{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7MU2IMAUP7KFCETAUWE7XVE6ZN","short_pith_number":"pith:7MU2IMAU","schema_version":"1.0","canonical_sha256":"fb29a430147fd4511260a589fbd49ecb5bcd350c1adf9a71219b0714fce2379e","source":{"kind":"arxiv","id":"2505.17280","version":1},"attestation_state":"computed","paper":{"title":"Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Chinchure, Alexander Tolbert, Emily Diana, Kartik Hosanagar, Leonid Sigal, Matthew Turk, Pushkar Shukla, Vineeth N Balasubramanian","submitted_at":"2025-05-22T20:56:38Z","abstract_excerpt":"The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such as ethnicity or age - can inadvertently affect another, like gender, either mitigating or exacerbating existing disparities. Understanding these interdependencies is crucial for designing fairer generative models, yet measuring such effects quantitatively remains a challenge. To address this, we introduce BiasConnect, a novel tool for analyzing and quantifying bias interactions in TTI models. BiasConnect uses counter"},"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":"2505.17280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T20:56:38Z","cross_cats_sorted":[],"title_canon_sha256":"1d2616e77b91ff1acafa8062869206a41818f18abbdccc659d041e9103a7cf9e","abstract_canon_sha256":"b63a610f4d512ffdf9eb00876b09758fd2fda0aec63b2387f3a5da1d8ae83427"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:23.867042Z","signature_b64":"OllZe1WtkkjDqqKtF5AduAh3qevoLnfQowSqMyPj+OS1sogiRFqL1Z9MF1sm5SjamYFJWlLIo7tMdfUX88LjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb29a430147fd4511260a589fbd49ecb5bcd350c1adf9a71219b0714fce2379e","last_reissued_at":"2026-07-05T11:08:23.866581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:23.866581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Chinchure, Alexander Tolbert, Emily Diana, Kartik Hosanagar, Leonid Sigal, Matthew Turk, Pushkar Shukla, Vineeth N Balasubramanian","submitted_at":"2025-05-22T20:56:38Z","abstract_excerpt":"The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such as ethnicity or age - can inadvertently affect another, like gender, either mitigating or exacerbating existing disparities. Understanding these interdependencies is crucial for designing fairer generative models, yet measuring such effects quantitatively remains a challenge. To address this, we introduce BiasConnect, a novel tool for analyzing and quantifying bias interactions in TTI models. BiasConnect uses counter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17280","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/2505.17280/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":"2505.17280","created_at":"2026-07-05T11:08:23.866638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17280v1","created_at":"2026-07-05T11:08:23.866638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17280","created_at":"2026-07-05T11:08:23.866638+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MU2IMAUP7KF","created_at":"2026-07-05T11:08:23.866638+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MU2IMAUP7KFCETA","created_at":"2026-07-05T11:08:23.866638+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MU2IMAU","created_at":"2026-07-05T11:08:23.866638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN","json":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN.json","graph_json":"https://pith.science/api/pith-number/7MU2IMAUP7KFCETAUWE7XVE6ZN/graph.json","events_json":"https://pith.science/api/pith-number/7MU2IMAUP7KFCETAUWE7XVE6ZN/events.json","paper":"https://pith.science/paper/7MU2IMAU"},"agent_actions":{"view_html":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN","download_json":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN.json","view_paper":"https://pith.science/paper/7MU2IMAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17280&json=true","fetch_graph":"https://pith.science/api/pith-number/7MU2IMAUP7KFCETAUWE7XVE6ZN/graph.json","fetch_events":"https://pith.science/api/pith-number/7MU2IMAUP7KFCETAUWE7XVE6ZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN/action/storage_attestation","attest_author":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN/action/author_attestation","sign_citation":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN/action/citation_signature","submit_replication":"https://pith.science/pith/7MU2IMAUP7KFCETAUWE7XVE6ZN/action/replication_record"}},"created_at":"2026-07-05T11:08:23.866638+00:00","updated_at":"2026-07-05T11:08:23.866638+00:00"}