{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5W5VFN3VADDQ6F5TQQIU7U7UIT","short_pith_number":"pith:5W5VFN3V","schema_version":"1.0","canonical_sha256":"edbb52b77500c70f17b384114fd3f444d898f607166355eeab1335101e548823","source":{"kind":"arxiv","id":"2504.05632","version":3},"attestation_state":"computed","paper":{"title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshita Jha, Chandan K. Reddy, Sanchit Kabra","submitted_at":"2025-04-08T03:21:51Z","abstract_excerpt":"Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple op"},"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":"2504.05632","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T03:21:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"38a2311781361b00f4fb472fc00029c06d20bc5cf5059412dfb27c8e42c090cd","abstract_canon_sha256":"e807bcaba23f5069a5a31fc8e7c469c22acb5c230922abd549e8ef8c1352ac14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:57.159475Z","signature_b64":"DI0ylMjhTb1JoHIg3LHMgY5p2lZNCkX12HCTq0KAjL8QsiOIiMgp47tjimdhqVkeODSRbqvCsnXcL4M8muUWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edbb52b77500c70f17b384114fd3f444d898f607166355eeab1335101e548823","last_reissued_at":"2026-07-05T11:16:57.158965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:57.158965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshita Jha, Chandan K. Reddy, Sanchit Kabra","submitted_at":"2025-04-08T03:21:51Z","abstract_excerpt":"Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05632","kind":"arxiv","version":3},"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/2504.05632/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":"2504.05632","created_at":"2026-07-05T11:16:57.159025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05632v3","created_at":"2026-07-05T11:16:57.159025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05632","created_at":"2026-07-05T11:16:57.159025+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W5VFN3VADDQ","created_at":"2026-07-05T11:16:57.159025+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W5VFN3VADDQ6F5T","created_at":"2026-07-05T11:16:57.159025+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W5VFN3V","created_at":"2026-07-05T11:16:57.159025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02595","citing_title":"MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT","json":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT.json","graph_json":"https://pith.science/api/pith-number/5W5VFN3VADDQ6F5TQQIU7U7UIT/graph.json","events_json":"https://pith.science/api/pith-number/5W5VFN3VADDQ6F5TQQIU7U7UIT/events.json","paper":"https://pith.science/paper/5W5VFN3V"},"agent_actions":{"view_html":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT","download_json":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT.json","view_paper":"https://pith.science/paper/5W5VFN3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05632&json=true","fetch_graph":"https://pith.science/api/pith-number/5W5VFN3VADDQ6F5TQQIU7U7UIT/graph.json","fetch_events":"https://pith.science/api/pith-number/5W5VFN3VADDQ6F5TQQIU7U7UIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT/action/storage_attestation","attest_author":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT/action/author_attestation","sign_citation":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT/action/citation_signature","submit_replication":"https://pith.science/pith/5W5VFN3VADDQ6F5TQQIU7U7UIT/action/replication_record"}},"created_at":"2026-07-05T11:16:57.159025+00:00","updated_at":"2026-07-05T11:16:57.159025+00:00"}