{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HQDQ4ZN7O3UBAQALXPSZ7X4ODB","short_pith_number":"pith:HQDQ4ZN7","schema_version":"1.0","canonical_sha256":"3c070e65bf76e810400bbbe59fdf8e185205558223165e1082be6e084b4951f0","source":{"kind":"arxiv","id":"2402.13919","version":4},"attestation_state":"computed","paper":{"title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beining Wang, Feiyun Ouyang, Hong Yu, Parth Vashisht, Prakamya Mishra, Vidhi Dhaval Mody, Zonghai Yao","submitted_at":"2024-02-21T16:33:22Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization"},"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":"2402.13919","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T16:33:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"367ae5e81ff811f3c555cdd5cb1420dbcc68ce5c7e0a0ab6b5a45b014ec40dc6","abstract_canon_sha256":"3f728164a468ffa53ebc675aee4845fff2983868f5be3f87f6757212ede86e23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:08.700520Z","signature_b64":"YZeS2+uZfm634mYI6Vm6LWmGZmvKD3a78El7edoc0M2nohnlY+PmbwUCyzINFYm5kzGeAREv1jnxh3OhNW7QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c070e65bf76e810400bbbe59fdf8e185205558223165e1082be6e084b4951f0","last_reissued_at":"2026-07-05T09:15:08.700024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:08.700024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beining Wang, Feiyun Ouyang, Hong Yu, Parth Vashisht, Prakamya Mishra, Vidhi Dhaval Mody, Zonghai Yao","submitted_at":"2024-02-21T16:33:22Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13919","kind":"arxiv","version":4},"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/2402.13919/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":"2402.13919","created_at":"2026-07-05T09:15:08.700083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13919v4","created_at":"2026-07-05T09:15:08.700083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13919","created_at":"2026-07-05T09:15:08.700083+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQDQ4ZN7O3UB","created_at":"2026-07-05T09:15:08.700083+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQDQ4ZN7O3UBAQAL","created_at":"2026-07-05T09:15:08.700083+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQDQ4ZN7","created_at":"2026-07-05T09:15:08.700083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05993","citing_title":"Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB","json":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB.json","graph_json":"https://pith.science/api/pith-number/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/graph.json","events_json":"https://pith.science/api/pith-number/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/events.json","paper":"https://pith.science/paper/HQDQ4ZN7"},"agent_actions":{"view_html":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB","download_json":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB.json","view_paper":"https://pith.science/paper/HQDQ4ZN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13919&json=true","fetch_graph":"https://pith.science/api/pith-number/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/graph.json","fetch_events":"https://pith.science/api/pith-number/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/action/storage_attestation","attest_author":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/action/author_attestation","sign_citation":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/action/citation_signature","submit_replication":"https://pith.science/pith/HQDQ4ZN7O3UBAQALXPSZ7X4ODB/action/replication_record"}},"created_at":"2026-07-05T09:15:08.700083+00:00","updated_at":"2026-07-05T09:15:08.700083+00:00"}