{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6OW423FQMA4K4V3656DZSG5H4W","short_pith_number":"pith:6OW423FQ","schema_version":"1.0","canonical_sha256":"f3adcd6cb06038ae577eef87991ba7e5ac2c2c4788317b1248042b9dafc082b1","source":{"kind":"arxiv","id":"2503.20418","version":2},"attestation_state":"computed","paper":{"title":"ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Ji Woo Hong, Sunjae Yoon, Tri Ton, Trung X. Pham","submitted_at":"2025-03-26T10:49:44Z","abstract_excerpt":"This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of previous approaches by leveraging the Masked Diffusion Transformer (MDT) for improved handling of both global garment context and fine-grained details. The IVTON task involves seamlessly superimposing a garment from one image onto a person in another, creating a realistic depiction of the person wearing the specified garment. Unlike conventional diffusion-based virtual try-on models that depend on large pre-trained U-N"},"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":"2503.20418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T10:49:44Z","cross_cats_sorted":[],"title_canon_sha256":"3d8ac82a87591cfc79a17e72be36de8c2f36193a43dffb3cec07f853f01df731","abstract_canon_sha256":"b3b643fcb2b12e7040d8295e8619511e845a68b0b9d468e2036584d6ed33c4d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:23.164995Z","signature_b64":"MS/RwSU5MwdbBHeCMziNVJ0rHTbOredquJau1ZzAdow7mr7BnggfGr6VKGu1ooBiFf4ANK2AG2Yfjy04iEjRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3adcd6cb06038ae577eef87991ba7e5ac2c2c4788317b1248042b9dafc082b1","last_reissued_at":"2026-07-05T11:13:23.164506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:23.164506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Ji Woo Hong, Sunjae Yoon, Tri Ton, Trung X. Pham","submitted_at":"2025-03-26T10:49:44Z","abstract_excerpt":"This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of previous approaches by leveraging the Masked Diffusion Transformer (MDT) for improved handling of both global garment context and fine-grained details. The IVTON task involves seamlessly superimposing a garment from one image onto a person in another, creating a realistic depiction of the person wearing the specified garment. Unlike conventional diffusion-based virtual try-on models that depend on large pre-trained U-N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20418","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/2503.20418/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":"2503.20418","created_at":"2026-07-05T11:13:23.164560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20418v2","created_at":"2026-07-05T11:13:23.164560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20418","created_at":"2026-07-05T11:13:23.164560+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OW423FQMA4K","created_at":"2026-07-05T11:13:23.164560+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OW423FQMA4K4V36","created_at":"2026-07-05T11:13:23.164560+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OW423FQ","created_at":"2026-07-05T11:13:23.164560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08285","citing_title":"FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W","json":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W.json","graph_json":"https://pith.science/api/pith-number/6OW423FQMA4K4V3656DZSG5H4W/graph.json","events_json":"https://pith.science/api/pith-number/6OW423FQMA4K4V3656DZSG5H4W/events.json","paper":"https://pith.science/paper/6OW423FQ"},"agent_actions":{"view_html":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W","download_json":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W.json","view_paper":"https://pith.science/paper/6OW423FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20418&json=true","fetch_graph":"https://pith.science/api/pith-number/6OW423FQMA4K4V3656DZSG5H4W/graph.json","fetch_events":"https://pith.science/api/pith-number/6OW423FQMA4K4V3656DZSG5H4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W/action/storage_attestation","attest_author":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W/action/author_attestation","sign_citation":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W/action/citation_signature","submit_replication":"https://pith.science/pith/6OW423FQMA4K4V3656DZSG5H4W/action/replication_record"}},"created_at":"2026-07-05T11:13:23.164560+00:00","updated_at":"2026-07-05T11:13:23.164560+00:00"}