{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NFDKRPOTDW4U2CIVORL2IDRT2X","short_pith_number":"pith:NFDKRPOT","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"},"canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","source":{"kind":"arxiv","id":"2504.21299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21299","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21299v2","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21299","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"NFDKRPOTDW4U","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"NFDKRPOTDW4U2CIV","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"NFDKRPOT","created_at":"2026-07-05T11:18:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NFDKRPOTDW4U2CIVORL2IDRT2X","target":"record","payload":{"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"},"canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","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"},"source_kind":"arxiv","source_id":"2504.21299","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8pDu+9aXkguLKRGQSK2Hoj4xqT1ARtTwLCOtBMk5ajfM42Rh66g2rdIXD8NHV+tkaL6PWdWnJDTSS5xNaBGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:04:47.170561Z"},"content_sha256":"f361736c7884094129160b0564c464eaa18d4569b399bebb9a396f29d374c261","schema_version":"1.0","event_id":"sha256:f361736c7884094129160b0564c464eaa18d4569b399bebb9a396f29d374c261"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NFDKRPOTDW4U2CIVORL2IDRT2X","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jISgzldO1B2RNpVDoBrg+YWKfr+S8LKfL4jxq9Otqv9Q8kTWSy6SB6Xqt5QEoxDdfx4019MUBbKXst4hb/+gCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:04:47.171516Z"},"content_sha256":"99d7ee66a758cc012ef7f9ec46d5f1d10c7eac9c8039a5909f12d752c261bf87","schema_version":"1.0","event_id":"sha256:99d7ee66a758cc012ef7f9ec46d5f1d10c7eac9c8039a5909f12d752c261bf87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/bundle.json","state_url":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T09:04:47Z","links":{"resolver":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X","bundle":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/bundle.json","state":"https://pith.science/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFDKRPOTDW4U2CIVORL2IDRT2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NFDKRPOTDW4U2CIVORL2IDRT2X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4cb1dc65e1d8afd785adafb46e81f26baf50acc6e8a9e5e64a271d6dc2aa0b57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T04:13:03Z","title_canon_sha256":"d5a568a83f304d513dc76e364d4c8a5a2bd8af9ddb697eff3206922d0707dfa2"},"schema_version":"1.0","source":{"id":"2504.21299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21299","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21299v2","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21299","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"NFDKRPOTDW4U","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"NFDKRPOTDW4U2CIV","created_at":"2026-07-05T11:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"NFDKRPOT","created_at":"2026-07-05T11:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:99d7ee66a758cc012ef7f9ec46d5f1d10c7eac9c8039a5909f12d752c261bf87","target":"graph","created_at":"2026-07-05T11:18:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.21299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ruizhe Chen, Zhiting Fan, Zuozhu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T04:13:03Z","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21299","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f361736c7884094129160b0564c464eaa18d4569b399bebb9a396f29d374c261","target":"record","created_at":"2026-07-05T11:18:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4cb1dc65e1d8afd785adafb46e81f26baf50acc6e8a9e5e64a271d6dc2aa0b57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T04:13:03Z","title_canon_sha256":"d5a568a83f304d513dc76e364d4c8a5a2bd8af9ddb697eff3206922d0707dfa2"},"schema_version":"1.0","source":{"id":"2504.21299","kind":"arxiv","version":2}},"canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6946a8bdd31db94d09157457a40e33d5d39a2e2ecb36fe9227df875ed5dcfa9c","first_computed_at":"2026-07-05T11:18:42.697569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:42.697569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwNUtzujtmJBZw6ktJSdfzOaaBl7piBGuuK9+ZnCSWoZahJ3XxP0fzdBJpcFZJEIlHAcBHmtVFUTEaSU9/AbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:42.698004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f361736c7884094129160b0564c464eaa18d4569b399bebb9a396f29d374c261","sha256:99d7ee66a758cc012ef7f9ec46d5f1d10c7eac9c8039a5909f12d752c261bf87"],"state_sha256":"4277634cf0982867d82fdedc4ec5a4fd96e64369ef278ac48b121115626485c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXHdN6KxXUyWIPodx2k4eglDjBxB46YPfAoDJoGqd1HI+apoC9lG/uOnY6/B3Dh7teg82xYhqUbUCPpfVb2RAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:04:47.178397Z","bundle_sha256":"d075dfdf9be8c7a883576438523bb547a8618fcb54f6cca9d14b5f336b5ef635"}}