{"id":"9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8","title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","argument":"Bing Hu and Rishabh Sharma present Taurus, a system for labeling aortas in CT scans, and compare it with coding agents that write their own segmentation code. Taurus uses an automated labeling pass followed by model review: when checks detect likely large errors, the model chooses among corrections shown on the scan. The authors say an early version gained little from model review, while a revised version incorporated useful parts of the free-form agents’ work into automation. On their evaluation, the final Taurus version matched the free-form Opus agent on the primary metric at less than half the per-case cost, and matched the surface smoothness of the human references. The authors’ central argument is that the harness and automated process, rather than the language model alone, accounted for most of Taurus’s competitiveness. They propose this kind of automation as a way to shift expert time from drawing labels to checking them. The result is evidence about annotation on the datasets and cases they tested; it does not by itself establish how Taurus would perform in other settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported evaluation uses six public datasets and 38 held-out cases; the evidence does not establish performance on a broader range of datasets or cases. The source reports no difference on the primary metric, not proof that the approaches are equivalent in all respects or settings. The source describes annotation results and a possible shift in expert work; it does not report the effects of that shift in practice.","speaker":{"name":"Hu, Bing, Sharma, Rishabh","roleAtSource":"Article author"},"source":{"title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.00247","publishedAt":"2026-10-30","dateBasis":"Date basis not provided."},"evidence":[{"text":"Hu and Sharma compare Taurus, a harness that automates labeling and asks a model to review detected errors, with free-form agents that write segmentation code.","excerpt":"We built a harness, Taurus, and compared it with free-form agents by blind label recovery","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The evaluation withheld labels from six public datasets containing 939 volumes and scored approaches against each dataset’s own classes.","excerpt":"we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors report that the final Taurus version matched the free-form Opus agent on the primary metric at less than half its per-case cost.","excerpt":"in the primary metric we found no difference from the free-form Opus agent, at under half its cost, $1.22 against $2.71 per case.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors say that most of Taurus’s competitive performance came from its harness and automation, rather than the language model itself.","excerpt":"Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors suggest automation could shift expert time from drawing labels to checking them.","excerpt":"Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.00247","checkedAt":"2026-11-08T22:34:07.058Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would Taurus retain its reported performance and cost advantage on a broader range of aortic CT datasets and cases?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","summary":"Bing Hu and Rishabh Sharma present Taurus, a system for labeling aortas in CT scans, and compare it with coding agents that write their own segmentation code. Taurus uses an automated labeling pass followed by model review: when checks detect likely large errors, the model chooses among corrections shown on the scan. The authors say an early version gained little from model review, while a revised version incorporated useful parts of the free-form agents’ work into automation. On their evaluation, the final Taurus version matched the free-form Opus agent on the primary metric at less than half the per-case cost, and matched the surface smoothness of the human references. The authors’ central argument is that the harness and automated process, rather than the language model alone, accounted for most of Taurus’s competitiveness. They propose this kind of automation as a way to shift expert time from drawing labels to checking them. The result is evidence about annotation on the datasets and cases they tested; it does not by itself establish how Taurus would perform in other settings.","question":"Would Taurus retain its reported performance and cost advantage on a broader range of aortic CT datasets and cases?","claims":[{"text":"Hu and Sharma compare Taurus, a harness that automates labeling and asks a model to review detected errors, with free-form agents that write segmentation code.","excerpt":"We built a harness, Taurus, and compared it with free-form agents by blind label recovery","support":"source-stated"},{"text":"The evaluation withheld labels from six public datasets containing 939 volumes and scored approaches against each dataset’s own classes.","excerpt":"we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes.","support":"source-stated"},{"text":"The authors report that the final Taurus version matched the free-form Opus agent on the primary metric at less than half its per-case cost.","excerpt":"in the primary metric we found no difference from the free-form Opus agent, at under half its cost, $1.22 against $2.71 per case.","support":"source-stated"},{"text":"The authors say that most of Taurus’s