{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q5KHO2WPNY3REUU7M6U27DC3O3","short_pith_number":"pith:Q5KHO2WP","schema_version":"1.0","canonical_sha256":"8754776acf6e3712529f67a9af8c5b76e3c02acfd2d006f4c85ef83f7aaab686","source":{"kind":"arxiv","id":"2302.03675","version":2},"attestation_state":"computed","paper":{"title":"Auditing Gender Presentation Differences in Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.CV","authors_text":"Diyi Yang, Greg Turk, Lu Jiang, Yanzhe Zhang","submitted_at":"2023-02-07T18:52:22Z","abstract_excerpt":"Text-to-image models, which can generate high-quality images based on textual input, have recently enabled various content-creation tools. Despite significantly affecting a wide range of downstream applications, the distributions of these generated images are still not fully understood, especially when it comes to the potential stereotypical attributes of different genders. In this work, we propose a paradigm (Gender Presentation Differences) that utilizes fine-grained self-presentation attributes to study how gender is presented differently in text-to-image models. By probing gender indicator"},"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":"2302.03675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T18:52:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"9eda2aff1a5ab7fb120fb365b0eb3fa5794e97868d7b53b998135250fc16b079","abstract_canon_sha256":"e06335046579050dca0d9a78a68c25c62a3c25825aa884872ec80ebdcdc15996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:54.224017Z","signature_b64":"S+PnohL2SYEr8gbWzx/1qpxKXlVafU0PNFSK6xJdg2aJT2ORk/D5P45wK+zCWVaYI/Av9kVrE0yVHM1lkkd+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8754776acf6e3712529f67a9af8c5b76e3c02acfd2d006f4c85ef83f7aaab686","last_reissued_at":"2026-07-05T11:08:54.223501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:54.223501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auditing Gender Presentation Differences in Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.CV","authors_text":"Diyi Yang, Greg Turk, Lu Jiang, Yanzhe Zhang","submitted_at":"2023-02-07T18:52:22Z","abstract_excerpt":"Text-to-image models, which can generate high-quality images based on textual input, have recently enabled various content-creation tools. Despite significantly affecting a wide range of downstream applications, the distributions of these generated images are still not fully understood, especially when it comes to the potential stereotypical attributes of different genders. In this work, we propose a paradigm (Gender Presentation Differences) that utilizes fine-grained self-presentation attributes to study how gender is presented differently in text-to-image models. By probing gender indicator"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03675","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/2302.03675/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":"2302.03675","created_at":"2026-07-05T11:08:54.223568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03675v2","created_at":"2026-07-05T11:08:54.223568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03675","created_at":"2026-07-05T11:08:54.223568+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5KHO2WPNY3R","created_at":"2026-07-05T11:08:54.223568+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5KHO2WPNY3REUU7","created_at":"2026-07-05T11:08:54.223568+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5KHO2WP","created_at":"2026-07-05T11:08:54.223568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04902","citing_title":"Learning AI Auditing: A Case Study of Teenagers Auditing a Generative AI Model","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3","json":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3.json","graph_json":"https://pith.science/api/pith-number/Q5KHO2WPNY3REUU7M6U27DC3O3/graph.json","events_json":"https://pith.science/api/pith-number/Q5KHO2WPNY3REUU7M6U27DC3O3/events.json","paper":"https://pith.science/paper/Q5KHO2WP"},"agent_actions":{"view_html":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3","download_json":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3.json","view_paper":"https://pith.science/paper/Q5KHO2WP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03675&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5KHO2WPNY3REUU7M6U27DC3O3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5KHO2WPNY3REUU7M6U27DC3O3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3/action/storage_attestation","attest_author":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3/action/author_attestation","sign_citation":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3/action/citation_signature","submit_replication":"https://pith.science/pith/Q5KHO2WPNY3REUU7M6U27DC3O3/action/replication_record"}},"created_at":"2026-07-05T11:08:54.223568+00:00","updated_at":"2026-07-05T11:08:54.223568+00:00"}