{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJLGOEKPRJFP4H7CDVLJATQLXF","short_pith_number":"pith:GJLGOEKP","schema_version":"1.0","canonical_sha256":"325667114f8a4afe1fe21d56904e0bb969042ec0e6d4bc5d38a0a2e3610cb3e5","source":{"kind":"arxiv","id":"2509.05741","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fernando Gabriela Garc\\'ia, Qiyang Shi, Zilin Feng","submitted_at":"2025-09-06T15:07:59Z","abstract_excerpt":"This research introduces VeriFact-CoT (Verified Factual Chain-of-Thought), a novel method designed to address the pervasive issues of hallucination and the absence of credible citation sources in Large Language Models (LLMs) when generating complex, fact-sensitive content. By incorporating a multi-stage mechanism of 'fact verification-reflection-citation integration,' VeriFact-CoT empowers LLMs to critically self-examine and revise their intermediate reasoning steps and final answers. This process significantly enhances the objective accuracy, trustworthiness, and traceability of the generated"},"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":"2509.05741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-06T15:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"c3a02ad9c51c7ba59533a4dd3743d33f7f076af885c7dd49a5396fbf96301c6c","abstract_canon_sha256":"faa0c56d8e94535811c6cd99967edf4e954c63aa0717bda0ad6470e0639b030b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:23.335134Z","signature_b64":"LVAtredPi5vvmszQyEeWpajSwJIwyJslKpcmTuXnMYK/ufiXYLTno51n2c8cI29uYC/6QBilNK1+T8h3FOs2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325667114f8a4afe1fe21d56904e0bb969042ec0e6d4bc5d38a0a2e3610cb3e5","last_reissued_at":"2026-07-05T12:06:23.334645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:23.334645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fernando Gabriela Garc\\'ia, Qiyang Shi, Zilin Feng","submitted_at":"2025-09-06T15:07:59Z","abstract_excerpt":"This research introduces VeriFact-CoT (Verified Factual Chain-of-Thought), a novel method designed to address the pervasive issues of hallucination and the absence of credible citation sources in Large Language Models (LLMs) when generating complex, fact-sensitive content. By incorporating a multi-stage mechanism of 'fact verification-reflection-citation integration,' VeriFact-CoT empowers LLMs to critically self-examine and revise their intermediate reasoning steps and final answers. This process significantly enhances the objective accuracy, trustworthiness, and traceability of the generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05741","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/2509.05741/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":"2509.05741","created_at":"2026-07-05T12:06:23.334699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05741v1","created_at":"2026-07-05T12:06:23.334699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05741","created_at":"2026-07-05T12:06:23.334699+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJLGOEKPRJFP","created_at":"2026-07-05T12:06:23.334699+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJLGOEKPRJFP4H7C","created_at":"2026-07-05T12:06:23.334699+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJLGOEKP","created_at":"2026-07-05T12:06:23.334699+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/GJLGOEKPRJFP4H7CDVLJATQLXF","json":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF.json","graph_json":"https://pith.science/api/pith-number/GJLGOEKPRJFP4H7CDVLJATQLXF/graph.json","events_json":"https://pith.science/api/pith-number/GJLGOEKPRJFP4H7CDVLJATQLXF/events.json","paper":"https://pith.science/paper/GJLGOEKP"},"agent_actions":{"view_html":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF","download_json":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF.json","view_paper":"https://pith.science/paper/GJLGOEKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05741&json=true","fetch_graph":"https://pith.science/api/pith-number/GJLGOEKPRJFP4H7CDVLJATQLXF/graph.json","fetch_events":"https://pith.science/api/pith-number/GJLGOEKPRJFP4H7CDVLJATQLXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF/action/storage_attestation","attest_author":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF/action/author_attestation","sign_citation":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF/action/citation_signature","submit_replication":"https://pith.science/pith/GJLGOEKPRJFP4H7CDVLJATQLXF/action/replication_record"}},"created_at":"2026-07-05T12:06:23.334699+00:00","updated_at":"2026-07-05T12:06:23.334699+00:00"}