{"id":"b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery | arXiv cs.AI","argument":"The authors argue that agentic AI scientists can already function as co-scientists, but are not built for autonomous scientific discovery. They identify four challenges. Problem selection is influenced by the McNamara fallacy; large language models (LLMs) omit tacit procedural and failure knowledge from laboratory practice in their training corpora. Preference optimisation during post-training compresses output diversity toward consensus. Most scientific benchmarks measure single-turn prediction accuracy without feedback from physical experiments to computational models. In the authors’ view, these are not merely problems of scale or scaffolding, but call for revisiting fundamental design choices. They recommend scientific simulations as verifiers for training and a persistent, mutable epistemic state that carries beliefs and shifting objectives across an investigation. They also recommend a centralized preregistration repository for AI-generated hypotheses, and applying AI scientists in response to scientific need rather than tool affordance. The abstract presents these as design recommendations; it does not spell out how to implement or evaluate them.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the paper's abstract; it does not include the paper's detailed arguments, examples, or evaluation of the proposed recommendations.","speaker":{"name":"Bisht, Harshit, Kumar, Vinay, Jablonka, Kevin Maik, Mausam, Krishnan, N. M. Anoop","roleAtSource":"Article author"},"source":{"title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2605.08956","publishedAt":"2026-05-09","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors argue that agentic AI scientists can function as co-scientists but are not built for autonomous scientific discovery.","excerpt":"although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery.","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors identify problem selection, missing laboratory knowledge, reduced output diversity, and limited experimental feedback in benchmarks as challenges.","excerpt":"Problem selection is influenced by the McNamara fallacy","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors say large language models' training corpora omit tacit procedural and failure knowledge of laboratory practice.","excerpt":"training corpora omit tacit procedural and failure knowledge of laboratory practice","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors recommend scientific simulations as verifiers for training, alongside changes to epistemic state, preregistration, and how applications are selected.","excerpt":"we recommend scientific simulations as verifiers for training, a persistent, mutable epistemic state","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2605.08956","checkedAt":"2026-11-09T10:48:08.118Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the authors propose implementing and evaluating scientific simulations as verifiers for training AI scientists?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery | arXiv cs.AI","summary":"The authors argue that agentic AI scientists can already function as co-scientists, but are not built for autonomous scientific discovery. They identify four challenges. Problem selection is influenced by the McNamara fallacy; large language models (LLMs) omit tacit procedural and failure knowledge from laboratory practice in their training corpora. Preference optimisation during post-training compresses output diversity toward consensus. Most scientific benchmarks measure single-turn prediction accuracy without feedback from physical experiments to computational models. In the authors’ view, these are not merely problems of scale or scaffolding, but call for revisiting fundamental design choices. They recommend scientific simulations as verifiers for training and a persistent, mutable epistemic state that carries beliefs and shifting objectives across an investigation. They also recommend a centralized preregistration repository for AI-generated hypotheses, and applying AI scientists in response to scientific need rather than tool affordance. The abstract presents these as design recommendations; it does not spell out how to implement or evaluate them.","question":"How do the authors propose implementing and evaluating scientific simulations as verifiers for training AI scientists?","claims":[{"text":"The authors argue that agentic AI scientists can function as co-scientists but are not built for autonomous scientific discovery.","excerpt":"although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery.","support":"source-stated"},{"text":"The authors identify problem selection, missing laboratory knowledge, reduced output diversity, and limited experimental feedback in benchmarks as challenges.","excerpt":"Problem selection is influenced by the McNamara fallacy","support":"source-stated"},{"text":"The authors say large language models' training corpora omit tacit procedural and failure knowledge of laboratory practice.","excerpt":"training corpora omit tacit procedural and failure knowledge of laboratory practice","support":"source-stated"},{"text":"The authors recommend scientific simulations as verifiers for training, alongside