{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HK3XXT2BMFJSXMHV7BNBYQWOOB","short_pith_number":"pith:HK3XXT2B","schema_version":"1.0","canonical_sha256":"3ab77bcf4161532bb0f5f85a1c42ce705c1a7d083fa9817a1cc5e9cc242fa7a7","source":{"kind":"arxiv","id":"2509.04515","version":1},"attestation_state":"computed","paper":{"title":"Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameeta Agrawal, Martha O. Dimgba, Philippe J. Giabbanelli, Sharon Oba","submitted_at":"2025-09-03T00:25:25Z","abstract_excerpt":"Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational stories. Representation biases are measured before and after applying our proposed mitigation strategy, Bias Analysis and Mitigation through Explanation (BAME), revealing improvements in demographic representation ranging from 2% to 20%. BAME leverages model-generated explanations to inform targeted prompt engineering, effectively reducing biases without modifying model paramet"},"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":"2509.04515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T00:25:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d1f173a1aefb52fff33050240ba16ca6326f26345465d1f1738339fc62e54a6","abstract_canon_sha256":"02ec80c461bbc97cbf837194fe22da5dae509b3f4bf5e31bdabdc7e5e8a76543"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:24.484218Z","signature_b64":"/sm9HPACgJcBeK7ecRj2pNcDdvdra70JuutE6hksqYmibnGB1Z4P2WMDnPfHqjQyUZGLP88J26JEQCnzi42PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ab77bcf4161532bb0f5f85a1c42ce705c1a7d083fa9817a1cc5e9cc242fa7a7","last_reissued_at":"2026-07-05T12:05:24.483696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:24.483696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameeta Agrawal, Martha O. Dimgba, Philippe J. Giabbanelli, Sharon Oba","submitted_at":"2025-09-03T00:25:25Z","abstract_excerpt":"Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational stories. Representation biases are measured before and after applying our proposed mitigation strategy, Bias Analysis and Mitigation through Explanation (BAME), revealing improvements in demographic representation ranging from 2% to 20%. BAME leverages model-generated explanations to inform targeted prompt engineering, effectively reducing biases without modifying model paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04515","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/2509.04515/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":"2509.04515","created_at":"2026-07-05T12:05:24.483760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04515v1","created_at":"2026-07-05T12:05:24.483760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04515","created_at":"2026-07-05T12:05:24.483760+00:00"},{"alias_kind":"pith_short_12","alias_value":"HK3XXT2BMFJS","created_at":"2026-07-05T12:05:24.483760+00:00"},{"alias_kind":"pith_short_16","alias_value":"HK3XXT2BMFJSXMHV","created_at":"2026-07-05T12:05:24.483760+00:00"},{"alias_kind":"pith_short_8","alias_value":"HK3XXT2B","created_at":"2026-07-05T12:05:24.483760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07969","citing_title":"Neutrality Bites: Gender Representation in AI-Generated Animal Stories","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB","json":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB.json","graph_json":"https://pith.science/api/pith-number/HK3XXT2BMFJSXMHV7BNBYQWOOB/graph.json","events_json":"https://pith.science/api/pith-number/HK3XXT2BMFJSXMHV7BNBYQWOOB/events.json","paper":"https://pith.science/paper/HK3XXT2B"},"agent_actions":{"view_html":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB","download_json":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB.json","view_paper":"https://pith.science/paper/HK3XXT2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04515&json=true","fetch_graph":"https://pith.science/api/pith-number/HK3XXT2BMFJSXMHV7BNBYQWOOB/graph.json","fetch_events":"https://pith.science/api/pith-number/HK3XXT2BMFJSXMHV7BNBYQWOOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB/action/storage_attestation","attest_author":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB/action/author_attestation","sign_citation":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB/action/citation_signature","submit_replication":"https://pith.science/pith/HK3XXT2BMFJSXMHV7BNBYQWOOB/action/replication_record"}},"created_at":"2026-07-05T12:05:24.483760+00:00","updated_at":"2026-07-05T12:05:24.483760+00:00"}