{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EM5Q4ORR6WH6HFPLFDZ3BXXUKK","short_pith_number":"pith:EM5Q4ORR","schema_version":"1.0","canonical_sha256":"233b0e3a31f58fe395eb28f3b0def452bfe5c80f1e9d16b18893df3081859fe4","source":{"kind":"arxiv","id":"2311.08303","version":2},"attestation_state":"computed","paper":{"title":"Extrinsically-Focused Evaluation of Omissions in Medical Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anitha Kannan, Daniel Rosenthal, Dhruv Naik, Elliot Schumacher, Geoffrey Tso, Luladay Price, Varun Nair","submitted_at":"2023-11-14T16:46:15Z","abstract_excerpt":"Large language models (LLMs) have shown promise in safety-critical applications such as healthcare, yet the ability to quantify performance has lagged. An example of this challenge is in evaluating a summary of the patient's medical record. A resulting summary can enable the provider to get a high-level overview of the patient's health status quickly. Yet, a summary that omits important facts about the patient's record can produce a misleading picture. This can lead to negative consequences on medical decision-making. We propose MED-OMIT as a metric to explore this challenge. We focus on using"},"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":"2311.08303","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T16:46:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1857a296fd0903b5c548caa17d3ce866e8d27e293d485ff2ed5381c5e515e130","abstract_canon_sha256":"70d0219491525629b38299d02a46ba5249ce9228e218448f8519c165df452181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:10.469871Z","signature_b64":"j03XoNIT49DZhTmDq68nzfKi3mBdXgJ4Q1QPwzve02TiTwkVixYK8qD/JcW4HV14uo2Tzo554ea77gK7HacSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"233b0e3a31f58fe395eb28f3b0def452bfe5c80f1e9d16b18893df3081859fe4","last_reissued_at":"2026-07-05T09:34:10.469366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:10.469366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extrinsically-Focused Evaluation of Omissions in Medical Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anitha Kannan, Daniel Rosenthal, Dhruv Naik, Elliot Schumacher, Geoffrey Tso, Luladay Price, Varun Nair","submitted_at":"2023-11-14T16:46:15Z","abstract_excerpt":"Large language models (LLMs) have shown promise in safety-critical applications such as healthcare, yet the ability to quantify performance has lagged. An example of this challenge is in evaluating a summary of the patient's medical record. A resulting summary can enable the provider to get a high-level overview of the patient's health status quickly. Yet, a summary that omits important facts about the patient's record can produce a misleading picture. This can lead to negative consequences on medical decision-making. We propose MED-OMIT as a metric to explore this challenge. We focus on using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08303","kind":"arxiv","version":2},"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/2311.08303/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":"2311.08303","created_at":"2026-07-05T09:34:10.469428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08303v2","created_at":"2026-07-05T09:34:10.469428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08303","created_at":"2026-07-05T09:34:10.469428+00:00"},{"alias_kind":"pith_short_12","alias_value":"EM5Q4ORR6WH6","created_at":"2026-07-05T09:34:10.469428+00:00"},{"alias_kind":"pith_short_16","alias_value":"EM5Q4ORR6WH6HFPL","created_at":"2026-07-05T09:34:10.469428+00:00"},{"alias_kind":"pith_short_8","alias_value":"EM5Q4ORR","created_at":"2026-07-05T09:34:10.469428+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/EM5Q4ORR6WH6HFPLFDZ3BXXUKK","json":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK.json","graph_json":"https://pith.science/api/pith-number/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/graph.json","events_json":"https://pith.science/api/pith-number/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/events.json","paper":"https://pith.science/paper/EM5Q4ORR"},"agent_actions":{"view_html":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK","download_json":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK.json","view_paper":"https://pith.science/paper/EM5Q4ORR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08303&json=true","fetch_graph":"https://pith.science/api/pith-number/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/graph.json","fetch_events":"https://pith.science/api/pith-number/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/action/storage_attestation","attest_author":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/action/author_attestation","sign_citation":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/action/citation_signature","submit_replication":"https://pith.science/pith/EM5Q4ORR6WH6HFPLFDZ3BXXUKK/action/replication_record"}},"created_at":"2026-07-05T09:34:10.469428+00:00","updated_at":"2026-07-05T09:34:10.469428+00:00"}