{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJKMFRCC5O7BC5KB43FQRUBOXI","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":"4615f75f08c0892bf0ab55043ef7984bd8ed067d22f9340822a08147e4274d18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:39:09Z","title_canon_sha256":"30fb53f2760d725f4ca24ad1737e2cf1a740abf2ecc7d13ccf8e97dc4f140252"},"schema_version":"1.0","source":{"id":"2412.09828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09828","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09828v1","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09828","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"KJKMFRCC5O7B","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"KJKMFRCC5O7BC5KB","created_at":"2026-07-05T09:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"KJKMFRCC","created_at":"2026-07-05T09:48:42Z"}],"graph_snapshots":[{"event_id":"sha256:1db7358af1ada6e071f57f59bdf362c2ece31c246ef9c142dc24ac36cbd774b0","target":"graph","created_at":"2026-07-05T09:48:42Z","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/2412.09828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to languages, video data are also auto-regressive by nature, so it is counter-intuitive to use attention mechanism with bi-directional dependency in the model. Here we propose a Multi-Scale Causal (MSC) framework to address these problems. Specifically, we introduce multiple resolutions in the spatial dimension and high-low frequencies in the temporal dimension to reali","authors_text":"Mengying Cao, Xunnong Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:39:09Z","title":"MSC: Multi-Scale Spatio-Temporal Causal Attention for Autoregressive Video Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09828","kind":"arxiv","version":1},"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:cb37c04ae889c5636497a45fdb24269e47967b9442c0a44fb73f4dab4e234692","target":"record","created_at":"2026-07-05T09:48:42Z","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":"4615f75f08c0892bf0ab55043ef7984bd8ed067d22f9340822a08147e4274d18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:39:09Z","title_canon_sha256":"30fb53f2760d725f4ca24ad1737e2cf1a740abf2ecc7d13ccf8e97dc4f140252"},"schema_version":"1.0","source":{"id":"2412.09828","kind":"arxiv","version":1}},"canonical_sha256":"5254c2c442ebbe117541e6cb08d02eba3847c189c010e6d691f2a08020888d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5254c2c442ebbe117541e6cb08d02eba3847c189c010e6d691f2a08020888d20","first_computed_at":"2026-07-05T09:48:42.304060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:42.304060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QNFIgtYNrYePpNrRChZtNGRljGYEkTvQZNCNOVpzMt14sAi8qTg4CU0LYhJovXXPS90AbPi9bXR1gtQB1fJlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:42.304483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb37c04ae889c5636497a45fdb24269e47967b9442c0a44fb73f4dab4e234692","sha256:1db7358af1ada6e071f57f59bdf362c2ece31c246ef9c142dc24ac36cbd774b0"],"state_sha256":"0b652c432ed0ec85d09364f6d66a4f6f3eb08112c1625bc30e72e5d1b4d567e3"}