the suffix and again it is numeric.\u003c/p\u003e\n\u003cp\u003eWeb 2.0\u003c/p\u003e\n\u003cp\u003eScience 2.0\u003c/p\u003e\n\u003cp\u003eReading 2.0\u003c/p\u003e\n\u003cp\u003eSloth 2.0\u003c/p\u003e\n","date_modified":"2006-06-10T00:22:57Z","date_published":"2006-06-10T00:22:57Z","id":"https://gbilder.com/2006/06/beginning-middle-end/","title":"Beginning, middle, end","url":"https://gbilder.com/2006/06/beginning-middle-end/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eThe “My Rating” feature on iTunes has always felt a little clumsy. First of all, I hardly ever listen to music on iTunes itself- I listen to most of my music on my iPod. Secondly, I don’t want to have to *do* anything convoluted or extra in order to register that I like or dislike a song. I am surprised that Apple, given its user interface prowess, hasn’t managed to take better advantage of natural user behavior in order to more effectively drive the ratings system. In short:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eIf I play a song multiple times in a row, it probably means I like it. Increment the rating.\u003c/li\u003e\n\u003cli\u003eWhen I repeatedly turn up the volume on a song- it probably means I like it. Increment the rating.\u003c/li\u003e\n\u003cli\u003eWhen I repeatedly skip a song, I probably don’t like it. Decrement the rating.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eI have taken to quoting Bradely Horowitz’s \u003ca href=\"http://www.elatable.com/blog/?p=5\"\u003eobservation\u003c/a\u003e that “\u003cspan style=\"font-size:13pt;\"\u003ethe act of consumption is itself an act of creation”. The iTunes/iPod UI team should be well positioned to exploit this phenomena. \u003c/span\u003e\u003c/p\u003e\n","date_modified":"2006-04-23T17:07:24Z","date_published":"2006-04-23T17:07:24Z","id":"https://doi.org/10.59347/4cw0s-mvg15","title":"User Behavior As A Music Rating Cue","url":"https://gbilder.com/2006/04/user-behavior-as-a-music-rating-cue/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eI am afraid that the Wikipedia is a classic case of what I’ve come to term “the internet trust anti-patttern”. It goes something like this:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eA communication/collaboration system is started by self-selecting core group of high-trust technologists (or specialists of some sort).\u003c/li\u003e\n\u003cli\u003eSaid system is touted as authority-less, non-hierarchical, etc. But this is not true (see 1).\u003c/li\u003e\n\u003cli\u003eThe general population starts using the system.\u003c/li\u003e\n\u003cli\u003eThe system nearly breaks under the strain of untrustworthy users.\u003c/li\u003e\n\u003cli\u003eRegulatory controls are instituted to restore order. Sometimes they are automated, sometimes not.\u003c/li\u003e\n\u003cli\u003eIf the regulatory controls work, the system survives and is again touted as authority-less, non-hierarchical, etc. But this is not true (see 5).\u003c/li\u003e\n\u003cli\u003eIf the regulatory controls don’t work, the system becomes marginalized or dies.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eThink of Usenet, think of IRC, think of email, think of P2P networks- they’ve all gone through this cycle. Some have survived and other have effectively died.\u003c/p\u003e\n\u003cp\u003eI’ve been \u003ca href=\"http://www.uksg.org/presentations4/bilder.pdf\"\u003espeaking\u003c/a\u003e (large PDF) and \u003ca href=\"http://www.hti.umich.edu/cgi/t/text/text-idx?c=jep;cc=jep;rgn=main;view=text;idno=3336451.0009.101\"\u003ewriting\u003c/a\u003e publicly about the issue of trust and the internet for two years now. This \u003ca href=\"http://technology.guardian.co.uk/weekly/story/0,,1752257,00.html\"\u003erecent article on the Wikipedia in The Guardian\u003c/a\u003e sounds familiar. Tim Bray has \u003ca href=\"http://www.tbray.org/ongoing/When/200x/2006/04/13/Wikipedia\"\u003ealready attacked it.\u003c/a\u003e “Sophmore philosophy” [sic] seems a bit rich given that the same can be said most pro-wikipedia philosophizing.\u003c/p\u003e\n\u003cp\u003eThe Register \u003ca href=\"http://www.theregister.co.uk/2006/04/18/wales_sanger_interviews/\"\u003ealso has a piece on Wikipedia\u003c/a\u003e. Not exactly balanced, but I doubt that this debate is never going to be.\u003c/p\u003e\n\u003cp\u003eI keep delaying posting this and keep running across more informed discontent- this time by \u003ca href=\"http://www.zephoria.org/thoughts/archives/2006/04/15/on_being_notabl.html\"\u003eApophenia\u003c/a\u003e and \u003ca href=\"http://www.archive.org/details/20060408-jscott-wikipedia\"\u003eJason Scott\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eOf course, the internet trust anti-pattern applies to more than the just the Wikipedia. \u003ca href=\"http://www.kuro5hin.org/story/2006/4/12/93756/9085\"\u003eKuro5hin\u003c/a\u003e is having problems.\u003c/p\u003e\n\u003cp\u003eI’ve written about \u003ca href=\"http://getoutfoxed.com/about\"\u003eOutfoxed\u003c/a\u003e as a possible model for a generalizable way of dealing with the anti-pattern. The \u003ca href=\"http://www.eclipse.org/higgins/\"\u003eHiggins\u003c/a\u003e project looks promising too.