{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D75T6TCSA3FUS4O6AVSHK7PTKF","short_pith_number":"pith:D75T6TCS","canonical_record":{"source":{"id":"2503.00355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1893b8a5648db0886f6e784d482c2c361b3597f90d1a3d34a1b81c2a18fdffe6","abstract_canon_sha256":"5e49408d8a76532bd839dc85376c1a6bc05c71533387b67671bf95276bfc7ec0"},"schema_version":"1.0"},"canonical_sha256":"1ffb3f4c5206cb4971de0564757df3514ec4f6822e7bc8580eb4b69d6b900c03","source":{"kind":"arxiv","id":"2503.00355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00355","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00355v1","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00355","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_12","alias_value":"D75T6TCSA3FU","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_16","alias_value":"D75T6TCSA3FUS4O6","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_8","alias_value":"D75T6TCS","created_at":"2026-07-05T10:22:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D75T6TCSA3FUS4O6AVSHK7PTKF","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1893b8a5648db0886f6e784d482c2c361b3597f90d1a3d34a1b81c2a18fdffe6","abstract_canon_sha256":"5e49408d8a76532bd839dc85376c1a6bc05c71533387b67671bf95276bfc7ec0"},"schema_version":"1.0"},"canonical_sha256":"1ffb3f4c5206cb4971de0564757df3514ec4f6822e7bc8580eb4b69d6b900c03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:21.287893Z","signature_b64":"d41TrrHcA32FWGHMVKpyPJn+DXHR2Cm22zxr1AHIMUStX+Da6sSQxa8BjVsXqcdWNN5FOyOk5qnYRg9c1tLmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ffb3f4c5206cb4971de0564757df3514ec4f6822e7bc8580eb4b69d6b900c03","last_reissued_at":"2026-07-05T10:22:21.287410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:21.287410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00355","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anBPRyxOE32q91BiLRl5Jtl6wTiTCcHSK+adntD/pZVy/RrP8sQ2GjjToM2BdaY2vHVPXGyBmuvsYKGruj37AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:45:16.975776Z"},"content_sha256":"c8f9738aa4265fe4d3fc796315cfbf3f98bb357e852882bcdb1ba9a21f80c94a","schema_version":"1.0","event_id":"sha256:c8f9738aa4265fe4d3fc796315cfbf3f98bb357e852882bcdb1ba9a21f80c94a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D75T6TCSA3FUS4O6AVSHK7PTKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Elsa Fan, Tianyi Huang","submitted_at":"2025-03-01T05:27:54Z","abstract_excerpt":"From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a multi-agent framework that systematically identifies biases by disentangling each statement as fact or opinion, assigning a bias intensity score, and providing concise, factual justifications. Evaluated on 1,500 samples from the WikiNPOV dataset, the framework achieves 84.9% accuracy$\\unicode{x2014}$an improvement of 13.0% over the zero-shot baseline$\\unicode{x2014"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00355","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/2503.00355/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":"2026-07-05T10:22:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5LqTpYbnP82LS1id+tKIWDXpX6mXeOsxoQgYNIzskWixT6C4VhZ7Ngdvo/54k/sZu1LCOa2cWBV6R2PVHBYYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:45:16.976298Z"},"content_sha256":"7cbab0ed520a4207e5407e1328d0d0e559736d96a90ef5a2cb7e4bfbc3b3283e","schema_version":"1.0","event_id":"sha256:7cbab0ed520a4207e5407e1328d0d0e559736d96a90ef5a2cb7e4bfbc3b3283e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/bundle.json","state_url":"https://pith.science/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/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":"2026-08-08T15:45:16Z","links":{"resolver":"https://pith.science/pith/D75T6TCSA3FUS4O6AVSHK7PTKF","bundle":"https://pith.science/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/bundle.json","state":"https://pith.science/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D75T6TCSA3FUS4O6AVSHK7PTKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D75T6TCSA3FUS4O6AVSHK7PTKF","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":"5e49408d8a76532bd839dc85376c1a6bc05c71533387b67671bf95276bfc7ec0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:27:54Z","title_canon_sha256":"1893b8a5648db0886f6e784d482c2c361b3597f90d1a3d34a1b81c2a18fdffe6"},"schema_version":"1.0","source":{"id":"2503.00355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00355","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00355v1","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00355","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_12","alias_value":"D75T6TCSA3FU","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_16","alias_value":"D75T6TCSA3FUS4O6","created_at":"2026-07-05T10:22:21Z"},{"alias_kind":"pith_short_8","alias_value":"D75T6TCS","created_at":"2026-07-05T10:22:21Z"}],"graph_snapshots":[{"event_id":"sha256:7cbab0ed520a4207e5407e1328d0d0e559736d96a90ef5a2cb7e4bfbc3b3283e","target":"graph","created_at":"2026-07-05T10:22:21Z","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/2503.00355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a multi-agent framework that systematically identifies biases by disentangling each statement as fact or opinion, assigning a bias intensity score, and providing concise, factual justifications. Evaluated on 1,500 samples from the WikiNPOV dataset, the framework achieves 84.9% accuracy$\\unicode{x2014}$an improvement of 13.0% over the zero-shot baseline$\\unicode{x2014","authors_text":"Elsa Fan, Tianyi Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:27:54Z","title":"Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00355","kind":"arxiv","version":1},"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:c8f9738aa4265fe4d3fc796315cfbf3f98bb357e852882bcdb1ba9a21f80c94a","target":"record","created_at":"2026-07-05T10:22:21Z","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":"5e49408d8a76532bd839dc85376c1a6bc05c71533387b67671bf95276bfc7ec0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:27:54Z","title_canon_sha256":"1893b8a5648db0886f6e784d482c2c361b3597f90d1a3d34a1b81c2a18fdffe6"},"schema_version":"1.0","source":{"id":"2503.00355","kind":"arxiv","version":1}},"canonical_sha256":"1ffb3f4c5206cb4971de0564757df3514ec4f6822e7bc8580eb4b69d6b900c03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ffb3f4c5206cb4971de0564757df3514ec4f6822e7bc8580eb4b69d6b900c03","first_computed_at":"2026-07-05T10:22:21.287410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:21.287410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d41TrrHcA32FWGHMVKpyPJn+DXHR2Cm22zxr1AHIMUStX+Da6sSQxa8BjVsXqcdWNN5FOyOk5qnYRg9c1tLmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:21.287893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8f9738aa4265fe4d3fc796315cfbf3f98bb357e852882bcdb1ba9a21f80c94a","sha256:7cbab0ed520a4207e5407e1328d0d0e559736d96a90ef5a2cb7e4bfbc3b3283e"],"state_sha256":"73afb5973e567a2aa899180b6e17c7308c8468f3e43fc954c694c349b58e2756"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rsfc6rpD2lz9nOpQlG0iKtFYtFQhN0t+jl2JNqSQLOFFJsZgTYF4o9fonmJg+/WXsZmO7Sb+C9qQYzmrG3aeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:45:16.980346Z","bundle_sha256":"55fd463196e8660b85bf999ab2e0d2afb01fa86372c7d570c258c42eb996bf27"}}