changes to epistemic state, preregistration, and how applications are selected.","excerpt":"we recommend scientific simulations as verifiers for training, a persistent, mutable epistemic state","support":"source-stated"}],"limitations":["The supplied evidence is the paper's abstract; it does not include the paper's detailed arguments, examples, or evaluation of the proposed recommendations."],"mediaId":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","correctionReason":null,"id":"b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726","publicationId":"b19f4942-288b-4958-8923-7f313c97b0a4","version":1,"sourceUrl":"https://arxiv.org/abs/2605.08956","sourceTitle":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-05-09","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-09T05:03:38.355Z","createdAt":"2026-11-09T10:16:08.852Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","kind":"article","url":"https://arxiv.org/abs/2605.08956","sourceUrl":"https://arxiv.org/abs/2605.08956","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T07:46:34.019Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2605.08956","checkedAt":"2026-11-09T10:48:08.118Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","confidence":0.91,"provider":"typesafe","model":"jev-1.13.0","inputHash":"e74650ef4e20ecfff36e963de2b8ff0e621bdc93bc7795aff326c836425c68df","decidedAt":"2026-11-09T07:46:35.724Z"},"provenance":{"textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observationId":"470580603a3f392ac8d58d0c62be600b85a642d5c99ddeb038a2cfb5980bb68f","retrievedAt":"2026-11-09T07:46:33.768Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"b2fa3588-1547-4b6a-8ae3-cd6e325d84b6"},"reviewer":{"model":"gpt-6-luna","runId":"d7ed90a0-802a-42ee-834f-4085c3a01fea"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T10:16:08.852Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Bisht, Harshit","url":null,"kind":"unknown"},{"name":"Kumar, Vinay","url":null,"kind":"unknown"},{"name":"Jablonka, Kevin Maik","url":null,"kind":"unknown"},{"name":"Mausam","url":null,"kind":"unknown"},{"name":"Krishnan, N. M. Anoop","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Bisht, Harshit","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Bisht, Harshit","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Kumar, Vinay","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kumar, Vinay","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Jablonka, Kevin Maik","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jablonka, Kevin Maik","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Mausam","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Mausam","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Krishnan, N. M. Anoop","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Krishnan, N. M. Anoop","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2605.08956","snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z","basis":"publisher-page-metadata","sourceLinks":46,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726/source"}},"canonicalUrl":"https://escapemeridian.com/readings/agentic-ai-scientists-are-not-built-for-autonomous-scientific-b15c980e","formats":{"html":"/readings/agentic-ai-scientists-are-not-built-for-autonomous-scientific-b15c980e","markdown":"/readings/agentic-ai-scientists-are-not-built-for-autonomous-scientific-b15c980e.md","json":"/readings/agentic-ai-scientists-are-not-built-for-autonomous-scientific-b15c980e.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-agentic","name":"Agentic AI","explanation":"AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.","referenceUrl":"https://developers.google.com/machine-learning/glossary#agentic"},{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-benchmark","name":"Benchmark","explanation":"A defined set of tests used to compare systems. Results depend on the tasks and measures selected.","referenceUrl":"https://arxiv.org/abs/2211.09110"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726","revision":"b19f4942-288b-4958-8923-7f313c97b0a4","revisionKind":"publication-id","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery | arXiv cs.AI","url":"https://escapemeridian.com/readings/agentic-ai-scientists-are-not-built-for-autonomous-scientific-b15c980e"},"source":{"type":"source","id":"https://arxiv.org/abs/2605.08956","revision":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","revisionKind":"sha256-source-text","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","url":"https://arxiv.org/abs/2605.08956"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery | arXiv cs.AI","argument":"The authors argue that agentic AI scientists can already function as co-scientists, but are not built for autonomous scientific discovery. They identify four challenges. Problem selection is influenced by the McNamara fallacy; large language models (LLMs) omit tacit procedural and failure knowledge from laboratory practice in their training corpora. Preference optimisation during post-training compresses output diversity toward consensus. Most scientific benchmarks measure single-turn prediction accuracy without feedback from physical experiments to computational models. In the authors’ view, these are not merely problems of scale or scaffolding, but call for revisiting fundamental design choices. They recommend scientific simulations as verifiers for training and a persistent, mutable epistemic state that carries beliefs and shifting objectives across an investigation. They also recommend a centralized preregistration repository for AI-generated hypotheses, and applying AI scientists in response to scientific need rather than tool affordance. The abstract presents these as design recommendations; it does not spell out how to implement or evaluate them.