\u003c/p\u003e\n\u003cp\u003eAnyway, I’d like to be wrong on Wikipedia.\u003c/p\u003e\n","date_modified":"2006-04-22T11:33:21Z","date_published":"2006-04-22T11:33:21Z","id":"https://doi.org/10.59347/atyeh-17291","title":"The Internet Trust Anti-Pattern","url":"https://gbilder.com/2006/04/the-internet-trust-anti-pattern/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eThe following, from Jorge Luis Borges, reminds me of some software projects I’ve seen…\u003c/p\u003e\n\u003cp\u003e“.. In that Empire, the Art of Cartography reached such Perfection that the map of one Province alone took up the whole of a City, and the map of the empire, the whole of a Province. In time, those Unconscionable Maps did not satisfy, and the Colleges of Cartographers set up a Map of the Empire which had the size of the Empire itself and coincided with it point by point. Less Addicted to the Study of Cartography, Succeeding Generations understood that this Widespread Map was Useless and not without Impiety they abandoned it to the Inclemencies of the Sun and of the Winters. In the deserts of the West some mangled Ruins of the Map lasted on, inhabited by animals and Beggars; in the whole Country there are no other relics of the Disciplines of Geography.”\u003c/p\u003e\n\u003cp\u003e— Jorge Luis Borges\u003c/p\u003e\n\u003cp\u003eOne can easily substitute a few words in the above, and it sounds remarkably familiar….\u003c/p\u003e\n\u003cp\u003e“.. In that Product, the Art of software architecture reached such Perfection that the UML diagram for the delivery of one feature alone took up the whole of a wall, and the functional spec of the project, the whole of an office. In time, those Unconscionable Specs did not satisfy, and the software architects wrote up a Specification of the Application which had the size of the Application itself and coincided with it point by point. Less Addicted to the Study of software architecture, Succeeding Generations understood that this Widespread Specification was Useless and not without Impiety they abandoned it to the Inclemencies of the Executives and of the Board. In the conference rooms of the West some mangled Ruins of the Specification lasted on, inhabited by middle managers and Contractors; in the whole Company there are no other relics of the Discipline of Software Architecture.”\u003c/p\u003e\n\u003cp\u003e— Not Jorge Luis Borges\u003c/p\u003e\n","date_modified":"2006-04-19T16:31:23Z","date_published":"2006-04-19T16:31:23Z","id":"https://doi.org/10.59347/x9dnv-gmb75","title":"Jorge Luis Borges on Software Architecture","url":"https://gbilder.com/2006/04/jorge-luis-borges-on-software-architecture/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003ch1 id=\"abulafia\"\u003eAbulafia\u003c/h1\u003e\n\u003cp\u003eWay back in 1990, when I worked at Brown University, I wrote a hypertext application for the Macintosh called “Abulafia.” (named after the computer in Umberto Eco’s book, \u003ca href=\"https://www.amazon.co.uk/Foucaults-Pendulum-Umberto-Eco/dp/0099287153/ref=sr_1_1?crid=V3J761W5FNWG\u0026amp;keywords=foucaults\u0026#43;pendulum\u0026amp;qid=1552845684\u0026amp;s=gateway\u0026amp;sprefix=Foucoult%2Caps%2C431\u0026amp;sr=8-1\"\u003eFoucault’s Pendulum\u003c/a\u003e. Recently I found some old Zip disks onto which I archived my Brown work when I left the university in 1995. I asked a hardware magpie friend of mine if he had a way of reading old 100MB Zip cartridges and he did. Amazingly, the old Zip cartridges were still accessible (thanks Iomega) and even more amazingly, I was able to find an old binary of Abulafia and run it under OS X’s classic emulation mode (thanks Apple).\u003c/p\u003e\n\u003cp\u003eOver the past few years I had grown self-consious about my periodic foam-at-the-mouth-old-man-rants concerning the paucity of the web hypertext model and about “how when I was a lad (way before that dang InterWeb) we did \u003cem\u003ereal\u003c/em\u003e hypertext.” I was happy, therefor, to discover that my memories had not deceived me and that Abulafia did some pretty kick-ass stuff. It seemed like it might be a good idea to document some of this via some screencasts as I doubt Abulafia will be runnable for much longer- particularly not with the Apple move to Intel processors.