{"slug": "bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and", "title": "Bye Bye Perspective API: Lessons for Measurement Infrastructure in NLP, CSS and LLM Evaluation", "summary": "Perspective API, the de facto standard for toxicity measurement, will shut down at the end of 2026, exposing researchers' dependence on a tool they did not control, according to a paper by David Hartmann and colleagues. Surveying 241 papers, the authors found that reliance on Perspective led to unsupported claims, shifting results from silent model retraining, and unexplained disparities, which were amplified throughout the LLM lifecycle. They release Perspective scores for 5.9 million text snippets from 77 datasets and specify ten requirements for field-owned measurement infrastructure.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 28 Apr 2026 (\n\n[v1](https://arxiv.org/abs/2604.25580v1)), last revised 31 Aug 2026 (this version, v2)]# Title:Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure\n\n[View PDF](/pdf/2604.25580)\n\n[HTML (experimental)](https://arxiv.org/html/2604.25580v2)\n\nAbstract:Perspective API closes at the end of 2026, removing the de facto standard for toxicity measurement and exposing researchers' dependence on a tool they did not control. Drawing on this case, we argue that a research field must build and govern its own measurement infrastructure rather than borrow it. Surveying 241 papers that use or study Perspective, we show what depending on it cost the research community: claims reaching past what the tool could support, results that shifted when its model was silently retrained, and disparities researchers could measure but not explain. These failures were amplified throughout the LLM lifecycle, where Perspective supplied the labels, filtered the corpora, and graded the systems trained on each, rewarding errors rather than catching them. To keep the instrument open to study after shutdown, we release Perspective scores for 5.9 million text snippets from 77 datasets. We further specify ten requirements for measurement infrastructure a field owns, and argue that what blocks such infrastructure is not technical capability but the value the field places on infrastructure work.\n\n## Submission history\n\nFrom: David Hartmann [[view email](/show-email/1cbf4cb3/2604.25580)]\n\n**Tue, 28 Apr 2026 12:49:54 UTC (394 KB)**\n\n[[v1]](/abs/2604.25580v1)**[v2]** Mon, 31 Aug 2026 13:45:30 UTC (478 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and", "canonical_source": "https://arxiv.org/abs/2604.25580", "published_at": "2026-09-02 11:52:23+00:00", "updated_at": "2026-09-02 12:23:53.921311+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-research", "ai-ethics"], "entities": ["Perspective API", "David Hartmann", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and", "markdown": "https://wpnews.pro/news/bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and.md", "text": "https://wpnews.pro/news/bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and.txt", "jsonld": "https://wpnews.pro/news/bye-bye-perspective-api-lessons-for-measurement-infrastructure-in-nlp-css-and.jsonld"}}