{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PX5XEYRSVV3WMNN7T7265TRESU","short_pith_number":"pith:PX5XEYRS","schema_version":"1.0","canonical_sha256":"7dfb726232ad776635bf9ff5eece24950879eb0ac9a855c8149d7cd583d68ebb","source":{"kind":"arxiv","id":"2303.03948","version":1},"attestation_state":"computed","paper":{"title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Griffin Adams, Jason Zucker, No\\'emie Elhadad","submitted_at":"2023-03-07T14:57:06Z","abstract_excerpt":"Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. The faithfulness of summaries is critical to their safe usage in clinical settings. To better understand the limitations of abstractive systems, as well as the suitability of existing evaluation metrics, we benchmark faithfulness metrics against fine-grained human annotations for model-generated summaries of a patient's Brief Hospital Course. We create a corpus of patient hospital admissions and summaries for a cohort of HIV patients, each with comp"},"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":"2303.03948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:57:06Z","cross_cats_sorted":[],"title_canon_sha256":"88370970cc6af79defee97976ea7853838912b5d015a666d05bf641cb73e421a","abstract_canon_sha256":"a5192d62e89c2ab2f55b8529663d2a3b9f77cf96de2aa5308e64bcd8006a1aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:01.368748Z","signature_b64":"GTqJ+6JPnvJa0tTTHddbLtD+hjFckkApbMn5wvfMqMQhsaj+SegBxvVjKXK921u5aT69SVNY4KHw6CLd8a77Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dfb726232ad776635bf9ff5eece24950879eb0ac9a855c8149d7cd583d68ebb","last_reissued_at":"2026-07-05T05:49:01.368249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:01.368249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Griffin Adams, Jason Zucker, No\\'emie Elhadad","submitted_at":"2023-03-07T14:57:06Z","abstract_excerpt":"Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. The faithfulness of summaries is critical to their safe usage in clinical settings. To better understand the limitations of abstractive systems, as well as the suitability of existing evaluation metrics, we benchmark faithfulness metrics against fine-grained human annotations for model-generated summaries of a patient's Brief Hospital Course. We create a corpus of patient hospital admissions and summaries for a cohort of HIV patients, each with comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03948","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/2303.03948/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":"2303.03948","created_at":"2026-07-05T05:49:01.368322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03948v1","created_at":"2026-07-05T05:49:01.368322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03948","created_at":"2026-07-05T05:49:01.368322+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX5XEYRSVV3W","created_at":"2026-07-05T05:49:01.368322+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX5XEYRSVV3WMNN7","created_at":"2026-07-05T05:49:01.368322+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX5XEYRS","created_at":"2026-07-05T05:49:01.368322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08977","citing_title":"Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU","json":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU.json","graph_json":"https://pith.science/api/pith-number/PX5XEYRSVV3WMNN7T7265TRESU/graph.json","events_json":"https://pith.science/api/pith-number/PX5XEYRSVV3WMNN7T7265TRESU/events.json","paper":"https://pith.science/paper/PX5XEYRS"},"agent_actions":{"view_html":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU","download_json":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU.json","view_paper":"https://pith.science/paper/PX5XEYRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03948&json=true","fetch_graph":"https://pith.science/api/pith-number/PX5XEYRSVV3WMNN7T7265TRESU/graph.json","fetch_events":"https://pith.science/api/pith-number/PX5XEYRSVV3WMNN7T7265TRESU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU/action/storage_attestation","attest_author":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU/action/author_attestation","sign_citation":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU/action/citation_signature","submit_replication":"https://pith.science/pith/PX5XEYRSVV3WMNN7T7265TRESU/action/replication_record"}},"created_at":"2026-07-05T05:49:01.368322+00:00","updated_at":"2026-07-05T05:49:01.368322+00:00"}