{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:64MABX2J2VY2B4JZIH2Z2NOIJO","short_pith_number":"pith:64MABX2J","schema_version":"1.0","canonical_sha256":"f71800df49d571a0f13941f59d35c84bb86570d5c1ae23387d238853f3ed2edb","source":{"kind":"arxiv","id":"2507.07079","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Attribute Confusion in Fashion Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Talon, Federico Girella, Yiming Wang, Ziyue Liu","submitted_at":"2025-07-09T17:38:40Z","abstract_excerpt":"Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) locali"},"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":"2507.07079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T17:38:40Z","cross_cats_sorted":[],"title_canon_sha256":"ef375945736d3ce0326b638d41c73795cd5f06c3485879d2f93763a991db3fd1","abstract_canon_sha256":"3b3576ac22ba65c0144cb18ae4dd40811b49a627d6f095f715801200630604b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:28.723388Z","signature_b64":"PSBOFb/KR/qKFNREdFMQLCZ/3YXaeESkQ1Pn394kZ4FzcZwLsxM9A5Tt9DdURKy7+slYFMF5sPq6ThSirGbXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f71800df49d571a0f13941f59d35c84bb86570d5c1ae23387d238853f3ed2edb","last_reissued_at":"2026-07-05T11:34:28.722898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:28.722898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Attribute Confusion in Fashion Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Talon, Federico Girella, Yiming Wang, Ziyue Liu","submitted_at":"2025-07-09T17:38:40Z","abstract_excerpt":"Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) locali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07079","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/2507.07079/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":"2507.07079","created_at":"2026-07-05T11:34:28.722959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07079v1","created_at":"2026-07-05T11:34:28.722959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07079","created_at":"2026-07-05T11:34:28.722959+00:00"},{"alias_kind":"pith_short_12","alias_value":"64MABX2J2VY2","created_at":"2026-07-05T11:34:28.722959+00:00"},{"alias_kind":"pith_short_16","alias_value":"64MABX2J2VY2B4JZ","created_at":"2026-07-05T11:34:28.722959+00:00"},{"alias_kind":"pith_short_8","alias_value":"64MABX2J","created_at":"2026-07-05T11:34:28.722959+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/64MABX2J2VY2B4JZIH2Z2NOIJO","json":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO.json","graph_json":"https://pith.science/api/pith-number/64MABX2J2VY2B4JZIH2Z2NOIJO/graph.json","events_json":"https://pith.science/api/pith-number/64MABX2J2VY2B4JZIH2Z2NOIJO/events.json","paper":"https://pith.science/paper/64MABX2J"},"agent_actions":{"view_html":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO","download_json":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO.json","view_paper":"https://pith.science/paper/64MABX2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07079&json=true","fetch_graph":"https://pith.science/api/pith-number/64MABX2J2VY2B4JZIH2Z2NOIJO/graph.json","fetch_events":"https://pith.science/api/pith-number/64MABX2J2VY2B4JZIH2Z2NOIJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO/action/storage_attestation","attest_author":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO/action/author_attestation","sign_citation":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO/action/citation_signature","submit_replication":"https://pith.science/pith/64MABX2J2VY2B4JZIH2Z2NOIJO/action/replication_record"}},"created_at":"2026-07-05T11:34:28.722959+00:00","updated_at":"2026-07-05T11:34:28.722959+00:00"}