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the paper's abstract; it does not include the paper's detailed arguments, examples, or evaluation of the proposed recommendations.","speaker":{"name":"Bisht, Harshit, Kumar, Vinay, Jablonka, Kevin Maik, Mausam, Krishnan, N. M. Anoop","roleAtSource":"Article author"},"source":{"title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2605.08956","publishedAt":"2026-05-09","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors argue that agentic AI scientists can function as co-scientists but are not built for autonomous scientific discovery.","excerpt":"although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery.","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors identify problem selection, missing laboratory knowledge, reduced output diversity, and limited experimental feedback in benchmarks as challenges.","excerpt":"Problem selection is influenced by the McNamara fallacy","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors say large language models' training corpora omit tacit procedural and failure knowledge of laboratory practice.","excerpt":"training corpora omit tacit procedural and failure knowledge of laboratory practice","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"},{"text":"The authors recommend scientific simulations as verifiers for training, alongside changes to epistemic state, preregistration, and how applications are selected.","excerpt":"we recommend scientific simulations as verifiers for training, a persistent, mutable epistemic state","url":"https://arxiv.org/abs/2605.08956","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2605.08956","checkedAt":"2026-11-09T10:48:08.118Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the authors propose implementing and evaluating scientific simulations as verifiers for training AI scientists?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery | arXiv cs.AI","summary":"The authors argue that agentic AI scientists can already function as co-scientists, but are not built for autonomous scientific discovery. They identify four challenges. Problem selection is influenced by the McNamara fallacy; large language models (LLMs) omit tacit procedural and failure knowledge from laboratory practice in their training corpora. Preference optimisation during post-training compresses output diversity toward consensus. Most scientific benchmarks measure single-turn prediction accuracy without feedback from physical experiments to computational models. In the authors’ view, these are not merely problems of scale or scaffolding, but call for revisiting fundamental design choices. They recommend scientific simulations as verifiers for training and a persistent, mutable epistemic state that carries beliefs and shifting objectives across an investigation. They also recommend a centralized preregistration repository for AI-generated hypotheses, and applying AI scientists in response to scientific need rather than tool affordance. The abstract presents these as design recommendations; it does not spell out how to implement or evaluate them.","question":"How do the authors propose implementing and evaluating scientific simulations as verifiers for training AI scientists?","claims":[{"text":"The authors argue that agentic AI scientists can function as co-scientists but are not built for autonomous scientific discovery.","excerpt":"although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery.","support":"source-stated"},{"text":"The authors identify problem selection, missing laboratory knowledge, reduced output diversity, and limited experimental feedback in benchmarks as challenges.","excerpt":"Problem selection is influenced by the McNamara fallacy","support":"source-stated"},{"text":"The authors say large language models' training corpora omit tacit procedural and failure knowledge of laboratory practice.","excerpt":"training corpora omit tacit procedural and failure knowledge of laboratory practice","support":"source-stated"},{"text":"The authors recommend scientific simulations as verifiers for training, alongside changes to epistemic state, preregistration, and how applications are selected.","excerpt":"we recommend scientific simulations as verifiers for training, a persistent, mutable epistemic state","support":"source-stated"}],"limitations":["The supplied evidence is the paper's abstract; it does not include the paper's detailed arguments, examples, or evaluation of the proposed