{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7WXP3YXUD4T6JODZEQZTT7LD7D","short_pith_number":"pith:7WXP3YXU","schema_version":"1.0","canonical_sha256":"fdaefde2f41f27e4b879243339fd63f8d4ac2ad326b3ec020de8f1ccee5afc04","source":{"kind":"arxiv","id":"2509.02594","version":3},"attestation_state":"computed","paper":{"title":"OpenAIs HealthBench in Action: Evaluating an LLM-Based Medical Assistant on Realistic Clinical Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.IR"],"primary_cat":"q-bio.QM","authors_text":"Michiel van der Heijden, Miguel Romano, Olivier Fail, Reinhard Berkels, Rogerio Corga Da Silva, Sandhanakrishnan Ravichandran, Shivesh Kumar, Valentine Emmanuel Gnanapragasam","submitted_at":"2025-08-29T09:51:41Z","abstract_excerpt":"Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios. Traditional evaluations are often limited to multiple-choice questions that fail to capture essential competencies such as contextual reasoning, contextual awareness, and uncertainty handling.\n  To address these limitations, we evaluate our agentic RAG-based clinical support assistant, DR. INFO, using HealthBench, a rubric-driven "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.02594","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-08-29T09:51:41Z","cross_cats_sorted":["cs.AI","cs.ET","cs.IR"],"title_canon_sha256":"de3b6fc0fe26ddf3fd59907023768dfee80aedec856bdf444dd3dec59935e478","abstract_canon_sha256":"132d5f688ff7de02e1c59a90585e4445cdac47b1c20269019066af210ad52062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:16.984766Z","signature_b64":"67UzTOv74wD9VHHjedClbTlYaSsVCCvhPn47RmXyVNTMdXHLepjt/gs5v4z4E2rRHgkvVzxwCabgXKvyHUd3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdaefde2f41f27e4b879243339fd63f8d4ac2ad326b3ec020de8f1ccee5afc04","last_reissued_at":"2026-07-28T02:23:16.983783Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:16.983783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenAIs HealthBench in Action: Evaluating an LLM-Based Medical Assistant on Realistic Clinical Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.IR"],"primary_cat":"q-bio.QM","authors_text":"Michiel van der Heijden, Miguel Romano, Olivier Fail, Reinhard Berkels, Rogerio Corga Da Silva, Sandhanakrishnan Ravichandran, Shivesh Kumar, Valentine Emmanuel Gnanapragasam","submitted_at":"2025-08-29T09:51:41Z","abstract_excerpt":"Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios. Traditional evaluations are often limited to multiple-choice questions that fail to capture essential competencies such as contextual reasoning, contextual awareness, and uncertainty handling.\n  To address these limitations, we evaluate our agentic RAG-based clinical support assistant, DR. INFO, using HealthBench, a rubric-driven "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02594","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.02594/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.02594","created_at":"2026-07-28T02:23:16.984251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02594v3","created_at":"2026-07-28T02:23:16.984251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02594","created_at":"2026-07-28T02:23:16.984251+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WXP3YXUD4T6","created_at":"2026-07-28T02:23:16.984251+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WXP3YXUD4T6JODZ","created_at":"2026-07-28T02:23:16.984251+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WXP3YXU","created_at":"2026-07-28T02:23:16.984251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.24699","citing_title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30529","citing_title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16346","citing_title":"DR. INFO at the Point of Care: A Prospective Pilot Study of Physician-Perceived Value of an Agentic AI Clinical Assistant","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D","json":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D.json","graph_json":"https://pith.science/api/pith-number/7WXP3YXUD4T6JODZEQZTT7LD7D/graph.json","events_json":"https://pith.science/api/pith-number/7WXP3YXUD4T6JODZEQZTT7LD7D/events.json","paper":"https://pith.science/paper/7WXP3YXU"},"agent_actions":{"view_html":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D","download_json":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D.json","view_paper":"https://pith.science/paper/7WXP3YXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02594&json=true","fetch_graph":"https://pith.science/api/pith-number/7WXP3YXUD4T6JODZEQZTT7LD7D/graph.json","fetch_events":"https://pith.science/api/pith-number/7WXP3YXUD4T6JODZEQZTT7LD7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D/action/storage_attestation","attest_author":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D/action/author_attestation","sign_citation":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D/action/citation_signature","submit_replication":"https://pith.science/pith/7WXP3YXUD4T6JODZEQZTT7LD7D/action/replication_record"}},"created_at":"2026-07-28T02:23:16.984251+00:00","updated_at":"2026-07-28T02:23:16.984251+00:00"}