{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W35TDWA4JEDWSMTR5BCO3VK3NN","short_pith_number":"pith:W35TDWA4","schema_version":"1.0","canonical_sha256":"b6fb31d81c4907693271e844edd55b6b58f7d72079fefc0a0d40bad587c5cddf","source":{"kind":"arxiv","id":"2502.11603","version":1},"attestation_state":"computed","paper":{"title":"DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongye Qiu, Meikang Qiu, Wenjie Wang, Yue Xu","submitted_at":"2025-02-17T09:43:36Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong natural language processing capabilities but also inherit and amplify societal biases, including gender bias, raising fairness concerns. Existing debiasing methods face significant limitations: parameter tuning requires access to model weights, prompt-based approaches often degrade model utility, and optimization-based techniques lack generalizability. To address these challenges, we propose DR.GAP (Demonstration and Reasoning for Gender-Aware Prompting), an automated and model-agnostic approach that mitigates gender bias while preserving model perfo"},"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":"2502.11603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T09:43:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41d4e04a3aed75e00f523560af3838f4b189c164ee0d994a3941364a546d98fc","abstract_canon_sha256":"3b5320b358b7c019d0b1a78140977e89284bf993c5df44020478f915e27a8cb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:31.437404Z","signature_b64":"i8weJwxJoemUfhQLL1CLj0CbHOybmtlPQHYw8O4brifNQwgdhaLbPP7DxCfKJ9qWSldDhB5ssPZCkaAkR+o0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6fb31d81c4907693271e844edd55b6b58f7d72079fefc0a0d40bad587c5cddf","last_reissued_at":"2026-07-05T10:15:31.436913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:31.436913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongye Qiu, Meikang Qiu, Wenjie Wang, Yue Xu","submitted_at":"2025-02-17T09:43:36Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong natural language processing capabilities but also inherit and amplify societal biases, including gender bias, raising fairness concerns. Existing debiasing methods face significant limitations: parameter tuning requires access to model weights, prompt-based approaches often degrade model utility, and optimization-based techniques lack generalizability. To address these challenges, we propose DR.GAP (Demonstration and Reasoning for Gender-Aware Prompting), an automated and model-agnostic approach that mitigates gender bias while preserving model perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11603","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/2502.11603/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":"2502.11603","created_at":"2026-07-05T10:15:31.436966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11603v1","created_at":"2026-07-05T10:15:31.436966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11603","created_at":"2026-07-05T10:15:31.436966+00:00"},{"alias_kind":"pith_short_12","alias_value":"W35TDWA4JEDW","created_at":"2026-07-05T10:15:31.436966+00:00"},{"alias_kind":"pith_short_16","alias_value":"W35TDWA4JEDWSMTR","created_at":"2026-07-05T10:15:31.436966+00:00"},{"alias_kind":"pith_short_8","alias_value":"W35TDWA4","created_at":"2026-07-05T10:15:31.436966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.16756","citing_title":"Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN","json":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN.json","graph_json":"https://pith.science/api/pith-number/W35TDWA4JEDWSMTR5BCO3VK3NN/graph.json","events_json":"https://pith.science/api/pith-number/W35TDWA4JEDWSMTR5BCO3VK3NN/events.json","paper":"https://pith.science/paper/W35TDWA4"},"agent_actions":{"view_html":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN","download_json":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN.json","view_paper":"https://pith.science/paper/W35TDWA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11603&json=true","fetch_graph":"https://pith.science/api/pith-number/W35TDWA4JEDWSMTR5BCO3VK3NN/graph.json","fetch_events":"https://pith.science/api/pith-number/W35TDWA4JEDWSMTR5BCO3VK3NN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN/action/storage_attestation","attest_author":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN/action/author_attestation","sign_citation":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN/action/citation_signature","submit_replication":"https://pith.science/pith/W35TDWA4JEDWSMTR5BCO3VK3NN/action/replication_record"}},"created_at":"2026-07-05T10:15:31.436966+00:00","updated_at":"2026-07-05T10:15:31.436966+00:00"}