{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2HRXIDWMNJKBWSKL3CDE5AYHVK","short_pith_number":"pith:2HRXIDWM","schema_version":"1.0","canonical_sha256":"d1e3740ecc6a541b494bd8864e8307aa9b058e1d6a402c40a45c02c837f03daa","source":{"kind":"arxiv","id":"2509.12440","version":3},"attestation_state":"computed","paper":{"title":"MedFact: Benchmarking the Fact-Checking Capabilities of Large Language Models on Chinese Medical Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxue Hu, Jiayi He, Lixian Lai, Qianyun Du, Xiangying Zhou, Xiaodong Tao, Yangmin Huang, Zhiyang He","submitted_at":"2025-09-15T20:46:21Z","abstract_excerpt":"Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory compliance. We introduce MedFact, a challenging Chinese medical fact-checking benchmark with 2,116 expert-annotated instances from diverse real-world texts, spanning 13 specialties, 8 error types, 4 writing styles, and 5 difficulty levels. Construction uses a hybrid AI-human framework where iterative expert feedback refines AI-driven, multi-criteria filtering to ensure high quality and difficulty. We evaluate 20 leading LLMs on veracity classification and e"},"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":"2509.12440","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-15T20:46:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eacb9bbd338e6a7faaf774cec6e67bd606682848414e7b41557dc593494affbb","abstract_canon_sha256":"817a09cc534bb9d2dd3c7fde88788bab8d52e3cc65f8459a6ba0e62e7952117e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:26.508210Z","signature_b64":"vDtwgdEwtawkkJ+1+Wui0g292eRXWCgCpovBRfokHGkXumdH+T0UzOTi9zWAcN4NVOuQeuHqTAUuE5v2K+J3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e3740ecc6a541b494bd8864e8307aa9b058e1d6a402c40a45c02c837f03daa","last_reissued_at":"2026-06-01T02:03:26.507214Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:26.507214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedFact: Benchmarking the Fact-Checking Capabilities of Large Language Models on Chinese Medical Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxue Hu, Jiayi He, Lixian Lai, Qianyun Du, Xiangying Zhou, Xiaodong Tao, Yangmin Huang, Zhiyang He","submitted_at":"2025-09-15T20:46:21Z","abstract_excerpt":"Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory compliance. We introduce MedFact, a challenging Chinese medical fact-checking benchmark with 2,116 expert-annotated instances from diverse real-world texts, spanning 13 specialties, 8 error types, 4 writing styles, and 5 difficulty levels. Construction uses a hybrid AI-human framework where iterative expert feedback refines AI-driven, multi-criteria filtering to ensure high quality and difficulty. We evaluate 20 leading LLMs on veracity classification and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.12440","kind":"arxiv","version":3},"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/2509.12440/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":"2509.12440","created_at":"2026-06-01T02:03:26.507342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.12440v3","created_at":"2026-06-01T02:03:26.507342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.12440","created_at":"2026-06-01T02:03:26.507342+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HRXIDWMNJKB","created_at":"2026-06-01T02:03:26.507342+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HRXIDWMNJKBWSKL","created_at":"2026-06-01T02:03:26.507342+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HRXIDWM","created_at":"2026-06-01T02:03:26.507342+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/2HRXIDWMNJKBWSKL3CDE5AYHVK","json":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK.json","graph_json":"https://pith.science/api/pith-number/2HRXIDWMNJKBWSKL3CDE5AYHVK/graph.json","events_json":"https://pith.science/api/pith-number/2HRXIDWMNJKBWSKL3CDE5AYHVK/events.json","paper":"https://pith.science/paper/2HRXIDWM"},"agent_actions":{"view_html":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK","download_json":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK.json","view_paper":"https://pith.science/paper/2HRXIDWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.12440&json=true","fetch_graph":"https://pith.science/api/pith-number/2HRXIDWMNJKBWSKL3CDE5AYHVK/graph.json","fetch_events":"https://pith.science/api/pith-number/2HRXIDWMNJKBWSKL3CDE5AYHVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK/action/storage_attestation","attest_author":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK/action/author_attestation","sign_citation":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK/action/citation_signature","submit_replication":"https://pith.science/pith/2HRXIDWMNJKBWSKL3CDE5AYHVK/action/replication_record"}},"created_at":"2026-06-01T02:03:26.507342+00:00","updated_at":"2026-06-01T02:03:26.507342+00:00"}