recommendations."],"mediaId":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","correctionReason":null,"id":"b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726","publicationId":"b19f4942-288b-4958-8923-7f313c97b0a4","version":1,"sourceUrl":"https://arxiv.org/abs/2605.08956","sourceTitle":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-05-09","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-09T05:03:38.355Z","createdAt":"2026-11-09T10:16:08.852Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","kind":"article","url":"https://arxiv.org/abs/2605.08956","sourceUrl":"https://arxiv.org/abs/2605.08956","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T07:46:34.019Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2605.08956","checkedAt":"2026-11-09T10:48:08.118Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"73eeffc4205f7f2ea0f1081a3ddc244268d643a176fd1f6216a366c4433390fd","confidence":0.91,"provider":"typesafe","model":"jev-1.13.0","inputHash":"e74650ef4e20ecfff36e963de2b8ff0e621bdc93bc7795aff326c836425c68df","decidedAt":"2026-11-09T07:46:35.724Z"},"provenance":{"textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observationId":"470580603a3f392ac8d58d0c62be600b85a642d5c99ddeb038a2cfb5980bb68f","retrievedAt":"2026-11-09T07:46:33.768Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"b2fa3588-1547-4b6a-8ae3-cd6e325d84b6"},"reviewer":{"model":"gpt-6-luna","runId":"d7ed90a0-802a-42ee-834f-4085c3a01fea"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T10:16:08.852Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Bisht, Harshit","url":null,"kind":"unknown"},{"name":"Kumar, Vinay","url":null,"kind":"unknown"},{"name":"Jablonka, Kevin Maik","url":null,"kind":"unknown"},{"name":"Mausam","url":null,"kind":"unknown"},{"name":"Krishnan, N. M. Anoop","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Bisht, Harshit","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Bisht, Harshit","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Kumar, Vinay","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kumar, Vinay","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Jablonka, Kevin Maik","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jablonka, Kevin Maik","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Mausam","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Mausam","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}},{"actor":{"name":"Krishnan, N. M. Anoop","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Krishnan, N. M. Anoop","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2605.08956","locator":"head/meta[name=author|citation_author]"},"assertionId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:48:08.118Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","sourceUrl":"https://arxiv.org/abs/2605.08956","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2605.08956","snapshotId":"1704aeda63462fe03c8102a473bbda83b5d61bf0804a6b099d97dda5f46d1e51","contentSha256":"6837b673bb91cc47fbdc982c1292c7621bc6bd661ddd9f926fd937efa44868d1","textHash":"489108fa5d37c0dcc90a92c410216195caa2f4e78d9924dcddc1849c9c922d73","observedAt":"2026-11-09T10:48:08.118Z","basis":"publisher-page-metadata","sourceLinks":46,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b15c980ef6705bd437dfc8848ce1c3b866e7f2b05900de59321bec1b7414f726/source"}}}],"audits":[{"publicationId":"b19f4942-288b-4958-8923-7f313c97b0a4","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading consistently presents the position as the authors' argument (\"The authors argue\", \"In the authors' view\"). It does not present those claims as established fact. The source is correctly identified as an arXiv cs.AI position paper by Bisht, Kumar, Jablonka, Mausam and Krishnan.","excerpt":"This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery."},{"dimension":"summary","status":"uncertain","explanation":"The reading tracks the abstract faithfully, but it leaves central jargon unexplained for a non-specialist: McNamara fallacy, agentic, preference optimisation/post-training, scaffolding, epistemic state, preregistration and tool affordance. A reader cannot grasp the first challenge without knowing that the McNamara fallacy means favoring what is easily measured. Smallest repair: add tooltips or one-clause glosses for these terms, plus one sentence on why autonomy versus co-scientist matters. Restoring the abstract's condition 'To build truly autonomous AI scientists' would also help. The NeurIPS 2026 position-track framing is omitted, though that is minor.","excerpt":"Problem selection is influenced by the McNamara fallacy"},{"dimension":"date","status":"pass","explanation":"originalPublished is 2026-05-09, which matches the v1 submission date. It does not match the later v3 revision (6 Nov 2026) or the feed date (9 Nov 2026).","excerpt":"[Submitted on 9 May 2026 (v1), last revised 6 Nov 2026 (this version, v3)]"},{"dimension":"support","status":"pass","explanation":"Each claim is source-stated and backed by its excerpt. The note that the abstract does not explain implementation or evaluation is an accurate limitation, not an invented claim. The question raises a genuine unresolved issue that follows from the recommendations. No unsupported benefits or costs are implied.","excerpt":"To build truly autonomous AI scientists, we recommend scientific simulations as verifiers for training"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct arXiv abstract page for this paper. That is the most direct way for readers to reach the source.","excerpt":null}],"createdAt":"2026-11-09T10:16:08.852Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}