\u003c/p\u003e\n\u003ch2 id=\"a-little-history\"\u003eA Little History\u003c/h2\u003e\n\u003cp\u003eAt the time I initially wrote Abulafia, the web was still an experiment at CERN and Apple’s \u003ca href=\"http://en.wikipedia.org/wiki/HyperCard\"\u003eHyperCard\u003c/a\u003e had practically co-opted the term “hypertext” despite really being an application development environment. Abulafia was partially a response to HyperCard and was inspired by IRIS’s industrial strength research hypertext environment, \u003ca href=\"http://www.scholars.nus.edu.sg/landow/cpace/ht/HTatBrown/Intermedia.html\"\u003eIntermedia\u003c/a\u003e. To a lesser extent, Abulafia was also influenced by Eastgate Systems’ “\u003ca href=\"http://www.eastgate.com/Storyspace.html\"\u003eStorySpace\u003c/a\u003e“- a hypertext system designed for the creation of interactive fiction. And of course all of these systems were, in turn, inspired by Ted Nelson’s \u003ca href=\"http://en.wikipedia.org/wiki/Project_Xanadu\"\u003eXanadu\u003c/a\u003e…\u003c/p\u003e\n\u003cp\u003eMy first version of Abulafia was – ironically – written in Hypercard. I demonstrated the first version of Abulafia to \u003ca href=\"https://listserv.brown.edu/cgi-bin/wa?A2=ind90\u0026amp;L=CHUG-L\u0026amp;P=R1659\"\u003eCHUG\u003c/a\u003e in October of 1990. Response to the HyperCard version of Abulafia was good. In fact, there was a brief period of time when Apple considered bundling it on Macintoshes sold to universities. Unfortunately- this was about the time that Apple decided that it wasn’t in the software business (Doh!) and spun out its software (including HyperCard) into a company called \u003ca href=\"http://en.wikipedia.org/wiki/Claris\"\u003eClaris\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eSome time during this period (chronology is hazy) I had grown sick of the limitations of HyperCard and rewrote Abulafia in a pseudo version of C++ that was then distributed with “\u003ca href=\"https://www.computer-dictionary-online.org/definitions-t/think-c.html\"\u003eThink C\u003c/a\u003e.” In about 1992-3 I think that I realized that the web was going to take off (I was a \u003ca href=\"http://en.wikipedia.org/wiki/NeXT\"\u003eNeXT\u003c/a\u003e developer and had seen early versions of the \u003ca href=\"http://www.w3.org/People/Berners-Lee/WorldWideWeb.html\"\u003eCERN web client\u003c/a\u003e) and I dropped development to focus on creating various web tools.\u003c/p\u003e\n\u003cp\u003eThe binary that I found on the Zip disks is the C++ version of Abulafia. I think I had to leave the source at Brown and I have no idea what happened to it.\u003c/p\u003e\n\u003ch2 id=\"the-current-state-of-abulafia\"\u003eThe Current State of Abulafia\u003c/h2\u003e\n\u003cp\u003eI was amazed when I managed to copy the binary off of the old Iomega disks and I was floored when I double-clicked on the application and it actually launched.\u003c/p\u003e\n\u003cp\u003eI didn’t have any good example hypertext “collections” and it was kind of a challenge to create demo collection because I had to be able to recreate all sorts of old versions of RTF, the old Apple “pict” graphics format, etc. Funnily enough, I had the least problem with multimedia formats because all Abulafia multimedia calls were done via the then-nascent QuickTime (although I can predictably crash Abulafia and the entire classic mode if I close any QuickTime window.)\u003c/p\u003e\n\u003cp\u003eAlmost everything in Abulafia still seems to work. The only things that I can’t get to work are links to external applications, “automatic” dictionary links (possibly because they were hard-coded to lookup words on the dictionary service I had running on my NeXT cube) and links into/out-off particular spans of audio/video. It is also evident that there are a number of memory leaks in the app- this becomes painfully clear when I play quicktime movies that are larger than the entire hard drive on the Mac II that I developed Abulafia on. Ah, memories…\u003c/p\u003e\n\u003cp\u003eAbulafia supported single-user “collections”, in which case it stored all links and document information in a special file within a collection folder, but it also supported multi-user collections, where documents were stored on network drives (AppleShare, I’m afraid) and link and document status information (e.g. document locks) were stored in a SQL database (Sybase, running on my NeXT cube). I’m afraid I can’t get it to work in multiuser mode anymore…\u003c/p\u003e\n\u003ch2 id=\"explanation-and-demonstration-of-abulafias-features\"\u003eExplanation and Demonstration of Abulafia’s Features\u003c/h2\u003e\n\u003cp\u003e(warning, the demo screencasts are large-ish QuickTime movies)\u003c/p\u003e\n\u003cp\u003eAbulafia supported links to and from text, graphics, sound and video/animation. In Abulafia, “links” were defined as connections between two sets of “spans” in two documents. A span could be a selection of text, an area of a graphic or the “in” and “out” points of video/sound. Spans were encoded in what I called “lightweight SGML” (XML didn’t exist back then). Links could also have arbitrary metadata associated with them. This architecture allowed Abulafia to support the following advanced linking features:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSaved document properties\u003c/strong\u003e: You could set specified documents to open automatically when a collection was opened. You could also save the size and position of documents so that they always opened in the same place.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eBasic linking\u003c/strong\u003e: Links to and from text, graphics, sound and video/animation. Note that links \u003cem\u003efrom\u003c/em\u003e sound, video and animation don’t seem to be working, but this was a pretty cool feature. You could, for instance, have a video open up a text document when a certain point of the video was reached.