{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RUNH5PXJRNLNOA5R6JQ3H6OYWG","short_pith_number":"pith:RUNH5PXJ","schema_version":"1.0","canonical_sha256":"8d1a7ebee98b56d703b1f261b3f9d8b18af6e57204ef192b24b3484ea565e165","source":{"kind":"arxiv","id":"2502.17924","version":2},"attestation_state":"computed","paper":{"title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongzhan Lin, Jing Ma, See-kiong Ng, Tat-Seng Chua, Wenxuan Zhang, Yang Deng, Yuxuan Gu","submitted_at":"2025-02-25T07:44:22Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs "},"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":"2502.17924","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T07:44:22Z","cross_cats_sorted":[],"title_canon_sha256":"ba9caa13c09373a4282ec633fd23b17790881068355a5daf50ec797848179aff","abstract_canon_sha256":"8297249c1892ba770cf615dad5dae7c815448780302b513354a47064342bd685"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:14.528659Z","signature_b64":"zOWmtrM1DQd2gkxpZ6zNp6+RJuyhYpyM41qz0sY+k5jfXvdWmMFCWahmmU0YMWC+htnpowFCOILd7E9y1VGuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1a7ebee98b56d703b1f261b3f9d8b18af6e57204ef192b24b3484ea565e165","last_reissued_at":"2026-07-05T10:22:14.528026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:14.528026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongzhan Lin, Jing Ma, See-kiong Ng, Tat-Seng Chua, Wenxuan Zhang, Yang Deng, Yuxuan Gu","submitted_at":"2025-02-25T07:44:22Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17924","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/2502.17924/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":"2502.17924","created_at":"2026-07-05T10:22:14.528096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17924v2","created_at":"2026-07-05T10:22:14.528096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17924","created_at":"2026-07-05T10:22:14.528096+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUNH5PXJRNLN","created_at":"2026-07-05T10:22:14.528096+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUNH5PXJRNLNOA5R","created_at":"2026-07-05T10:22:14.528096+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUNH5PXJ","created_at":"2026-07-05T10:22:14.528096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30241","citing_title":"CommunityFact: A Dynamic, Multilingual, Multi-domain Benchmark for Misinformation Detection in the Wild","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2507.19090","citing_title":"Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG","json":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG.json","graph_json":"https://pith.science/api/pith-number/RUNH5PXJRNLNOA5R6JQ3H6OYWG/graph.json","events_json":"https://pith.science/api/pith-number/RUNH5PXJRNLNOA5R6JQ3H6OYWG/events.json","paper":"https://pith.science/paper/RUNH5PXJ"},"agent_actions":{"view_html":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG","download_json":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG.json","view_paper":"https://pith.science/paper/RUNH5PXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17924&json=true","fetch_graph":"https://pith.science/api/pith-number/RUNH5PXJRNLNOA5R6JQ3H6OYWG/graph.json","fetch_events":"https://pith.science/api/pith-number/RUNH5PXJRNLNOA5R6JQ3H6OYWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG/action/storage_attestation","attest_author":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG/action/author_attestation","sign_citation":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG/action/citation_signature","submit_replication":"https://pith.science/pith/RUNH5PXJRNLNOA5R6JQ3H6OYWG/action/replication_record"}},"created_at":"2026-07-05T10:22:14.528096+00:00","updated_at":"2026-07-05T10:22:14.528096+00:00"}