{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BVQYWRB7TQFAWBFVOMH55OBM3K","short_pith_number":"pith:BVQYWRB7","schema_version":"1.0","canonical_sha256":"0d618b443f9c0a0b04b5730fdeb82cda80502917b5a3ab4361b04545839585be","source":{"kind":"arxiv","id":"2605.21807","version":1},"attestation_state":"computed","paper":{"title":"When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Srisuwananukorn, Ashish Manne, Brady Buchanan, Doeun Lee, Frank Wen, James Lim, Kathryn Tobin, Lynda Villagomez, Muge Zhang, Oluwatoba Moninuola, Ping Zhang, Sachin Kumar, Stephen Koesters, Yi Yu","submitted_at":"2026-05-20T23:04:48Z","abstract_excerpt":"Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by guidelines. Most medical large language models (LLMs), however, are trained to encode common, guideline-focused medical knowledge in their parameters. Current evaluations test models primarily on recalling and reasoning with this memorized content, often in multiple-choice settings. Given the fundamental importance of evidence-based reasoning in medicine, it is n"},"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":"2605.21807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T23:04:48Z","cross_cats_sorted":[],"title_canon_sha256":"da551d47f09305c7c09151af5e1c76c4527c9d6bdecfe4c6a0b8e6a64a8b053a","abstract_canon_sha256":"86881e6813b830be968f4e74eef32b0b27bd6a8bcc40c424ec7b9bcf43b1153d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:33.323032Z","signature_b64":"HabZeIgi+XB4TUo3S5GQO1Kd/8q/QPyapQKQwXRNFcawisEfzeAdHLD+n3MS4Nh/a5CSDpfkCAPa6nnKa89RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d618b443f9c0a0b04b5730fdeb82cda80502917b5a3ab4361b04545839585be","last_reissued_at":"2026-05-22T01:03:33.322526Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:33.322526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Srisuwananukorn, Ashish Manne, Brady Buchanan, Doeun Lee, Frank Wen, James Lim, Kathryn Tobin, Lynda Villagomez, Muge Zhang, Oluwatoba Moninuola, Ping Zhang, Sachin Kumar, Stephen Koesters, Yi Yu","submitted_at":"2026-05-20T23:04:48Z","abstract_excerpt":"Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by guidelines. Most medical large language models (LLMs), however, are trained to encode common, guideline-focused medical knowledge in their parameters. Current evaluations test models primarily on recalling and reasoning with this memorized content, often in multiple-choice settings. Given the fundamental importance of evidence-based reasoning in medicine, it is n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21807","kind":"arxiv","version":1},"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/2605.21807/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":"2605.21807","created_at":"2026-05-22T01:03:33.322598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21807v1","created_at":"2026-05-22T01:03:33.322598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21807","created_at":"2026-05-22T01:03:33.322598+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVQYWRB7TQFA","created_at":"2026-05-22T01:03:33.322598+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVQYWRB7TQFAWBFV","created_at":"2026-05-22T01:03:33.322598+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVQYWRB7","created_at":"2026-05-22T01:03:33.322598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K","json":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K.json","graph_json":"https://pith.science/api/pith-number/BVQYWRB7TQFAWBFVOMH55OBM3K/graph.json","events_json":"https://pith.science/api/pith-number/BVQYWRB7TQFAWBFVOMH55OBM3K/events.json","paper":"https://pith.science/paper/BVQYWRB7"},"agent_actions":{"view_html":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K","download_json":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K.json","view_paper":"https://pith.science/paper/BVQYWRB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21807&json=true","fetch_graph":"https://pith.science/api/pith-number/BVQYWRB7TQFAWBFVOMH55OBM3K/graph.json","fetch_events":"https://pith.science/api/pith-number/BVQYWRB7TQFAWBFVOMH55OBM3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K/action/storage_attestation","attest_author":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K/action/author_attestation","sign_citation":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K/action/citation_signature","submit_replication":"https://pith.science/pith/BVQYWRB7TQFAWBFVOMH55OBM3K/action/replication_record"}},"created_at":"2026-05-22T01:03:33.322598+00:00","updated_at":"2026-05-22T01:03:33.322598+00:00"}