{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IKXVVRSU5LRMR3UF2OJJG2CE4A","short_pith_number":"pith:IKXVVRSU","schema_version":"1.0","canonical_sha256":"42af5ac654eae2c8ee85d392936844e01b93cda9f8d131dfd20abbfac38b12ae","source":{"kind":"arxiv","id":"2506.19644","version":1},"attestation_state":"computed","paper":{"title":"Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"B. Y. Lim, C. Hurter, J. Ng, M. Michelessa","submitted_at":"2025-06-24T14:08:48Z","abstract_excerpt":"Diversity in image generation is essential to ensure fair representations and support creativity in ideation. Hence, many text-to-image models have implemented diversification mechanisms. Yet, after a few iterations of generation, a lack of diversity becomes apparent, because each user has their own diversity goals (e.g., different colors, brands of cars), and there are diverse attributions to be specified. To support user-driven diversity control, we propose Varif.ai that employs text-to-image and Large Language Models to iteratively i) (re)generate a set of images, ii) verify if user-specifi"},"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":"2506.19644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-24T14:08:48Z","cross_cats_sorted":[],"title_canon_sha256":"f8cd8dd258d4e7085699e4d45d185ed1ce81b16843cda25f46974e1b460e97a1","abstract_canon_sha256":"6a2b02b4bf4a82884e1cce252529c75fdb7606e028364a49653756a4d2174093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:36.091990Z","signature_b64":"P6aJ2pc5FsDejGacl0NR6iJKONYd3UT2beG+Lk99HlcliXqi0N0XVzsfhtBMuTxuW3ZFVYusumpqG8+KgIqbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42af5ac654eae2c8ee85d392936844e01b93cda9f8d131dfd20abbfac38b12ae","last_reissued_at":"2026-07-05T11:26:36.091623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:36.091623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"B. Y. Lim, C. Hurter, J. Ng, M. Michelessa","submitted_at":"2025-06-24T14:08:48Z","abstract_excerpt":"Diversity in image generation is essential to ensure fair representations and support creativity in ideation. Hence, many text-to-image models have implemented diversification mechanisms. Yet, after a few iterations of generation, a lack of diversity becomes apparent, because each user has their own diversity goals (e.g., different colors, brands of cars), and there are diverse attributions to be specified. To support user-driven diversity control, we propose Varif.ai that employs text-to-image and Large Language Models to iteratively i) (re)generate a set of images, ii) verify if user-specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19644","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/2506.19644/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":"2506.19644","created_at":"2026-07-05T11:26:36.091678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19644v1","created_at":"2026-07-05T11:26:36.091678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19644","created_at":"2026-07-05T11:26:36.091678+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKXVVRSU5LRM","created_at":"2026-07-05T11:26:36.091678+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKXVVRSU5LRMR3UF","created_at":"2026-07-05T11:26:36.091678+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKXVVRSU","created_at":"2026-07-05T11:26:36.091678+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/IKXVVRSU5LRMR3UF2OJJG2CE4A","json":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A.json","graph_json":"https://pith.science/api/pith-number/IKXVVRSU5LRMR3UF2OJJG2CE4A/graph.json","events_json":"https://pith.science/api/pith-number/IKXVVRSU5LRMR3UF2OJJG2CE4A/events.json","paper":"https://pith.science/paper/IKXVVRSU"},"agent_actions":{"view_html":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A","download_json":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A.json","view_paper":"https://pith.science/paper/IKXVVRSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19644&json=true","fetch_graph":"https://pith.science/api/pith-number/IKXVVRSU5LRMR3UF2OJJG2CE4A/graph.json","fetch_events":"https://pith.science/api/pith-number/IKXVVRSU5LRMR3UF2OJJG2CE4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A/action/storage_attestation","attest_author":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A/action/author_attestation","sign_citation":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A/action/citation_signature","submit_replication":"https://pith.science/pith/IKXVVRSU5LRMR3UF2OJJG2CE4A/action/replication_record"}},"created_at":"2026-07-05T11:26:36.091678+00:00","updated_at":"2026-07-05T11:26:36.091678+00:00"}