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDemo 1\u003c/strong\u003e: Here I launch Abulafia, set a default overview image, link from the overview to a text document and then link from the text document to a photograph. Finally, I save the collection and quit Abulafia.\u003c/p\u003e\n\u003cvideo class=\"video-shortcode\" preload=\"auto\" controls\u003e\n    \u003csource src=\"assets/img/01.webm\" type=\"video/webm\"\u003e\n    There should have been a video here but your browser does not seem\n    to support it.\n\u003c/video\u003e\n\u003cp\u003e\u003cstrong\u003eOverlapping links\u003c/strong\u003e: The same span of text or area of a document could link to several places at one. Clicking on a linked span would provide a popup menu of the relevant links, whilst double-clicking on an active span would launch a dialog box listing the relevant links. Think of this as the ability to support overlapping HREFs.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRenaming links\u003c/strong\u003e: Links could be renamed and remain persistent.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLink annotation\u003c/strong\u003e: Links could be annotated. All links were stamped with their author name and time of creation. Link authors were able to provide short explanatory text for each link. This explanatory text would only appear in the link dialog box (not the link popup). This was actually all based on a generic ability to attach any metadata to a link. Note that, under OS X, Abulafia seems unable to determine a username and defaults to “Jane Doe” as the username. Hardly a surprise that this doesn’t work as I was probably grabbing the username from AppleShare settings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDemo 2\u003c/strong\u003e: Here I launch Abulafia again to show that the overview document now opens automatically. I follow the link to the text document, and then add two overlapping links to the same place that I linked from in example 1. I then rename and annotate the links to help disambiguate them. This example shows a link into a QuickTime movie (I don’t close the movie because doing so crashes everything).\u003c/p\u003e\n\u003cvideo class=\"video-shortcode\" preload=\"auto\" controls\u003e\n    \u003csource src=\"assets/img/02.webm\" type=\"video/webm\"\u003e\n    There should have been a video here but your browser does not seem\n    to support it.\n\u003c/video\u003e\n\u003cp\u003e\u003cstrong\u003eAsynchronous linking\u003c/strong\u003e: When creating links, the author could start and end links in any order. This was really just an authoring convenience, but other hypertext systems of the time made linking documents a pretty tedious process.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMulti-headed links\u003c/strong\u003e: Links that could originate from several spans within the same document. Handy, for instance, if you wanted to link from all of the examples of X in document A to a detailed explanation of X in document B. Under OS X all link types except for multimedia in/out points seem to still work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMulti-tailed links\u003c/strong\u003e: Links that targeted several spans within a document. For instance, you might want to link from the definition of X in document A to all examples of X in document B.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDemo 3\u003c/strong\u003e: I open the text document again, and start several links. I then open the target documents and end the links. I go to the initial document again and start a “multi-headed link” from the several instances of the word “HyperCard”. I then rename the link to show that both anchors point to the same link. Finally, to demo a “multi-tailed link” I open a document that defines the word “Adjective” and I link it to four examples of adjectives in a not-very-original sample sentence.\u003c/p\u003e\n\u003cvideo class=\"video-shortcode\" preload=\"auto\" controls\u003e\n    \u003csource src=\"assets/img/03.webm\" type=\"video/webm\"\u003e\n    There should have been a video here but your browser does not seem\n    to support it.\n\u003c/video\u003e\n\u003cp\u003e\u003cstrong\u003eAuto links\u003c/strong\u003e: Links to queries. So, for instance, you could link to a search for all instances of the word “foo” in any document. Again, this feature is broken under OS X- possibly because Abulafia can no longer find my NeXT cube ;-).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConditional Links\u003c/strong\u003e: Links that would be active or inactive depending on certain conditions. The conditions supported were “link state”, “date”, “time” and “random”. They worked like this:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003eState\u003c/strong\u003e: Links activate or deactivate depending on the whether or not other links have already been followed. For instance, could make a user have to follow a link to the introduction before they were alowed to follow links to more advanced topics. This could also be used by the interactive fiction crowd to create stories that changed as you navigated them.