{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HBQEB4PC44DTZ5YKFEXEYEOOG4","short_pith_number":"pith:HBQEB4PC","schema_version":"1.0","canonical_sha256":"386040f1e2e7073cf70a292e4c11ce373e3fc31f251a9f9c45310d5e84ccfd9b","source":{"kind":"arxiv","id":"2506.05210","version":2},"attestation_state":"computed","paper":{"title":"Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Guandao Yang, Jan Ackermann, Kiyohiro Nakayama, Tong Wu","submitted_at":"2025-06-05T16:22:17Z","abstract_excerpt":"Multimodal foundation models have demonstrated strong generalization, yet their ability to transfer knowledge to specialized domains such as garment generation remains underexplored. We introduce VLG, a vision-language-garment model that synthesizes garments from textual descriptions and visual imagery. Our experiments assess VLG's zero-shot generalization, investigating its ability to transfer web-scale reasoning to unseen garment styles and prompts. Preliminary results indicate promising transfer capabilities, highlighting the potential for multimodal foundation models to adapt effectively t"},"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":"2506.05210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T16:22:17Z","cross_cats_sorted":[],"title_canon_sha256":"68985ec24977db803328a93619dcc77a721aad176af404713e273c8b9cf2534c","abstract_canon_sha256":"cb85b43fa9854a2688804bc5c4292a4c3a33545175a5dfbb723b5c1722e951dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:12.523265Z","signature_b64":"wdy2Iohm3SZN9aMKiEStUf2rW2ClXs5wTRXXdFFt0S8azPHJIuNedYxzGOpqROt0cQvSUvzk3JQDj49j/0GFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"386040f1e2e7073cf70a292e4c11ce373e3fc31f251a9f9c45310d5e84ccfd9b","last_reissued_at":"2026-07-05T11:29:12.522752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:12.522752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Guandao Yang, Jan Ackermann, Kiyohiro Nakayama, Tong Wu","submitted_at":"2025-06-05T16:22:17Z","abstract_excerpt":"Multimodal foundation models have demonstrated strong generalization, yet their ability to transfer knowledge to specialized domains such as garment generation remains underexplored. We introduce VLG, a vision-language-garment model that synthesizes garments from textual descriptions and visual imagery. Our experiments assess VLG's zero-shot generalization, investigating its ability to transfer web-scale reasoning to unseen garment styles and prompts. Preliminary results indicate promising transfer capabilities, highlighting the potential for multimodal foundation models to adapt effectively t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05210","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/2506.05210/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":"2506.05210","created_at":"2026-07-05T11:29:12.522817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05210v2","created_at":"2026-07-05T11:29:12.522817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05210","created_at":"2026-07-05T11:29:12.522817+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBQEB4PC44DT","created_at":"2026-07-05T11:29:12.522817+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBQEB4PC44DTZ5YK","created_at":"2026-07-05T11:29:12.522817+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBQEB4PC","created_at":"2026-07-05T11:29:12.522817+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/HBQEB4PC44DTZ5YKFEXEYEOOG4","json":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4.json","graph_json":"https://pith.science/api/pith-number/HBQEB4PC44DTZ5YKFEXEYEOOG4/graph.json","events_json":"https://pith.science/api/pith-number/HBQEB4PC44DTZ5YKFEXEYEOOG4/events.json","paper":"https://pith.science/paper/HBQEB4PC"},"agent_actions":{"view_html":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4","download_json":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4.json","view_paper":"https://pith.science/paper/HBQEB4PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05210&json=true","fetch_graph":"https://pith.science/api/pith-number/HBQEB4PC44DTZ5YKFEXEYEOOG4/graph.json","fetch_events":"https://pith.science/api/pith-number/HBQEB4PC44DTZ5YKFEXEYEOOG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4/action/storage_attestation","attest_author":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4/action/author_attestation","sign_citation":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4/action/citation_signature","submit_replication":"https://pith.science/pith/HBQEB4PC44DTZ5YKFEXEYEOOG4/action/replication_record"}},"created_at":"2026-07-05T11:29:12.522817+00:00","updated_at":"2026-07-05T11:29:12.522817+00:00"}