competitive performance came from its harness and automation, rather than the language model itself.","excerpt":"Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself.","support":"source-stated"},{"text":"The authors suggest automation could shift expert time from drawing labels to checking them.","excerpt":"Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.","support":"source-stated"}],"limitations":["The reported evaluation uses six public datasets and 38 held-out cases; the evidence does not establish performance on a broader range of datasets or cases.","The source reports no difference on the primary metric, not proof that the approaches are equivalent in all respects or settings.","The source describes annotation results and a possible shift in expert work; it does not report the effects of that shift in practice."],"mediaId":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","correctionReason":null,"id":"9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8","publicationId":"83fe04e7-bcd3-48ee-868a-402a44b85eab","version":1,"sourceUrl":"https://arxiv.org/abs/2611.00247","sourceTitle":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-30","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T09:04:07.371Z","createdAt":"2026-11-08T22:03:32.180Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","kind":"article","url":"https://arxiv.org/abs/2611.00247","sourceUrl":"https://arxiv.org/abs/2611.00247","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-08T22:02:05.960Z","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/2611.00247","checkedAt":"2026-11-08T22:34:07.058Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","confidence":0.89,"provider":"typesafe","model":"jev-1.13.0","inputHash":"b1eb2a045cda6b25b749245fe8e5a5bba0ba92a46766d66d5e6c57336e7c91d1","decidedAt":"2026-11-08T22:02:08.087Z"},"provenance":{"textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observationId":"ce026ef41c79d8e49cb5034d4785de4a8cddb49bbaf51039e05680a43308d841","retrievedAt":"2026-11-08T22:02:05.615Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"d5842699-3fa2-4120-851a-15c35913afa3"},"reviewer":{"model":"gpt-6-luna","runId":"5fb6fe2c-835a-4c4f-8d59-692f257d385f"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T22:03:32.180Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Hu, Bing","url":null,"kind":"unknown"},{"name":"Sharma, Rishabh","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Hu, Bing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Hu, Bing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.00247","locator":"head/meta[name=author|citation_author]"},"assertionId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T22:34:07.058Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","sourceUrl":"https://arxiv.org/abs/2611.00247","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z"}},{"actor":{"name":"Sharma, Rishabh","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sharma, Rishabh","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.00247","locator":"head/meta[name=author|citation_author]"},"assertionId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T22:34:07.058Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","sourceUrl":"https://arxiv.org/abs/2611.00247","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.00247","snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8/source"}},"canonicalUrl":"https://escapemeridian.com/readings/taurus-llm-in-the-loop-ct-annotation-matches-coding-agents-at-9f0816d4","formats":{"html":"/readings/taurus-llm-in-the-loop-ct-annotation-matches-coding-agents-at-9f0816d4","markdown":"/readings/taurus-llm-in-the-loop-ct-annotation-matches-coding-agents-at-9f0816d4.md","json":"/readings/taurus-llm-in-the-loop-ct-annotation-matches-coding-agents-at-9f0816d4.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-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"}],"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"},{"id":"time","name":"TIME","kind":"organization","context":"TIME is a news magazine publishing reporting on world affairs, business, technology and the workers behind digital services.","referenceUrls":["https://time.com/"],"path":"/entities/time","json":"/entities/time.json","markdown":"/entities/time.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8","revision":"83fe04e7-bcd3-48ee-868a-402a44b85eab","revisionKind":"publication-id","title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","url":"https://escapemeridian.com/readings/taurus-llm-in-the-loop-ct-annotation-matches-coding-agents-at-9f0816d4"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.00247","revision":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","revisionKind":"sha256-source-text","title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","url":"https://arxiv.org/abs/2611.00247"},"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":"9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8","title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","argument":"Bing Hu and Rishabh Sharma present Taurus, a system for labeling aortas in CT scans, and compare it with coding agents that write their own segmentation code. Taurus uses an automated labeling pass followed by model review: when checks detect likely large errors, the model chooses among corrections shown on the scan. The authors say an early version gained little from model review, while a revised version incorporated useful parts of the free-form agents’ work into automation. On their evaluation, the final