{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WQ7ETN46TQD4CFN6HMMJCR4IMV","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":"87c2e0577f971bc0e4f25493f50e3b0a442b85cb6b37e6adec23ad6577034d07","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:58Z","title_canon_sha256":"4eef10ed92d9f9fe46d436d3c71cb590c3b9c6cf0228bcdc9e3fc28fb5b5d440"},"schema_version":"1.0","source":{"id":"2412.07776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07776","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07776v2","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07776","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"WQ7ETN46TQD4","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"WQ7ETN46TQD4CFN6","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"WQ7ETN46","created_at":"2026-07-05T10:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:cf1edbd17b7ff19107bf19139ec759ace016a286ed5c89385d0affa75e2099e3","target":"graph","created_at":"2026-07-05T10:40:15Z","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/2412.07776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embed","authors_text":"Alexander Pondaven, Aliaksandr Siarohin, Fabio Pizzati, Philip Torr, Sergey Tulyakov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:58Z","title":"Video Motion Transfer with Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07776","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":"sha256:26be970ae6d5bb8162a18fc2e2cec0cf9bac9fc95b1325b15c56f2ea90d49596","target":"record","created_at":"2026-07-05T10:40:15Z","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":"87c2e0577f971bc0e4f25493f50e3b0a442b85cb6b37e6adec23ad6577034d07","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:58Z","title_canon_sha256":"4eef10ed92d9f9fe46d436d3c71cb590c3b9c6cf0228bcdc9e3fc28fb5b5d440"},"schema_version":"1.0","source":{"id":"2412.07776","kind":"arxiv","version":2}},"canonical_sha256":"b43e49b79e9c07c115be3b18914788656f01495999ae6ebe546f529e70fd3913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b43e49b79e9c07c115be3b18914788656f01495999ae6ebe546f529e70fd3913","first_computed_at":"2026-07-05T10:40:15.131353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:15.131353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6bY5PWNiaGsNzMpLSVdIrrTlnjktSf6hUQkwXsEmGayLT1TpvMfb689QCdlPYPN0zxLboPxOcZ9HZnskE6eOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:15.131880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26be970ae6d5bb8162a18fc2e2cec0cf9bac9fc95b1325b15c56f2ea90d49596","sha256:cf1edbd17b7ff19107bf19139ec759ace016a286ed5c89385d0affa75e2099e3"],"state_sha256":"6540b16e7d882fca02bc873c3985695ef4d3818f93cfc1d89540e8a5ee5ee8e0"}