{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZHXVBTKHPSFCHY4YHVUPKM3H65","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":"7453587843dc047d4d68602196bb7bc5f8a38c218cb77f8b22f6c40537b0e7e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T21:39:50Z","title_canon_sha256":"2df332f88e4569fb9628aa4afdb41d113ad09be1c3d13ac421b83d85364364dd"},"schema_version":"1.0","source":{"id":"2605.14136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14136","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14136v1","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14136","created_at":"2026-05-17T23:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZHXVBTKHPSFC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZHXVBTKHPSFCHY4Y","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZHXVBTKH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:78d6fc2d2ce54efd628064d1ed3eb2e8b974c1b8e2e1fed13e26161b030d9bd8","target":"graph","created_at":"2026-05-17T23:39:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across multiple video diffusion models (e.g., Wan2.1, CogVideoX), TeDiO delivers markedly smoother motion while preserving per-frame visual quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That irregular, fragmented temporal diagonals in self-attention maps are the primary cause of temporal incoherence and that lightweight latent updates to promote diagonal smoothness will reliably fix it without introducing new artifacts or degrading quality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TeDiO improves temporal coherence in video diffusion by smoothing irregular diagonals in self-attention maps."}],"snapshot_sha256":"46464cd42366f7df8c707069afd0c526c3e60f1160afa85d6f73ca8ecf6ad136"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering, drifting, or unstable motion. We show that these failures leave a clear imprint inside the model: incoherent videos consistently exhibit irregular, fragmented temporal diagonals in their intermediate self-attention maps, whereas stable motion corresponds to smooth, band-diagonal patterns. Building on this observation, we introduce TeDiO, a training-free, inference-time method that reinforces temporal consistency by regularizing these internal ","authors_text":"Gedas Bertasius, Heather Yu, Marc Niethammer, Nurislam Tursynbek, Zhiqiang Lao","cross_cats":[],"headline":"TeDiO improves temporal coherence in video diffusion by smoothing irregular diagonals in self-attention maps.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T21:39:50Z","title":"TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion"},"references":{"count":56,"internal_anchors":14,"resolved_work":56,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Prolific.https://www.prolific.com/. 7","work_id":"2f65ca33-e999-40b9-8d76-44a72a9119c4","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Cross-image attention for zero- shot appearance transfer","work_id":"7e822769-42c8-475a-92b3-91ae526d6188","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Uniedit: A unified tuning- free framework for video motion and appearance editing","work_id":"daa0c536-ddbd-41ae-8a50-3447fcf0c0d8","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Separate-and-enhance: Composi- tional finetuning for text-to-image diffusion models","work_id":"1d368525-d098-4165-9d22-b555d6a0b449","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Cd- tvd: Contrastive diffusion for 3d super-resolution with scarce high-resolution time-varying data.arXiv preprint arXiv:2508.08173, 2025","work_id":"769afac9-dc01-475e-b27c-ecf4246f40f0","year":2025}],"snapshot_sha256":"b18a97f71c400d68825b225c97c39d8f5bfea0e54a6577ff6a17ed2352971bdf"},"source":{"id":"2605.14136","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T04:56:27.059297Z","id":"e066b3b1-6cf2-4e05-84cb-be40f3596398","model_set":{"reader":"grok-4.3"},"one_line_summary":"TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TeDiO improves temporal coherence in video diffusion by smoothing irregular diagonals in self-attention maps.","strongest_claim":"Across multiple video diffusion models (e.g., Wan2.1, CogVideoX), TeDiO delivers markedly smoother motion while preserving per-frame visual quality.","weakest_assumption":"That irregular, fragmented temporal diagonals in self-attention maps are the primary cause of temporal incoherence and that lightweight latent updates to promote diagonal smoothness will reliably fix it without introducing new artifacts or degrading quality."}},"verdict_id":"e066b3b1-6cf2-4e05-84cb-be40f3596398"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b1d8e2b4af02ae2d97dd7112d932da8ebcac15c3fe281485132c0db53ddecbd6","target":"record","created_at":"2026-05-17T23:39:11Z","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":"7453587843dc047d4d68602196bb7bc5f8a38c218cb77f8b22f6c40537b0e7e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T21:39:50Z","title_canon_sha256":"2df332f88e4569fb9628aa4afdb41d113ad09be1c3d13ac421b83d85364364dd"},"schema_version":"1.0","source":{"id":"2605.14136","kind":"arxiv","version":1}},"canonical_sha256":"c9ef50cd477c8a23e3983d68f53367f77340812cd5cd1dae56ce399b4bda4b14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9ef50cd477c8a23e3983d68f53367f77340812cd5cd1dae56ce399b4bda4b14","first_computed_at":"2026-05-17T23:39:11.738810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:11.738810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QNfV/9lnJZzrKdO4f63Q0mOO+oV0K71/s19GBedCtH2JkNHR+lAzHT+WEz45uJNBqdZO1uexeyZRPnTtkuDvBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:11.739297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1d8e2b4af02ae2d97dd7112d932da8ebcac15c3fe281485132c0db53ddecbd6","sha256:78d6fc2d2ce54efd628064d1ed3eb2e8b974c1b8e2e1fed13e26161b030d9bd8"],"state_sha256":"db62a117e15a7573d34c1ea76395899de65d2fd67d00a59310f6fdca09ad0717"}