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eDate\u003c/strong\u003e: Links only activate or deactivate depending on a date condition. So, for instance, you could have links that are only active before X date, only active after X date or only active between dates X and Y. This feature was put in to support learning management features (e.g. You can not access the answers to the problem sets until after their due date). It could also be used for creating date/time sensitive interactive fiction.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eTime\u003c/strong\u003e: Similar to the above. You could set links to only activate at certain times. For some reason, this feature doesn’t seem to be working under OS X.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eRandom\u003c/strong\u003e: Links are given a 1 in N chance of being active. This feature was put in to support interactive fiction applications and it doesn’t seem to be working under OS X.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eOf course you could combine conditions so that you could say that a certain link had a 1 in 2 chance of being active in the morning and a 1 in 100 chance of being active in the afternoon, but only after December 29th, 1996 and only if the user had already followed the link to the narrative about the butler. Kinda cool, if you were into that sort of thing.\u003c/p\u003e\n\u003cp\u003e[Demo 4][13]: I set a “state condition” on the link to the “Abulafia’s Features” document that only makes the link active if the user has already followed the “Abulafia Development” link. I also show how, if one wanted to, one could add a date condition to the link.\u003c/p\u003e\n\u003cvideo class=\"video-shortcode\" preload=\"auto\" controls\u003e\n    \u003csource src=\"assets/img/04.webm\" type=\"video/webm\"\u003e\n    There should have been a video here but your browser does not seem\n    to support it.\n\u003c/video\u003e\n\u003cp\u003e\u003cstrong\u003ePersistent links\u003c/strong\u003e: Both originating and target documents could be edited and link integrity would be maintained as long as said documents continued to contain at least one origin and target span. When all all relevant origin or target spans were deleted, then the link would be deleted (after warning the user).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDemo 5\u003c/strong\u003e: I open the text document, unlock it, and edit it. Finally, I show that all the anchors still exist and all the links persist.\u003c/p\u003e\n\u003cvideo class=\"video-shortcode\" preload=\"auto\" controls\u003e\n    \u003csource src=\"assets/img/05.webm\" type=\"video/webm\"\u003e\n    There should have been a video here but your browser does not seem\n    to support it.\n\u003c/video\u003e\n\u003cp\u003eAnyway, I’m happy that I have finally been able to document Abulafia. Perhaps now I will stop frightening youngsters with tales of the hypertext systems of yore…\u003c/p\u003e\n","date_modified":"2005-07-01T16:00:02Z","date_published":"2005-07-01T16:00:02Z","id":"https://doi.org/10.59347/enn0g-06q87","title":"Abulafia","url":"https://gbilder.com/2005/07/abulafia/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eIn \u003ca href=\"/2005/06/two-graphs-that-explain-most-it-dysfunction-part-i/\"\u003ePart I\u003c/a\u003e, I described two graphs that I think help explain much IT dysfunction.\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/benefit_risk.png\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eI also noted that, typically:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePeople in group A will often talk to and solicit advice from people in group C. (think VC or CEO talking to technical guru)\u003c/li\u003e\n\u003cli\u003eThere are relatively few people in group C. (some companies might not have anybody internal in group C- they hire consultants or read expert opinion)\u003c/li\u003e\n\u003cli\u003eMost of the people who actually have to implement and maintain new technologies are in group B.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eClearly there are lots of gradations between A \u0026amp; C \u0026amp; B, so I am using the groups as a convenient way to refer to the extremes. In the case of group B, the extreme is people with relatively-solid technical credentials but who are very cynical about technology and are very risk-averse. There are a few things that one often finds with group B:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eGroup B are adverse to risk because, when things go wrong, they are on the front lines having to deal with the aftermath.\u003c/li\u003e\n\u003cli\u003eGroup B are rewarded for keeping things predictable and consistent- change and the risk that goes with it are anathema.\u003c/li\u003e\n\u003cli\u003eGroup A and C perceive group B as being, at best, passive aggressive and, at worst, obstructionist. Sometimes this is true.