{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OQLZA73H724QA6NA7QRCBGCDQM","short_pith_number":"pith:OQLZA73H","schema_version":"1.0","canonical_sha256":"7417907f67feb90079a0fc2220984383228626226b95f976a07e6d2c03e73ec3","source":{"kind":"arxiv","id":"2408.11305","version":2},"attestation_state":"computed","paper":{"title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Wenlong Zhang, Xiangyu Zhao, Xiao-Ming Wu, Yuehan Zhang","submitted_at":"2024-08-21T03:17:20Z","abstract_excerpt":"The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language models for text generation and diffusion models for visual generation, have sparked widespread research interest in applying these multimodal models in the fashion domain. However, tasks involving embeddings, such as image-to-text or text-to-image retrieval, have been largely overlooked from this perspective due to the diverse nature of the multimod"},"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":"2408.11305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T03:17:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5f22e4364472d1ea7b5c797ce689cdfabd694253cc046c509605d2cb7c5458c","abstract_canon_sha256":"c42526d835bff9b687daf14d6ec35f15e3f8be12d87438e0f74695d511661d7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:30.953514Z","signature_b64":"IEw5hHXF3qx0WzgeQC3tRYddxvS7J/6smj3Y0xykLiU0qT0wC+G5ws3PxO3MT8+9BkIgFD4/9e8KTFGMEX3jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7417907f67feb90079a0fc2220984383228626226b95f976a07e6d2c03e73ec3","last_reissued_at":"2026-07-05T09:19:30.953090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:30.953090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Wenlong Zhang, Xiangyu Zhao, Xiao-Ming Wu, Yuehan Zhang","submitted_at":"2024-08-21T03:17:20Z","abstract_excerpt":"The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language models for text generation and diffusion models for visual generation, have sparked widespread research interest in applying these multimodal models in the fashion domain. However, tasks involving embeddings, such as image-to-text or text-to-image retrieval, have been largely overlooked from this perspective due to the diverse nature of the multimod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11305","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/2408.11305/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":"2408.11305","created_at":"2026-07-05T09:19:30.953136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11305v2","created_at":"2026-07-05T09:19:30.953136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11305","created_at":"2026-07-05T09:19:30.953136+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQLZA73H724Q","created_at":"2026-07-05T09:19:30.953136+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQLZA73H724QA6NA","created_at":"2026-07-05T09:19:30.953136+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQLZA73H","created_at":"2026-07-05T09:19:30.953136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09247","citing_title":"Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM","json":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM.json","graph_json":"https://pith.science/api/pith-number/OQLZA73H724QA6NA7QRCBGCDQM/graph.json","events_json":"https://pith.science/api/pith-number/OQLZA73H724QA6NA7QRCBGCDQM/events.json","paper":"https://pith.science/paper/OQLZA73H"},"agent_actions":{"view_html":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM","download_json":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM.json","view_paper":"https://pith.science/paper/OQLZA73H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11305&json=true","fetch_graph":"https://pith.science/api/pith-number/OQLZA73H724QA6NA7QRCBGCDQM/graph.json","fetch_events":"https://pith.science/api/pith-number/OQLZA73H724QA6NA7QRCBGCDQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM/action/storage_attestation","attest_author":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM/action/author_attestation","sign_citation":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM/action/citation_signature","submit_replication":"https://pith.science/pith/OQLZA73H724QA6NA7QRCBGCDQM/action/replication_record"}},"created_at":"2026-07-05T09:19:30.953136+00:00","updated_at":"2026-07-05T09:19:30.953136+00:00"}