{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GLP42B6R7UT7WSR6NBWDA5AOV7","short_pith_number":"pith:GLP42B6R","schema_version":"1.0","canonical_sha256":"32dfcd07d1fd27fb4a3e686c30740eafd08a2b1ff5af23c50b60420bedba346b","source":{"kind":"arxiv","id":"2404.01030","version":3},"attestation_state":"computed","paper":{"title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Anaelia Ovalle, Arjun Subramonian, Ashima Suvarna, Christina Chance, Hritik Bansal, Kai-Wei Chang, Rebecca Pattichis, Yixin Wan, Zongyu Lin","submitted_at":"2024-04-01T10:19:05Z","abstract_excerpt":"The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body of recent works has been dedicated to investigating different dimensions of bias "},"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":"2404.01030","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T10:19:05Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"2b1c329929576cc481c442ce6dc9c72ce68de40dd6111d3338bafa97e41d72c1","abstract_canon_sha256":"c0759b6baadcb55fb43b8c11088c3ddf816a54c8638209b3e389d279f3ead33a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:23.079720Z","signature_b64":"iRDTssJGlnEs10U4/iykbwJR2KdgWFpACPBy++xbiIMziNKqnyJUYKq3pVNCnWAPt7/ZN4QBzfZy+zFpR0+aDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32dfcd07d1fd27fb4a3e686c30740eafd08a2b1ff5af23c50b60420bedba346b","last_reissued_at":"2026-07-05T08:14:23.079157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:23.079157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Anaelia Ovalle, Arjun Subramonian, Ashima Suvarna, Christina Chance, Hritik Bansal, Kai-Wei Chang, Rebecca Pattichis, Yixin Wan, Zongyu Lin","submitted_at":"2024-04-01T10:19:05Z","abstract_excerpt":"The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body of recent works has been dedicated to investigating different dimensions of bias "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01030","kind":"arxiv","version":3},"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/2404.01030/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":"2404.01030","created_at":"2026-07-05T08:14:23.079221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01030v3","created_at":"2026-07-05T08:14:23.079221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01030","created_at":"2026-07-05T08:14:23.079221+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLP42B6R7UT7","created_at":"2026-07-05T08:14:23.079221+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLP42B6R7UT7WSR6","created_at":"2026-07-05T08:14:23.079221+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLP42B6R","created_at":"2026-07-05T08:14:23.079221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20241","citing_title":"BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05829","citing_title":"Gender Artifacts from Art History to Text-to-Image Generation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00039","citing_title":"Beyond Categories of Caste: Examining Caste Bias and Morality in Text-to-Image AI Models","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2405.06535","citing_title":"Controllable Image Generation with Composed Parallel Token Prediction","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21036","citing_title":"Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11934","citing_title":"BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05730","citing_title":"Controllable Image Generation with Composed Parallel Token Prediction","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18167","citing_title":"Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7","json":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7.json","graph_json":"https://pith.science/api/pith-number/GLP42B6R7UT7WSR6NBWDA5AOV7/graph.json","events_json":"https://pith.science/api/pith-number/GLP42B6R7UT7WSR6NBWDA5AOV7/events.json","paper":"https://pith.science/paper/GLP42B6R"},"agent_actions":{"view_html":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7","download_json":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7.json","view_paper":"https://pith.science/paper/GLP42B6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01030&json=true","fetch_graph":"https://pith.science/api/pith-number/GLP42B6R7UT7WSR6NBWDA5AOV7/graph.json","fetch_events":"https://pith.science/api/pith-number/GLP42B6R7UT7WSR6NBWDA5AOV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7/action/storage_attestation","attest_author":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7/action/author_attestation","sign_citation":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7/action/citation_signature","submit_replication":"https://pith.science/pith/GLP42B6R7UT7WSR6NBWDA5AOV7/action/replication_record"}},"created_at":"2026-07-05T08:14:23.079221+00:00","updated_at":"2026-07-05T08:14:23.079221+00:00"}