\u003c/li\u003e\n\u003cli\u003eGroup B views groups A and C as being out-of-touch and/or irresponsible. Sometimes this is true.\u003c/li\u003e\n\u003cli\u003eEven though both group A and C are frustrated by group B, if there is ever any contention between groups A and B, group C will usually align with group B because they share technical DNA and members of group C were once (at least briefly) members of group B.\u003c/li\u003e\n\u003cli\u003eA large percentage of the technical world never progresses beyond group B.\u003c/li\u003e\n\u003cli\u003eGroup B makes up most of the total IT salary cost of an organization\u003c/li\u003e\n\u003cli\u003eIndividual members of Group C cost significantly more than individual members of group B\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eIn your typical organization, you will often find that the helpdesk, QA, network administration, and facilities groups are at the apex/trough of the risk benefit curves in group B. I have to emphasize that this is not meant to be slamming group B. As shown above- there are often very good reasons for group B’s world outlook.\u003c/p\u003e\n\u003cp\u003eSo why am I faffing on about this? Well, having spent about ten years managing technical groups, I have found that a very large percentage of my time has been spent dealing with the tensions described in this chart. The superficially similar world outlook of senior management (group A) and the technorati (group C) can often lead to trouble when both groups are largely dependent on a third group- the technological Eeyore’s of the world- group B. The danger comes when group B completely dominates an organization and makes it impossible for them to innovate, or, conversely, when groups A and C, underestimate the legitimate concerns of group B. I’ve witnessed a few different strategies for trying to manage the technology disfunction caused by the different world views of groups A, B and C and they generally fall into the following categories:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eIgnore Group B\u003c/strong\u003e: This is probably the most common strategy the companies adopt when they feel paralyzed by IT dysfunction (though calling it a “strategy” is probably just dignifying what was really a muddle). The typical scenario is- A major project is estimated and planned by senior management (A), with very occasional sanity checks of isolated elements of the projects with some senior architects (C) and virtually no acknowledged input or buy-in from the poor sods who are going to implement and run the thing. The project radically misses the deadline, there are recriminations all around. Does this sound familiar? I bet it does.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eHire only group C\u003c/strong\u003e: This is often cited as the “Google strategy”, but it is common to many tech startups. In order to avoid the disconnects caused by the differing world views of groups A, B and C- just hire people in group C. The problem with this strategy is that, while it may work very well in the initial stages of a startup, it doesn’t scale very well. Either you have to eventually hire people in group B (even if you outsource it), or you are going to have a lot of pissed off senior engineers ineffectually doing things like product management, sales, helpdesk and basic systems administration. I guarantee you that Google has recently had to hire people in the A and B camps. I know because I’ve met them. Eventually Google too will have to deal with the ABC dynamic.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eOutsource\u003c/strong\u003e: This is probably the second most popular strategy for dealing with IT dysfunction. Without going into the debates about the ethics of outsourcing, it is important to note that, in the context of dealing with the disconnects between groups A, B and C- outsourcing is simply a displacement activity (in the psychological sense- obviously this is literally true as well). It has long been noted by outsourcing specialists that you are only likely to succeed in outsourcing something that you already know how to manage. If you are having trouble managing a process, then outsourcing it will probably actually exacerbate your management problems. If a company outsources IT, they are still going to need an informed IT strategy and that strategy will still have to reconcile the differing world views of groups A, B and C. Outsourcing IT might temporarily mask IT management problems by making mistakes less costly, but I suspect that, in the longer-term, the cost will creep back up as management takes advantage of the “cheapness” to launch even more ill-informed and mismanaged IT projects.