{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QCA26RZZO3KXLQE3CJSVD3VZLH","short_pith_number":"pith:QCA26RZZ","canonical_record":{"source":{"id":"2503.17350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"8ece9216fb8af45e0d1cd9c02f0de2440246bed9de9b9bf805bf483633d4e3d6","abstract_canon_sha256":"ef42dd4b1a6c92f4b2c1e246dd0f378c289a3134470fcf4989a90bcd763a6fdb"},"schema_version":"1.0"},"canonical_sha256":"8081af473976d575c09b126551eeb959c27a8984f9a8b9546eb802171087f0cb","source":{"kind":"arxiv","id":"2503.17350","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17350","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17350v2","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17350","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"QCA26RZZO3KX","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"QCA26RZZO3KXLQE3","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"QCA26RZZ","created_at":"2026-07-05T11:48:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QCA26RZZO3KXLQE3CJSVD3VZLH","target":"record","payload":{"canonical_record":{"source":{"id":"2503.17350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"8ece9216fb8af45e0d1cd9c02f0de2440246bed9de9b9bf805bf483633d4e3d6","abstract_canon_sha256":"ef42dd4b1a6c92f4b2c1e246dd0f378c289a3134470fcf4989a90bcd763a6fdb"},"schema_version":"1.0"},"canonical_sha256":"8081af473976d575c09b126551eeb959c27a8984f9a8b9546eb802171087f0cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:48.009008Z","signature_b64":"IEZ4u8e3dvI3e7dI/2zlrYEDN+UX3wP6mMpTPZUVVoh6O8pYJ8jNAP8sA3GgkHGBp+E+GbkNq6fjZlsm1nicCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8081af473976d575c09b126551eeb959c27a8984f9a8b9546eb802171087f0cb","last_reissued_at":"2026-07-05T11:48:48.008501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:48.008501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.17350","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":"2026-07-05T11:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5QFVWWDXwmLtGdS4MnAS4r+7fkR0QDlO2wKvKqMleWM95P9cLVMWJUiTf9vX4SayDIHdC7N9hb3QP6YE6xaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:26:59.334017Z"},"content_sha256":"051ee5ef58f4d476f737a803c113f5dacd148530a495b1e93ef87f972007daad","schema_version":"1.0","event_id":"sha256:051ee5ef58f4d476f737a803c113f5dacd148530a495b1e93ef87f972007daad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QCA26RZZO3KXLQE3CJSVD3VZLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Jianzong Wu, Jinbin Bai, Lu Qi, Qingyu Shi, Xiangtai Li, Yunhai Tong","submitted_at":"2025-03-21T17:52:05Z","abstract_excerpt":"The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based methods primarily rely on separate spatial and temporal attention mechanisms within the 3D U-Net. In contrast, state-of-the-art video Diffusion Transformers (DiT) models use 3D full attention, which does not explicitly separate temporal and spatial information. Thus, the interaction between spatial and temporal dimensions makes decoupling motion and appearance more challenging for DiT models. In this paper, we propose D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17350","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/2503.17350/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":"2026-07-05T11:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGm8lac39/QYq7MA1Ll2zPI3LJ9/+YQ+6vpRI/fI4L6bMJ2WzFNtG4BdbQO1qyrjXM06Vzr2qRmi0PMGe5gZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:26:59.334535Z"},"content_sha256":"a446599516300c22f0280f1f07508e7d89b3990f10469de322fa281cb809dff9","schema_version":"1.0","event_id":"sha256:a446599516300c22f0280f1f07508e7d89b3990f10469de322fa281cb809dff9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/bundle.json","state_url":"https://pith.science/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/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":"2026-08-09T15:26:59Z","links":{"resolver":"https://pith.science/pith/QCA26RZZO3KXLQE3CJSVD3VZLH","bundle":"https://pith.science/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/bundle.json","state":"https://pith.science/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCA26RZZO3KXLQE3CJSVD3VZLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QCA26RZZO3KXLQE3CJSVD3VZLH","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":"ef42dd4b1a6c92f4b2c1e246dd0f378c289a3134470fcf4989a90bcd763a6fdb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:05Z","title_canon_sha256":"8ece9216fb8af45e0d1cd9c02f0de2440246bed9de9b9bf805bf483633d4e3d6"},"schema_version":"1.0","source":{"id":"2503.17350","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17350","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17350v2","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17350","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"QCA26RZZO3KX","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"QCA26RZZO3KXLQE3","created_at":"2026-07-05T11:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"QCA26RZZ","created_at":"2026-07-05T11:48:48Z"}],"graph_snapshots":[{"event_id":"sha256:a446599516300c22f0280f1f07508e7d89b3990f10469de322fa281cb809dff9","target":"graph","created_at":"2026-07-05T11:48:48Z","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/2503.17350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The motion transfer task aims to transfer motion from a source video to newly generated videos, requiring the model to decouple motion from appearance. Previous diffusion-based methods primarily rely on separate spatial and temporal attention mechanisms within the 3D U-Net. In contrast, state-of-the-art video Diffusion Transformers (DiT) models use 3D full attention, which does not explicitly separate temporal and spatial information. Thus, the interaction between spatial and temporal dimensions makes decoupling motion and appearance more challenging for DiT models. In this paper, we propose D","authors_text":"Jiangning Zhang, Jianzong Wu, Jinbin Bai, Lu Qi, Qingyu Shi, Xiangtai Li, Yunhai Tong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:05Z","title":"Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17350","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":"sha256:051ee5ef58f4d476f737a803c113f5dacd148530a495b1e93ef87f972007daad","target":"record","created_at":"2026-07-05T11:48:48Z","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":"ef42dd4b1a6c92f4b2c1e246dd0f378c289a3134470fcf4989a90bcd763a6fdb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T17:52:05Z","title_canon_sha256":"8ece9216fb8af45e0d1cd9c02f0de2440246bed9de9b9bf805bf483633d4e3d6"},"schema_version":"1.0","source":{"id":"2503.17350","kind":"arxiv","version":2}},"canonical_sha256":"8081af473976d575c09b126551eeb959c27a8984f9a8b9546eb802171087f0cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8081af473976d575c09b126551eeb959c27a8984f9a8b9546eb802171087f0cb","first_computed_at":"2026-07-05T11:48:48.008501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:48.008501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEZ4u8e3dvI3e7dI/2zlrYEDN+UX3wP6mMpTPZUVVoh6O8pYJ8jNAP8sA3GgkHGBp+E+GbkNq6fjZlsm1nicCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:48.009008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17350","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:051ee5ef58f4d476f737a803c113f5dacd148530a495b1e93ef87f972007daad","sha256:a446599516300c22f0280f1f07508e7d89b3990f10469de322fa281cb809dff9"],"state_sha256":"dd26c20be0078cb54e1939f20445039a51e88cc64de9969be17466d248d2ea0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3vjP1QPr9fTijd7FMfSJCFGoayj1nLmmuURy652sqDoJ0To5VfeuST92fLzCqJ8YTX1y8JHNctcPEuiJKYS+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:26:59.340941Z","bundle_sha256":"13a525ee625e7b38c8a4a8320e4a13d9a7b6898f2708394176229b541c801b75"}}