{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E3NO4YJWKF3M3KO3OE367Q3OM4","short_pith_number":"pith:E3NO4YJW","canonical_record":{"source":{"id":"2405.18326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T16:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"93941adee274b415c1301d46fcc07781b164ff9809ed0d45371d93d2801f8c6d","abstract_canon_sha256":"5039e6f7a5de0b519a935b36e3819c2854d5cad2dde3e6e9d8d93f952df50b07"},"schema_version":"1.0"},"canonical_sha256":"26daee61365176cda9db7137efc36e673218ab73a45795e987b8f2cb5f50b419","source":{"kind":"arxiv","id":"2405.18326","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18326","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18326v2","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18326","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"E3NO4YJWKF3M","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"E3NO4YJWKF3M3KO3","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"E3NO4YJW","created_at":"2026-07-05T08:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E3NO4YJWKF3M3KO3OE367Q3OM4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T16:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"93941adee274b415c1301d46fcc07781b164ff9809ed0d45371d93d2801f8c6d","abstract_canon_sha256":"5039e6f7a5de0b519a935b36e3819c2854d5cad2dde3e6e9d8d93f952df50b07"},"schema_version":"1.0"},"canonical_sha256":"26daee61365176cda9db7137efc36e673218ab73a45795e987b8f2cb5f50b419","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:41.398613Z","signature_b64":"ZkyGR+aeIBz47iGeZk82/aywomF7Ehn5lEdBsxkLTAmHA+L3iJMc6y5q11uGKylrYrKMlc+NI/BuJUZoYeIpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26daee61365176cda9db7137efc36e673218ab73a45795e987b8f2cb5f50b419","last_reissued_at":"2026-07-05T08:28:41.398123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:41.398123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18326","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCcqQAxJJAF8GzEoHZnHY1Wp7S6WNkBFAam8KXCwmWppDi5npc2rrr7tAHv8SdDOMTQ1A3NWaJJJ0IqdCyXaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:34:45.326705Z"},"content_sha256":"2ef3059cd5d7f1e149e39b5bd92b3910693f02051446143c21ce9f5a11aa331f","schema_version":"1.0","event_id":"sha256:2ef3059cd5d7f1e149e39b5bd92b3910693f02051446143c21ce9f5a11aa331f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E3NO4YJWKF3M3KO3OE367Q3OM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuwei Zhao, Jun Zheng, Xiaodan Liang, Xin Dong, Youjiang Xu","submitted_at":"2024-05-28T16:21:03Z","abstract_excerpt":"Video try-on stands as a promising area for its tremendous real-world potential. Prior works are limited to transferring product clothing images onto person videos with simple poses and backgrounds, while underperforming on casually captured videos. Recently, Sora revealed the scalability of Diffusion Transformer (DiT) in generating lifelike videos featuring real-world scenarios. Inspired by this, we explore and propose the first DiT-based video try-on framework for practical in-the-wild applications, named VITON-DiT. Specifically, VITON-DiT consists of a garment extractor, a Spatial-Temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18326","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/2405.18326/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t/wtJPVEQKV6Dv735Dz2ivIdQp+5kCPRxxOihN0UoWvl/r5t7sbabSlLj7PqPaedyCZcsl98SrQ5LHrgcw5ACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:34:45.327575Z"},"content_sha256":"71c6444174cdd3105c26965d005ef959a09b4b3ac04763f701859eed9e0262fd","schema_version":"1.0","event_id":"sha256:71c6444174cdd3105c26965d005ef959a09b4b3ac04763f701859eed9e0262fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/bundle.json","state_url":"https://pith.science/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T01:34:45Z","links":{"resolver":"https://pith.science/pith/E3NO4YJWKF3M3KO3OE367Q3OM4","bundle":"https://pith.science/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/bundle.json","state":"https://pith.science/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3NO4YJWKF3M3KO3OE367Q3OM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E3NO4YJWKF3M3KO3OE367Q3OM4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5039e6f7a5de0b519a935b36e3819c2854d5cad2dde3e6e9d8d93f952df50b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T16:21:03Z","title_canon_sha256":"93941adee274b415c1301d46fcc07781b164ff9809ed0d45371d93d2801f8c6d"},"schema_version":"1.0","source":{"id":"2405.18326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18326","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18326v2","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18326","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"E3NO4YJWKF3M","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"E3NO4YJWKF3M3KO3","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"E3NO4YJW","created_at":"2026-07-05T08:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:71c6444174cdd3105c26965d005ef959a09b4b3ac04763f701859eed9e0262fd","target":"graph","created_at":"2026-07-05T08:28:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.18326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video try-on stands as a promising area for its tremendous real-world potential. Prior works are limited to transferring product clothing images onto person videos with simple poses and backgrounds, while underperforming on casually captured videos. Recently, Sora revealed the scalability of Diffusion Transformer (DiT) in generating lifelike videos featuring real-world scenarios. Inspired by this, we explore and propose the first DiT-based video try-on framework for practical in-the-wild applications, named VITON-DiT. Specifically, VITON-DiT consists of a garment extractor, a Spatial-Temporal ","authors_text":"Fuwei Zhao, Jun Zheng, Xiaodan Liang, Xin Dong, Youjiang Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T16:21:03Z","title":"VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18326","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2ef3059cd5d7f1e149e39b5bd92b3910693f02051446143c21ce9f5a11aa331f","target":"record","created_at":"2026-07-05T08:28:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5039e6f7a5de0b519a935b36e3819c2854d5cad2dde3e6e9d8d93f952df50b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T16:21:03Z","title_canon_sha256":"93941adee274b415c1301d46fcc07781b164ff9809ed0d45371d93d2801f8c6d"},"schema_version":"1.0","source":{"id":"2405.18326","kind":"arxiv","version":2}},"canonical_sha256":"26daee61365176cda9db7137efc36e673218ab73a45795e987b8f2cb5f50b419","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26daee61365176cda9db7137efc36e673218ab73a45795e987b8f2cb5f50b419","first_computed_at":"2026-07-05T08:28:41.398123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:41.398123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZkyGR+aeIBz47iGeZk82/aywomF7Ehn5lEdBsxkLTAmHA+L3iJMc6y5q11uGKylrYrKMlc+NI/BuJUZoYeIpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:41.398613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ef3059cd5d7f1e149e39b5bd92b3910693f02051446143c21ce9f5a11aa331f","sha256:71c6444174cdd3105c26965d005ef959a09b4b3ac04763f701859eed9e0262fd"],"state_sha256":"a7d95a12e7b3de99555657152f5faf93beec91da609bd798f99ea9442c725995"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uVTOGZtnGSJ9JPY2xPMe3xEgCn7ZfkbSYeRdpG8Y9676Yuyit7Lm7D0sbu+zUbIMHFvuhuIzgOZaLxxyj5oDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:34:45.334999Z","bundle_sha256":"c882916380b770f289a4c74bde72f200311a961960482500f3f8457ed656ce22"}}