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTurn A into B:\u003c/strong\u003e This is the most original strategy that I’ve seen for dealing with problems inherent in the ABC dynamic. The CTO (group C) of a small technical company made a habit of hiring people from group A, and intensively training them to handle group B tasks. The advantage of this, from the company’s point of view, was that they had a group with the apparent expertise of group B, but with none of the cynicism and risk aversion typically associated with the group. The result was that, for a while, the company in question was incredibly agile and innovative and the company’s clients loved dealing with the IT group because their answer to everything was “Sure, that can be done. It will only take a few days”. In the long term, this strategy had some ultimately pernicious side effects. The reason that the team was initially able to deliver on its “it will only take a few days” promise was that they took shortcuts everywhere, didn’t build to scale and released alpha quality code that they would then spend months repairing and rewriting. Clients who were at first thrilled by the quick turn-around, grew increasingly disillusioned when almost every project had to be re-released N times before it really worked. And, of course, the cumulative effect of all of these problems was that eventually many members of the team developed much of the cynicism and risk-aversion typical of group B (though, to be fair, I should note that they still remained a remarkably optimistic bunch, considering what they went through).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTriangulate\u003c/strong\u003e: This is the dialectical process, but the key to it is recognizing that you have a three world views in the first place. Most companies just muddle along, knowing that there are different views, but not clearly understanding what informs those views or how they relate to each other. The problem is even worse for companies who have IT departments exclusively made up of group Bs- to them there just seems to be an unbridgeable gap between the non-tech and tech sides of the organization. Recognizing the three world views is the first step to being able to mange how much influence each group has over a company’s technical strategy.\u003c/p\u003e\n\u003cp\u003eThe two graphs illustrating the relationship between technical expertise and attitude toward the introduction of a new technology are descriptive not prescriptive- but they have always seemed to me to serve as a useful model against which to compare the interactions of an organization and its technology group.\u003c/p\u003e\n","date_modified":"2005-06-29T13:04:34Z","date_published":"2005-06-29T13:04:34Z","id":"https://doi.org/10.59347/98qfz-sck57","title":"Two graphs that explain most IT dysfunction (Part II)","url":"https://gbilder.com/2005/06/two-graphs-that-explain-most-it-dysfunction-part-ii/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eInspired by reading about other people’s \u003ca href=\"http://edu-blogger.blogspot.com/2005/05/my-blogging-weakness.html\"\u003eblogging weaknesses\u003c/a\u003e, I’ve decided to finally get this one off the back burner and post it. I’m pretty sure that this isn’t original, but I started thinking about this way back in 1996 (pre-social-bookmarking) and I’ve lost my pointer to whatever influenced it. Anybody who can set me straight- I’d appreciate it.\u003c/p\u003e\n\u003cp\u003eSo here goes.\u003c/p\u003e\n\u003cp\u003eThere are two graphs which, when seen together, explain a hell of a lot about various forms of dysfunction that you see in the technology world.\u003c/p\u003e\n\u003cp\u003eIn this first graph, \u003cstrong\u003eX\u003c/strong\u003e represents relative “technical expertise” and \u003cstrong\u003eY\u003c/strong\u003e represents the “perceived benefit” in the introduction of a new technology:\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/benefit.png\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eThe summary is that technical neophytes (A) tend to see high potential benefit in new technologies, while people who have a bit of technology experience (B) grow increasingly cynical about technology claims and can rattle-off the names of technologies that they have seen over-hyped and that have under-delivered. The interesting thing though, is that, as people become really expert in technology (C), their view of the potential benefits in new technology starts to increase again. At the far right of this scale I’m talking about the real experts- the alpha-geeks of the world.\u003c/p\u003e\n\u003cp\u003eIn the second graph, \u003cstrong\u003eX\u003c/strong\u003e again represents technical expertise, but \u003cstrong\u003eY\u003c/strong\u003e represents “perceived risk” associated with the introduction of a new technology:\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/risk.png\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eHere the curve is inverted, but the basic pattern is the same. The neophytes (A) are blissfully unaware of the things that can go wrong with the introduction of a new technology. The tech-savvy (B) are battle-scarred and have seen (and possibly caused) countless disasters. The alpha-geeks (C) have also seen their share of problems, but they have also learned from their mistakes and know how to avoid them in the future. The alpha-geeks understand how to manage the risk.