Taurus version matched the free-form Opus agent on the primary metric at less than half the per-case cost, and matched the surface smoothness of the human references. The authors’ central argument is that the harness and automated process, rather than the language model alone, accounted for most of Taurus’s competitiveness. They propose this kind of automation as a way to shift expert time from drawing labels to checking them. The result is evidence about annotation on the datasets and cases they tested; it does not by itself establish how Taurus would perform in other settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported evaluation uses six public datasets and 38 held-out cases; the evidence does not establish performance on a broader range of datasets or cases. The source reports no difference on the primary metric, not proof that the approaches are equivalent in all respects or settings. The source describes annotation results and a possible shift in expert work; it does not report the effects of that shift in practice.","speaker":{"name":"Hu, Bing, Sharma, Rishabh","roleAtSource":"Article author"},"source":{"title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.00247","publishedAt":"2026-10-30","dateBasis":"Date basis not provided."},"evidence":[{"text":"Hu and Sharma compare Taurus, a harness that automates labeling and asks a model to review detected errors, with free-form agents that write segmentation code.","excerpt":"We built a harness, Taurus, and compared it with free-form agents by blind label recovery","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The evaluation withheld labels from six public datasets containing 939 volumes and scored approaches against each dataset’s own classes.","excerpt":"we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors report that the final Taurus version matched the free-form Opus agent on the primary metric at less than half its per-case cost.","excerpt":"in the primary metric we found no difference from the free-form Opus agent, at under half its cost, $1.22 against $2.71 per case.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors say that most of Taurus’s competitive performance came from its harness and automation, rather than the language model itself.","excerpt":"Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"},{"text":"The authors suggest automation could shift expert time from drawing labels to checking them.","excerpt":"Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.","url":"https://arxiv.org/abs/2611.00247","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.00247","checkedAt":"2026-11-08T22:34:07.058Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would Taurus retain its reported performance and cost advantage on a broader range of aortic CT datasets and cases?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","summary":"Bing Hu and Rishabh Sharma present Taurus, a system for labeling aortas in CT scans, and compare it with coding agents that write their own segmentation code. Taurus uses an automated labeling pass followed by model review: when checks detect likely large errors, the model chooses among corrections shown on the scan. The authors say an early version gained little from model review, while a revised version incorporated useful parts of the free-form agents’ work into automation. On their evaluation, the final Taurus version matched the free-form Opus agent on the primary metric at less than half the per-case cost, and matched the surface smoothness of the human references. The authors’ central argument is that the harness and automated process, rather than the language model alone, accounted for most of Taurus’s competitiveness. They propose this kind of automation as a way to shift expert time from drawing labels to checking them. The result is evidence about annotation on the datasets and cases they tested; it does not by itself establish how Taurus would perform in other settings.","question":"Would Taurus retain its reported performance and cost advantage on a broader range of aortic CT datasets and cases?","claims":[{"text":"Hu and Sharma compare Taurus, a harness that automates labeling and asks a model to review detected errors, with free-form agents that write segmentation code.","excerpt":"We built a harness, Taurus, and compared it with free-form agents by blind label recovery","support":"source-stated"},{"text":"The evaluation withheld labels from six public datasets containing 939 volumes and scored approaches against each dataset’s own classes.","excerpt":"we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes.","support":"source-stated"},{"text":"The authors report that the final Taurus version matched the free-form Opus agent on the primary metric at less than half its per-case cost.","excerpt":"in the primary metric we found no difference from the free-form Opus agent, at under half its cost, $1.22 against $2.71 per case.","support":"source-stated"},{"text":"The authors say that most of Taurus’s competitive performance came from its harness and automation, rather than the language model itself.","excerpt":"Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself.","support":"source-stated"},{"text":"The authors suggest automation could shift expert time from drawing labels to checking them.","excerpt":"Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.","support":"source-stated"}],"limitations":["The reported evaluation uses six public datasets and 38 held-out cases; the evidence does not establish performance on