{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EUBTCKC2VX3GEJCJO56YTHHXNM","short_pith_number":"pith:EUBTCKC2","schema_version":"1.0","canonical_sha256":"250331285aadf6622449777d899cf76b3169631269390fa4d87beaaef960280d","source":{"kind":"arxiv","id":"2408.11843","version":2},"attestation_state":"computed","paper":{"title":"Identifying and Mitigating Social Bias Knowledge in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianfei Yang, Jian Wu, Joey Tianyi Zhou, Ruizhe Chen, Yichen Li, Zuozhu Liu","submitted_at":"2024-08-07T17:14:58Z","abstract_excerpt":"Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and evaluated to achieve parity across different social groups but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions. In this paper, we first establish a new bias mitigation benchmark, BiaScope, which systematically assesses performance by leveraging newly constructed datasets and metrics on "},"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":"2408.11843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T17:14:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc14d56a7d0c6c5f6cd7585e850678e7ea44d832a1ba7149d0284bdb0841edb2","abstract_canon_sha256":"1069dcfc0ba087d2ef452a8dc9bb4e3625ed382beadd703e9772f379eb84f58b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:39.428431Z","signature_b64":"59JMcDXUrnZ5WUb4bnVrZ+FnICoTgp4XWSAr5FgQSCvMxIVZs3iCGkYqSoMVjh5ficxEcQEZApSMW0KjfEQLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"250331285aadf6622449777d899cf76b3169631269390fa4d87beaaef960280d","last_reissued_at":"2026-07-05T10:20:39.427932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:39.427932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying and Mitigating Social Bias Knowledge in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianfei Yang, Jian Wu, Joey Tianyi Zhou, Ruizhe Chen, Yichen Li, Zuozhu Liu","submitted_at":"2024-08-07T17:14:58Z","abstract_excerpt":"Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and evaluated to achieve parity across different social groups but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions. In this paper, we first establish a new bias mitigation benchmark, BiaScope, which systematically assesses performance by leveraging newly constructed datasets and metrics on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11843","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/2408.11843/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":"2408.11843","created_at":"2026-07-05T10:20:39.427996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11843v2","created_at":"2026-07-05T10:20:39.427996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11843","created_at":"2026-07-05T10:20:39.427996+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUBTCKC2VX3G","created_at":"2026-07-05T10:20:39.427996+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUBTCKC2VX3GEJCJ","created_at":"2026-07-05T10:20:39.427996+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUBTCKC2","created_at":"2026-07-05T10:20:39.427996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18100","citing_title":"Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM","json":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM.json","graph_json":"https://pith.science/api/pith-number/EUBTCKC2VX3GEJCJO56YTHHXNM/graph.json","events_json":"https://pith.science/api/pith-number/EUBTCKC2VX3GEJCJO56YTHHXNM/events.json","paper":"https://pith.science/paper/EUBTCKC2"},"agent_actions":{"view_html":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM","download_json":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM.json","view_paper":"https://pith.science/paper/EUBTCKC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11843&json=true","fetch_graph":"https://pith.science/api/pith-number/EUBTCKC2VX3GEJCJO56YTHHXNM/graph.json","fetch_events":"https://pith.science/api/pith-number/EUBTCKC2VX3GEJCJO56YTHHXNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM/action/storage_attestation","attest_author":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM/action/author_attestation","sign_citation":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM/action/citation_signature","submit_replication":"https://pith.science/pith/EUBTCKC2VX3GEJCJO56YTHHXNM/action/replication_record"}},"created_at":"2026-07-05T10:20:39.427996+00:00","updated_at":"2026-07-05T10:20:39.427996+00:00"}