{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SKVPMH7O3YI5FHVUA2ASS2VWUT","short_pith_number":"pith:SKVPMH7O","schema_version":"1.0","canonical_sha256":"92aaf61feede11d29eb40681296ab6a4c63192e14338477a1e370ee7300b647a","source":{"kind":"arxiv","id":"2408.12352","version":2},"attestation_state":"computed","paper":{"title":"GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanhui Li, Shiyue Zhang, Xiaodan Liang, Xujie Zhang, Yiqiang Yan, Yuhao Cheng, Zheng Chong","submitted_at":"2024-08-22T12:50:45Z","abstract_excerpt":"General text-to-image models bring revolutionary innovation to the fields of arts, design, and media. However, when applied to garment generation, even the state-of-the-art text-to-image models suffer from fine-grained semantic misalignment, particularly concerning the quantity, position, and interrelations of garment components. Addressing this, we propose GarmentAligner, a text-to-garment diffusion model trained with retrieval-augmented multi-level corrections. To achieve semantic alignment at the component level, we introduce an automatic component extraction pipeline to obtain spatial and "},"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":"2408.12352","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T12:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"32bf655a86024a72bbdbb5ef9e924639463397903d2c15d90663f32c1ff2b7fd","abstract_canon_sha256":"7adb912815780f2e3eb9434568ac0e8fc8c282af2b12875640c749af3c01ba6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:26.858005Z","signature_b64":"3wg0zN3fUFG7C9lrxFIFvPhS8RemE1K9j+ck8NYiJIf0ud2nda4Mtob0hjCvCafrJrSeGjTpXfNuEXCXBc3gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92aaf61feede11d29eb40681296ab6a4c63192e14338477a1e370ee7300b647a","last_reissued_at":"2026-07-05T08:58:26.857581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:26.857581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanhui Li, Shiyue Zhang, Xiaodan Liang, Xujie Zhang, Yiqiang Yan, Yuhao Cheng, Zheng Chong","submitted_at":"2024-08-22T12:50:45Z","abstract_excerpt":"General text-to-image models bring revolutionary innovation to the fields of arts, design, and media. However, when applied to garment generation, even the state-of-the-art text-to-image models suffer from fine-grained semantic misalignment, particularly concerning the quantity, position, and interrelations of garment components. Addressing this, we propose GarmentAligner, a text-to-garment diffusion model trained with retrieval-augmented multi-level corrections. To achieve semantic alignment at the component level, we introduce an automatic component extraction pipeline to obtain spatial and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12352","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/2408.12352/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":"2408.12352","created_at":"2026-07-05T08:58:26.857643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12352v2","created_at":"2026-07-05T08:58:26.857643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12352","created_at":"2026-07-05T08:58:26.857643+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKVPMH7O3YI5","created_at":"2026-07-05T08:58:26.857643+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKVPMH7O3YI5FHVU","created_at":"2026-07-05T08:58:26.857643+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKVPMH7O","created_at":"2026-07-05T08:58:26.857643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23186","citing_title":"HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT","json":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT.json","graph_json":"https://pith.science/api/pith-number/SKVPMH7O3YI5FHVUA2ASS2VWUT/graph.json","events_json":"https://pith.science/api/pith-number/SKVPMH7O3YI5FHVUA2ASS2VWUT/events.json","paper":"https://pith.science/paper/SKVPMH7O"},"agent_actions":{"view_html":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT","download_json":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT.json","view_paper":"https://pith.science/paper/SKVPMH7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12352&json=true","fetch_graph":"https://pith.science/api/pith-number/SKVPMH7O3YI5FHVUA2ASS2VWUT/graph.json","fetch_events":"https://pith.science/api/pith-number/SKVPMH7O3YI5FHVUA2ASS2VWUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT/action/storage_attestation","attest_author":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT/action/author_attestation","sign_citation":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT/action/citation_signature","submit_replication":"https://pith.science/pith/SKVPMH7O3YI5FHVUA2ASS2VWUT/action/replication_record"}},"created_at":"2026-07-05T08:58:26.857643+00:00","updated_at":"2026-07-05T08:58:26.857643+00:00"}