a broader range of datasets or cases.","The source reports no difference on the primary metric, not proof that the approaches are equivalent in all respects or settings.","The source describes annotation results and a possible shift in expert work; it does not report the effects of that shift in practice."],"mediaId":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","correctionReason":null,"id":"9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8","publicationId":"83fe04e7-bcd3-48ee-868a-402a44b85eab","version":1,"sourceUrl":"https://arxiv.org/abs/2611.00247","sourceTitle":"Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-30","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T09:04:07.371Z","createdAt":"2026-11-08T22:03:32.180Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","kind":"article","url":"https://arxiv.org/abs/2611.00247","sourceUrl":"https://arxiv.org/abs/2611.00247","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-08T22:02:05.960Z","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/2611.00247","checkedAt":"2026-11-08T22:34:07.058Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"93d8a7d8e1c8aa0eaed0ea126b36798c14c45932ca3bcc69967e3ff48edc75f3","confidence":0.89,"provider":"typesafe","model":"jev-1.13.0","inputHash":"b1eb2a045cda6b25b749245fe8e5a5bba0ba92a46766d66d5e6c57336e7c91d1","decidedAt":"2026-11-08T22:02:08.087Z"},"provenance":{"textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observationId":"ce026ef41c79d8e49cb5034d4785de4a8cddb49bbaf51039e05680a43308d841","retrievedAt":"2026-11-08T22:02:05.615Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"d5842699-3fa2-4120-851a-15c35913afa3"},"reviewer":{"model":"gpt-6-luna","runId":"5fb6fe2c-835a-4c4f-8d59-692f257d385f"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-08T22:03:32.180Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Hu, Bing","url":null,"kind":"unknown"},{"name":"Sharma, Rishabh","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Hu, Bing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Hu, Bing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.00247","locator":"head/meta[name=author|citation_author]"},"assertionId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T22:34:07.058Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","sourceUrl":"https://arxiv.org/abs/2611.00247","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z"}},{"actor":{"name":"Sharma, Rishabh","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sharma, Rishabh","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.00247","locator":"head/meta[name=author|citation_author]"},"assertionId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-08T22:34:07.058Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","sourceUrl":"https://arxiv.org/abs/2611.00247","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.00247","snapshotId":"4fbf5b946839869db6e63488e23e1fb42e9ff5c4313b97a4baad900d058636dd","contentSha256":"39e1238c498c05b3b403ee4fc93dcc9ddf9b222eba09740c4ac2ecac112596f4","textHash":"c0684adae9bd97fe88adc10c333bf9c84e9b715d375eda7f84175fa6e91ef306","observedAt":"2026-11-08T22:34:07.058Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/9f0816d43f617fa2b1137fb3ebc75e4bc157b2809b49ea81e7233bc36db078c8/source"}}}],"audits":[{"publicationId":"83fe04e7-bcd3-48ee-868a-402a44b85eab","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the work to Bing Hu and Rishabh Sharma and keeps the results and the central argument framed as the authors' own reported findings and claims.","excerpt":"Authors:Bing Hu, Rishabh Sharma"},{"dimension":"summary","status":"uncertain","explanation":"The summary is faithful overall, but it refers to 'the free-form Opus agent' without saying it was a free-form agent running Claude Opus 5.5. A general reader cannot identify the main comparison point. 'CT' and 'segmentation code' are also central terms left unexplained; tooltips or brief glosses are needed. The summary omits the dollar figures ($1.22 vs $2.71 per case) and the motivating problem: labels are slow to draw and public datasets use inconsistent conventions. Smallest repair: name Claude Opus 5.5, give the per-case costs, and add one clause on why aortic labeling is hard.","excerpt":"A free-form agent running Claude Opus 5.5 scored higher on most datasets."},{"dimension":"date","status":"pass","explanation":"The originalPublished date of 2026-10-30 matches the v1 submission date. The 5 Nov revision and the 6 Nov feed date are correctly not used.","excerpt":"[Submitted on 30 Oct 2026 (v1), last revised 5 Nov 2026 (this version, v2)]"},{"dimension":"support","status":"pass","explanation":"Every claim is source-stated and carries an exact excerpt. The early-version and revision narrative matches the abstract. The limitations appropriately note that 'no difference' does not mean equivalence and that the shift in expert work is a proposal. Minor caution: the abstract ties the 38 held-out cases to the gain from moving agent strengths into automation. It is not explicit that the final comparison used only those cases, so the limitation should not imply that it did. The question follows from the evidence.","excerpt":"Moving what the free-form agents did well into the automated pass then carried most of the gain on 38 held-out cases."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct arXiv abstract page for this paper, which is the most direct access to the source.","excerpt":null}],"createdAt":"2026-11-08T22:03:32.180Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}