{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U77AJ2RF3TRIAP3ZND4KTMZJUE","short_pith_number":"pith:U77AJ2RF","schema_version":"1.0","canonical_sha256":"a7fe04ea25dce2803f7968f8a9b329a11051812abcf98d2b869282674dec6eb3","source":{"kind":"arxiv","id":"2305.10566","version":1},"attestation_state":"computed","paper":{"title":"Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Liwei Shen, Luhang Sun, Mian Wei, Sijia Yang, Yibing Sun, Yoo Ji Suh","submitted_at":"2023-05-17T20:59:10Z","abstract_excerpt":"Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL-E 2 images spanning 153 occupations, and assessed potential bias amplification by benchmarking against 2021 census labor statistics and Google Images. Our findings reveal that DALL-E 2 underrepresents women"},"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":"2305.10566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T20:59:10Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"826f01c11501eb15a7c7fb3b30b13659e4ba92e84ad2cee17bf9a1c02e102ea3","abstract_canon_sha256":"16901e3eb879b4f94f13128831419100fbef1b918f975a886fea1df06d8d7f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:00.096283Z","signature_b64":"0DchC2Hm+YvsAXAX5zrhieZZR2OcWDRq2JYflWFYVL8BlHFGgdX8neoIpzn8NzEo0l/CyLep6uhxTl0XX/+tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7fe04ea25dce2803f7968f8a9b329a11051812abcf98d2b869282674dec6eb3","last_reissued_at":"2026-07-05T09:06:00.095805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:00.095805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Liwei Shen, Luhang Sun, Mian Wei, Sijia Yang, Yibing Sun, Yoo Ji Suh","submitted_at":"2023-05-17T20:59:10Z","abstract_excerpt":"Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL-E 2 images spanning 153 occupations, and assessed potential bias amplification by benchmarking against 2021 census labor statistics and Google Images. Our findings reveal that DALL-E 2 underrepresents women"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10566","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/2305.10566/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":"2305.10566","created_at":"2026-07-05T09:06:00.095863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10566v1","created_at":"2026-07-05T09:06:00.095863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10566","created_at":"2026-07-05T09:06:00.095863+00:00"},{"alias_kind":"pith_short_12","alias_value":"U77AJ2RF3TRI","created_at":"2026-07-05T09:06:00.095863+00:00"},{"alias_kind":"pith_short_16","alias_value":"U77AJ2RF3TRIAP3Z","created_at":"2026-07-05T09:06:00.095863+00:00"},{"alias_kind":"pith_short_8","alias_value":"U77AJ2RF","created_at":"2026-07-05T09:06:00.095863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.20640","citing_title":"CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE","json":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE.json","graph_json":"https://pith.science/api/pith-number/U77AJ2RF3TRIAP3ZND4KTMZJUE/graph.json","events_json":"https://pith.science/api/pith-number/U77AJ2RF3TRIAP3ZND4KTMZJUE/events.json","paper":"https://pith.science/paper/U77AJ2RF"},"agent_actions":{"view_html":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE","download_json":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE.json","view_paper":"https://pith.science/paper/U77AJ2RF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10566&json=true","fetch_graph":"https://pith.science/api/pith-number/U77AJ2RF3TRIAP3ZND4KTMZJUE/graph.json","fetch_events":"https://pith.science/api/pith-number/U77AJ2RF3TRIAP3ZND4KTMZJUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE/action/storage_attestation","attest_author":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE/action/author_attestation","sign_citation":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE/action/citation_signature","submit_replication":"https://pith.science/pith/U77AJ2RF3TRIAP3ZND4KTMZJUE/action/replication_record"}},"created_at":"2026-07-05T09:06:00.095863+00:00","updated_at":"2026-07-05T09:06:00.095863+00:00"}