{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E247SW7SLWSPCZWNN6NAVNRCJC","short_pith_number":"pith:E247SW7S","schema_version":"1.0","canonical_sha256":"26b9f95bf25da4f166cd6f9a0ab62248a72e9aa9a6bacd400ec3aba2a98b6a75","source":{"kind":"arxiv","id":"2602.06806","version":2},"attestation_state":"computed","paper":{"title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anjan Dutta, Dan Wang, Muhammad Awais, Serge Belongie, Silpa Vadakkeeveetil Sreelatha","submitted_at":"2026-02-06T15:54:41Z","abstract_excerpt":"Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultur"},"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":"2602.06806","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-06T15:54:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d068a9587284b5e4aacd0a99dd23518f8f9684dc98b6d7de99b301bf0fcf1e7d","abstract_canon_sha256":"a82915c057fdcc6c96034307202c0f8535aa2ade597c4518939cbdd0febc9c96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:42.439892Z","signature_b64":"pJPoiU8mUsoyABz5A3R3NyzF0I/Qva0B9dyOjsUFr8LBZCQOwz7ux19YYdl6Vk4w0xDczGemjFv5KB/hIrW1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b9f95bf25da4f166cd6f9a0ab62248a72e9aa9a6bacd400ec3aba2a98b6a75","last_reissued_at":"2026-06-02T01:03:42.439372Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:42.439372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anjan Dutta, Dan Wang, Muhammad Awais, Serge Belongie, Silpa Vadakkeeveetil Sreelatha","submitted_at":"2026-02-06T15:54:41Z","abstract_excerpt":"Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06806","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/2602.06806/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":"2602.06806","created_at":"2026-06-02T01:03:42.439440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06806v2","created_at":"2026-06-02T01:03:42.439440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06806","created_at":"2026-06-02T01:03:42.439440+00:00"},{"alias_kind":"pith_short_12","alias_value":"E247SW7SLWSP","created_at":"2026-06-02T01:03:42.439440+00:00"},{"alias_kind":"pith_short_16","alias_value":"E247SW7SLWSPCZWN","created_at":"2026-06-02T01:03:42.439440+00:00"},{"alias_kind":"pith_short_8","alias_value":"E247SW7S","created_at":"2026-06-02T01:03:42.439440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC","json":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC.json","graph_json":"https://pith.science/api/pith-number/E247SW7SLWSPCZWNN6NAVNRCJC/graph.json","events_json":"https://pith.science/api/pith-number/E247SW7SLWSPCZWNN6NAVNRCJC/events.json","paper":"https://pith.science/paper/E247SW7S"},"agent_actions":{"view_html":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC","download_json":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC.json","view_paper":"https://pith.science/paper/E247SW7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06806&json=true","fetch_graph":"https://pith.science/api/pith-number/E247SW7SLWSPCZWNN6NAVNRCJC/graph.json","fetch_events":"https://pith.science/api/pith-number/E247SW7SLWSPCZWNN6NAVNRCJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC/action/storage_attestation","attest_author":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC/action/author_attestation","sign_citation":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC/action/citation_signature","submit_replication":"https://pith.science/pith/E247SW7SLWSPCZWNN6NAVNRCJC/action/replication_record"}},"created_at":"2026-06-02T01:03:42.439440+00:00","updated_at":"2026-06-02T01:03:42.439440+00:00"}