{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R72CDHLZ3XHKXSXLT6C5L5VJ6P","short_pith_number":"pith:R72CDHLZ","schema_version":"1.0","canonical_sha256":"8ff4219d79ddceabcaeb9f85d5f6a9f3d5d014f70b4bc5213d2241c99477e92b","source":{"kind":"arxiv","id":"2309.05569","version":1},"attestation_state":"computed","paper":{"title":"ITI-GEN: Inclusive Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Chen Henry Wu, Dmitry Lagun, Fernando De la Torre, Siqi Chai, Thabo Beeler, Xuanbai Chen","submitted_at":"2023-09-11T15:54:30Z","abstract_excerpt":"Text-to-image generative models often reflect the biases of the training data, leading to unequal representations of underrepresented groups. This study investigates inclusive text-to-image generative models that generate images based on human-written prompts and ensure the resulting images are uniformly distributed across attributes of interest. Unfortunately, directly expressing the desired attributes in the prompt often leads to sub-optimal results due to linguistic ambiguity or model misrepresentation. Hence, this paper proposes a drastically different approach that adheres to the maxim th"},"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":"2309.05569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T15:54:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e51c7a44ba0147adccb7c5cb0f142e9afe5d232c28fe28afa4f083f5e05e81ad","abstract_canon_sha256":"59571ec1d55ca48c3d4c36774ec77727864bed6fd295eb5626c88d828b0bae32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:37.015547Z","signature_b64":"zwJ3Zrarzx/E57ZonSibUMINnx/brf5B+Ckt3a65DdoOAjt1PUya/Cmfx5cNzxjKgfl/g1JCCsYkAxghurd3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ff4219d79ddceabcaeb9f85d5f6a9f3d5d014f70b4bc5213d2241c99477e92b","last_reissued_at":"2026-07-05T06:49:37.015031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:37.015031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITI-GEN: Inclusive Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Chen Henry Wu, Dmitry Lagun, Fernando De la Torre, Siqi Chai, Thabo Beeler, Xuanbai Chen","submitted_at":"2023-09-11T15:54:30Z","abstract_excerpt":"Text-to-image generative models often reflect the biases of the training data, leading to unequal representations of underrepresented groups. This study investigates inclusive text-to-image generative models that generate images based on human-written prompts and ensure the resulting images are uniformly distributed across attributes of interest. Unfortunately, directly expressing the desired attributes in the prompt often leads to sub-optimal results due to linguistic ambiguity or model misrepresentation. Hence, this paper proposes a drastically different approach that adheres to the maxim th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05569","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/2309.05569/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":"2309.05569","created_at":"2026-07-05T06:49:37.015094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05569v1","created_at":"2026-07-05T06:49:37.015094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05569","created_at":"2026-07-05T06:49:37.015094+00:00"},{"alias_kind":"pith_short_12","alias_value":"R72CDHLZ3XHK","created_at":"2026-07-05T06:49:37.015094+00:00"},{"alias_kind":"pith_short_16","alias_value":"R72CDHLZ3XHKXSXL","created_at":"2026-07-05T06:49:37.015094+00:00"},{"alias_kind":"pith_short_8","alias_value":"R72CDHLZ","created_at":"2026-07-05T06:49:37.015094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21036","citing_title":"Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P","json":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P.json","graph_json":"https://pith.science/api/pith-number/R72CDHLZ3XHKXSXLT6C5L5VJ6P/graph.json","events_json":"https://pith.science/api/pith-number/R72CDHLZ3XHKXSXLT6C5L5VJ6P/events.json","paper":"https://pith.science/paper/R72CDHLZ"},"agent_actions":{"view_html":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P","download_json":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P.json","view_paper":"https://pith.science/paper/R72CDHLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05569&json=true","fetch_graph":"https://pith.science/api/pith-number/R72CDHLZ3XHKXSXLT6C5L5VJ6P/graph.json","fetch_events":"https://pith.science/api/pith-number/R72CDHLZ3XHKXSXLT6C5L5VJ6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P/action/storage_attestation","attest_author":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P/action/author_attestation","sign_citation":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P/action/citation_signature","submit_replication":"https://pith.science/pith/R72CDHLZ3XHKXSXLT6C5L5VJ6P/action/replication_record"}},"created_at":"2026-07-05T06:49:37.015094+00:00","updated_at":"2026-07-05T06:49:37.015094+00:00"}