\u003c/p\u003e\n\u003cp\u003eNow things get interesting when you map these two dynamics against each other:\u003c/p\u003e\n\u003cfigure\u003e\n    \u003cimg loading=\"lazy\" src=\"assets/img/benefit_risk.png\"/\u003e \n\u003c/figure\u003e\n\n\u003cp\u003eYou see that neophytes in group A have essentially the same world view as the alpha-geeks in group C, but for completely different reasons. The trouble starts when you realize that most of senior executives, venture capitalists and members of the popular press are in group A. At the other extreme, most R\u0026amp;D groups, architecture groups, independent consultancies, technology pundits, etc. are in group C . There are a few problems with this:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePeople in group A will often talk to and solicit advice from people in group C\u003c/li\u003e\n\u003cli\u003eThere are relatively few people in group C\u003c/li\u003e\n\u003cli\u003eMost of the people who actually have to implement new technologies are in group B.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSo you can start to see the problem.\u003c/p\u003e\n\u003cp\u003eIn \u003cstrong\u003e\u003ca href=\"/2005/06/two-graphs-that-explain-most-it-dysfunction-part-ii/\"\u003ePart II\u003c/a\u003e\u003c/strong\u003e I’l talk some more about group B and I’ll discuss some of the classic patterns that emerge when A, B and C try to work with each other.\u003c/p\u003e\n","date_modified":"2005-06-22T10:48:03Z","date_published":"2005-06-22T10:48:03Z","id":"https://doi.org/10.59347/9f77m-ewy98","title":"Two graphs that explain most IT dysfunction (Part I)","url":"https://gbilder.com/2005/06/two-graphs-that-explain-most-it-dysfunction-part-i/"},{"authors":[{"name":"Geoffrey Bilder","url":"https://orcid.org/0000-0003-1315-5960"}],"content_html":"\u003cp\u003eThe other day I was talking to a \u003ca href=\"http://www.ldodds.com/\"\u003eformer colleague\u003c/a\u003e and I was trying to explain how I have gradually switched to using an assortment of social content tools as my primary mechanism for finding relevant and authoritative information on the web. With these tools, I can subscribe to an assortment of RSS feeds produced by people who I trust and think of as authorities in their respective subjects. In short, I said, “I can subscribe to their brains”.\u003c/p\u003e\n\u003cp\u003eOr at least I can in theory… At the moment, for those of non-geekly tendencies, the practicalities of “subscribing to somebody’s brain” are a little daunting. If you have an RSS-aware browser or have installed one of the useful bookmarklets provided by the likes of bloglines, then subscribing to individual RSS feeds is relatively easy. The problem is that I might be interested subscribing to:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eWhat person X is blogging\u003c/li\u003e\n\u003cli\u003eWhat person X is bookmarking- on several social bookmarking sites (e.g. del.isio.us, CiteULike, Furl)\u003c/li\u003e\n\u003cli\u003eWhat person X is listening to (e.g. AudioScrobbler)\u003c/li\u003e\n\u003cli\u003eWhat person X is taking pictures of (e.g. Flickr)\u003c/li\u003e\n\u003cli\u003eWhat person X’s travel schedule is (e.g. iCal)\u003c/li\u003e\n\u003cli\u003eWhat books X is reading or planning on reading (e.g. Amazon wish lists)\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe first problem is finding out what feeds person X provides. Most of the time you have to ask them, or search through the individual services for the person’s name. If you are dealing with a relatively clued-in person, you might be lucky enough to find links to their various feeds off of their home page or in the margins of their blogs. If you are dealing with an uber-geek, then you might find this information encoded in their FOAF file. All that seems to be missing is the button titled “Subscribe to X’s Brain”.\u003c/p\u003e\n\u003cp\u003e\u003clazywebrequest\u003eThat is what I want- I want a bookmarklet or service that makes a best attempt to find all of the feeds that a person is publishing. If it detects a FOAF file, it will just use that to locate the feeds, if it doesn’t find a FOAF file, then it will make a bunch of educated guesses using a combination of the user’s name and the handy RESTFUL interfaces that most of these services support. Once it has located these feeds, it will create a new appropriately named folder in your favorite RSS reader and populate it with the feeds. Bonus points if it merges the feeds. A gold star if it periodically checks other services and auto-detects new feeds from that person\u003c/lazywebrequest\u003e\u003c/p\u003e\n\u003cp\u003eAnd as for the person who eventually writes this wonderful tool- I want to subscribe to their brain.\u003c/p\u003e\n","date_modified":"2005-06-14T21:05:34Z","date_published":"2005-06-14T21:05:34Z","id":"https://doi.org/10.59347/my5n6-7z30","title":"I want to subscribe to your brain","url":"https://gbilder.com/2005/06/i-want-to-subscribe-to-your-brain/"}]}