{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GFNULGWHOXNG4N7SKKLZKRQTN3","short_pith_number":"pith:GFNULGWH","schema_version":"1.0","canonical_sha256":"315b459ac775da6e37f252979546136ed545b1db87b10651da48c1414183d9da","source":{"kind":"arxiv","id":"2605.24902","version":1},"attestation_state":"computed","paper":{"title":"When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Faizan Faisal","submitted_at":"2026-05-24T06:58:57Z","abstract_excerpt":"Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical documentation; we investigate this question using SOAP note generation from clinical dialogue in a source-aware benchmark spanning OMI Health, ACI-Bench, and PriMock57. We evaluate GPT-5.4, DeepSeek-V4-Flash, and Gemma-4-E4B in a controlled 2x2 design that independently toggles provider-native reasoning and same-source retrieval-augmented generation (RAG). Outputs are assessed using seven automatic metrics alongside two reference-aware LLM judges. "},"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":"2605.24902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T06:58:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0ce09ff269858414f59e1c274d33cac47216e04dcd76758fafdaeea2a8c7133b","abstract_canon_sha256":"99c92429c6898478d4948c0e035da1e3e707231ec0f6028a7dbb3933d9413592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:04.588828Z","signature_b64":"OPcsXFEf5hZSuhuQO+fSpqqfKHPt4hmTNJV0CwecQa7N5/UvQYUY5i4UgdLEprgVv7+tp1moOXktZHPsoJkLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315b459ac775da6e37f252979546136ed545b1db87b10651da48c1414183d9da","last_reissued_at":"2026-05-26T01:04:04.588098Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:04.588098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Faizan Faisal","submitted_at":"2026-05-24T06:58:57Z","abstract_excerpt":"Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical documentation; we investigate this question using SOAP note generation from clinical dialogue in a source-aware benchmark spanning OMI Health, ACI-Bench, and PriMock57. We evaluate GPT-5.4, DeepSeek-V4-Flash, and Gemma-4-E4B in a controlled 2x2 design that independently toggles provider-native reasoning and same-source retrieval-augmented generation (RAG). Outputs are assessed using seven automatic metrics alongside two reference-aware LLM judges. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24902","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/2605.24902/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":"2605.24902","created_at":"2026-05-26T01:04:04.588222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24902v1","created_at":"2026-05-26T01:04:04.588222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24902","created_at":"2026-05-26T01:04:04.588222+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFNULGWHOXNG","created_at":"2026-05-26T01:04:04.588222+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFNULGWHOXNG4N7S","created_at":"2026-05-26T01:04:04.588222+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFNULGWH","created_at":"2026-05-26T01:04:04.588222+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/GFNULGWHOXNG4N7SKKLZKRQTN3","json":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3.json","graph_json":"https://pith.science/api/pith-number/GFNULGWHOXNG4N7SKKLZKRQTN3/graph.json","events_json":"https://pith.science/api/pith-number/GFNULGWHOXNG4N7SKKLZKRQTN3/events.json","paper":"https://pith.science/paper/GFNULGWH"},"agent_actions":{"view_html":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3","download_json":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3.json","view_paper":"https://pith.science/paper/GFNULGWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24902&json=true","fetch_graph":"https://pith.science/api/pith-number/GFNULGWHOXNG4N7SKKLZKRQTN3/graph.json","fetch_events":"https://pith.science/api/pith-number/GFNULGWHOXNG4N7SKKLZKRQTN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3/action/storage_attestation","attest_author":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3/action/author_attestation","sign_citation":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3/action/citation_signature","submit_replication":"https://pith.science/pith/GFNULGWHOXNG4N7SKKLZKRQTN3/action/replication_record"}},"created_at":"2026-05-26T01:04:04.588222+00:00","updated_at":"2026-05-26T01:04:04.588222+00:00"}