{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FO75H7MZHWLU5C42ONWX6MWVAG","short_pith_number":"pith:FO75H7MZ","schema_version":"1.0","canonical_sha256":"2bbfd3fd993d974e8b9a736d7f32d50191574c8ea82ef4ea3c118b38e45c98cd","source":{"kind":"arxiv","id":"2210.06340","version":2},"attestation_state":"computed","paper":{"title":"Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nathan Andrew Chi, Pranav Rajpurkar, Vignav Ramesh","submitted_at":"2022-09-27T00:44:41Z","abstract_excerpt":"Current deep learning models trained to generate radiology reports from chest radiographs are capable of producing clinically accurate, clear, and actionable text that can advance patient care. However, such systems all succumb to the same problem: making hallucinated references to non-existent prior reports. Such hallucinations occur because these models are trained on datasets of real-world patient reports that inherently refer to priors. To this end, we propose two methods to remove references to priors in radiology reports: (1) a GPT-3-based few-shot approach to rewrite medical reports wit"},"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":"2210.06340","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T00:44:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d70256a1d125edcf047500b96db5213ac5396ae1404c62e15175157549836fa7","abstract_canon_sha256":"7f81dc2a952d8aced66d3f1bda2b0235a67dd9d6a29257b9f728566d5b43830c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:16.175292Z","signature_b64":"uAsMcBP1TqsStNlnxltvTQaZMmy92eQmYYJcaohg3+tz6w7mmzVvK1/x6y2/NSNaPtUlqUkKNV8MFtHLIEq5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bbfd3fd993d974e8b9a736d7f32d50191574c8ea82ef4ea3c118b38e45c98cd","last_reissued_at":"2026-07-05T05:06:16.174808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:16.174808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nathan Andrew Chi, Pranav Rajpurkar, Vignav Ramesh","submitted_at":"2022-09-27T00:44:41Z","abstract_excerpt":"Current deep learning models trained to generate radiology reports from chest radiographs are capable of producing clinically accurate, clear, and actionable text that can advance patient care. However, such systems all succumb to the same problem: making hallucinated references to non-existent prior reports. Such hallucinations occur because these models are trained on datasets of real-world patient reports that inherently refer to priors. To this end, we propose two methods to remove references to priors in radiology reports: (1) a GPT-3-based few-shot approach to rewrite medical reports wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06340","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/2210.06340/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":"2210.06340","created_at":"2026-07-05T05:06:16.174861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06340v2","created_at":"2026-07-05T05:06:16.174861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06340","created_at":"2026-07-05T05:06:16.174861+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO75H7MZHWLU","created_at":"2026-07-05T05:06:16.174861+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO75H7MZHWLU5C42","created_at":"2026-07-05T05:06:16.174861+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO75H7MZ","created_at":"2026-07-05T05:06:16.174861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14318","citing_title":"RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG","json":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG.json","graph_json":"https://pith.science/api/pith-number/FO75H7MZHWLU5C42ONWX6MWVAG/graph.json","events_json":"https://pith.science/api/pith-number/FO75H7MZHWLU5C42ONWX6MWVAG/events.json","paper":"https://pith.science/paper/FO75H7MZ"},"agent_actions":{"view_html":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG","download_json":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG.json","view_paper":"https://pith.science/paper/FO75H7MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06340&json=true","fetch_graph":"https://pith.science/api/pith-number/FO75H7MZHWLU5C42ONWX6MWVAG/graph.json","fetch_events":"https://pith.science/api/pith-number/FO75H7MZHWLU5C42ONWX6MWVAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG/action/storage_attestation","attest_author":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG/action/author_attestation","sign_citation":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG/action/citation_signature","submit_replication":"https://pith.science/pith/FO75H7MZHWLU5C42ONWX6MWVAG/action/replication_record"}},"created_at":"2026-07-05T05:06:16.174861+00:00","updated_at":"2026-07-05T05:06:16.174861+00:00"}