{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O6CKSWJT4C6J4QDQEDR4XL52Q3","short_pith_number":"pith:O6CKSWJT","schema_version":"1.0","canonical_sha256":"7784a95933e0bc9e407020e3cbafba86f34aa17d373c99dec544f4024cbc866d","source":{"kind":"arxiv","id":"2406.11451","version":4},"attestation_state":"computed","paper":{"title":"CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Jiawei Chen, Ke Li, Lihua Zhang, Mingcheng Li, Shunli Wang, Tong Wu, Yue Jiang","submitted_at":"2024-06-17T12:03:32Z","abstract_excerpt":"Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention. Despite recent progress, generating accurate reports remains arduous due to the requirement for precise clinical comprehension and disease diagnosis inference. Furthermore, owing to the limited accessibility of medical data and the imbalanced distribution of diseases, the underrepresentation of rare diseases in training data makes large-scale medical visual language models (LVLMs) prone to hallucination"},"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":"2406.11451","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T12:03:32Z","cross_cats_sorted":[],"title_canon_sha256":"ca63c9e119c0c205d3a1c8a4c430add9b5b589594c940f0b37e24b5d5551008b","abstract_canon_sha256":"b2315a7e22c437e022240802110dfb5a8f9f8b2fef1e550512b4326736fb5ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:21.134757Z","signature_b64":"qQO0Ykh+4JqIQq1Hup0KvWeS85siuOHx1aBAthAXwUzlJ8Ge0oQe+okEIlu/B4uClDTUsplNL1ij8airvX4hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7784a95933e0bc9e407020e3cbafba86f34aa17d373c99dec544f4024cbc866d","last_reissued_at":"2026-07-05T10:21:21.134222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:21.134222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Jiawei Chen, Ke Li, Lihua Zhang, Mingcheng Li, Shunli Wang, Tong Wu, Yue Jiang","submitted_at":"2024-06-17T12:03:32Z","abstract_excerpt":"Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention. Despite recent progress, generating accurate reports remains arduous due to the requirement for precise clinical comprehension and disease diagnosis inference. Furthermore, owing to the limited accessibility of medical data and the imbalanced distribution of diseases, the underrepresentation of rare diseases in training data makes large-scale medical visual language models (LVLMs) prone to hallucination"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11451","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/2406.11451/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":"2406.11451","created_at":"2026-07-05T10:21:21.134276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11451v4","created_at":"2026-07-05T10:21:21.134276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11451","created_at":"2026-07-05T10:21:21.134276+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6CKSWJT4C6J","created_at":"2026-07-05T10:21:21.134276+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6CKSWJT4C6J4QDQ","created_at":"2026-07-05T10:21:21.134276+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6CKSWJT","created_at":"2026-07-05T10:21:21.134276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10955","citing_title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","ref_index":216,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3","json":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3.json","graph_json":"https://pith.science/api/pith-number/O6CKSWJT4C6J4QDQEDR4XL52Q3/graph.json","events_json":"https://pith.science/api/pith-number/O6CKSWJT4C6J4QDQEDR4XL52Q3/events.json","paper":"https://pith.science/paper/O6CKSWJT"},"agent_actions":{"view_html":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3","download_json":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3.json","view_paper":"https://pith.science/paper/O6CKSWJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11451&json=true","fetch_graph":"https://pith.science/api/pith-number/O6CKSWJT4C6J4QDQEDR4XL52Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/O6CKSWJT4C6J4QDQEDR4XL52Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3/action/storage_attestation","attest_author":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3/action/author_attestation","sign_citation":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3/action/citation_signature","submit_replication":"https://pith.science/pith/O6CKSWJT4C6J4QDQEDR4XL52Q3/action/replication_record"}},"created_at":"2026-07-05T10:21:21.134276+00:00","updated_at":"2026-07-05T10:21:21.134276+00:00"}