{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NFDKRPOTDW4U2CIVORL2IDRT2X","short_pith_number":"pith:NFDKRPOT","schema_version":"1.0","canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","source":{"kind":"arxiv","id":"2504.21299","version":2},"attestation_state":"computed","paper":{"title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruizhe Chen, Zhiting Fan, Zuozhu Liu","submitted_at":"2025-04-30T04:13:03Z","abstract_excerpt":"Identifying bias in LLM-generated content is a crucial prerequisite for ensuring fairness in LLMs. Existing methods, such as fairness classifiers and LLM-based judges, face limitations related to difficulties in understanding underlying intentions and the lack of criteria for fairness judgment. In this paper, we introduce BiasGuard, a novel bias detection tool that explicitly analyzes inputs and reasons through fairness specifications to provide accurate judgments. BiasGuard is implemented through a two-stage approach: the first stage initializes the model to explicitly reason based on fairnes"},"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":"2504.21299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T04:13:03Z","cross_cats_sorted":[],"title_canon_sha256":"d5a568a83f304d513dc76e364d4c8a5a2bd8af9ddb697eff3206922d0707dfa2","abstract_canon_sha256":"4cb1dc65e1d8afd785adafb46e81f26baf50acc6e8a9e5e64a271d6dc2aa0b57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:42.698004Z","signature_b64":"iwNUtzujtmJBZw6ktJSdfzOaaBl7piBGuuK9+ZnCSWoZahJ3XxP0fzdBJpcFZJEIlHAcBHmtVFUTEaSU9/AbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","last_reissued_at":"2026-07-05T11:18:42.697569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:42.697569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruizhe Chen, Zhiting Fan, Zuozhu Liu","submitted_at":"2025-04-30T04:13:03Z","abstract_excerpt":"Identifying bias in LLM-generated content is a crucial prerequisite for ensuring fairness in LLMs. Existing methods, such as fairness classifiers and LLM-based judges, face limitations related to difficulties in understanding underlying intentions and the lack of criteria for fairness judgment. In this paper, we introduce BiasGuard, a novel bias detection tool that explicitly analyzes inputs and reasons through fairness specifications to provide accurate judgments. BiasGuard is implemented through a two-stage approach: the first stage initializes the model to explicitly reason based on fairnes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21299","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/2504.21299/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":"2504.21299","created_at":"2026-07-05T11:18:42.697628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21299v2","created_at":"2026-07-05T11:18:42.697628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21299","created_at":"2026-07-05T11:18:42.697628+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFDKRPOTDW4U","created_at":"2026-07-05T11:18:42.697628+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFDKRPOTDW4U2CIV","created_at":"2026-07-05T11:18:42.697628+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFDKRPOT","created_at":"2026-07-05T11:18:42.697628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12527","citing_title":"Detection, Classification, and Mitigation of Gender Bias in Large Language Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X","json":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X.json","graph_json":"https://pith.science/api/pith-number/NFDKRPOTDW4U2CIVORL2IDRT2X/graph.json","events_json":"https://pith.science/api/pith-number/NFDKRPOTDW4U2CIVORL2IDRT2X/events.json","paper":"https://pith.science/paper/NFDKRPOT"},"agent_actions":{"view_html":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X","download_json":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X.json","view_paper":"https://pith.science/paper/NFDKRPOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21299&json=true","fetch_graph":"https://pith.science/api/pith-number/NFDKRPOTDW4U2CIVORL2IDRT2X/graph.json","fetch_events":"https://pith.science/api/pith-number/NFDKRPOTDW4U2CIVORL2IDRT2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/action/storage_attestation","attest_author":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/action/author_attestation","sign_citation":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/action/citation_signature","submit_replication":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/action/replication_record"}},"created_at":"2026-07-05T11:18:42.697628+00:00","updated_at":"2026-07-05T11:18:42.697628+00:00"}