{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XMVYVI3VDNZADBEOLI7WLVPVXY","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":"b51eeafcae0d3c0acd78532f8608bfa472fc5e62f8d3fbe30e974c81dee28525","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T09:42:55Z","title_canon_sha256":"198e55f98d6ba9ab5245d3dabbfea1d6ecfd7c14f99180c248931d6ba693c1a3"},"schema_version":"1.0","source":{"id":"2503.14070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14070","created_at":"2026-07-05T10:33:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14070v1","created_at":"2026-07-05T10:33:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14070","created_at":"2026-07-05T10:33:54Z"},{"alias_kind":"pith_short_12","alias_value":"XMVYVI3VDNZA","created_at":"2026-07-05T10:33:54Z"},{"alias_kind":"pith_short_16","alias_value":"XMVYVI3VDNZADBEO","created_at":"2026-07-05T10:33:54Z"},{"alias_kind":"pith_short_8","alias_value":"XMVYVI3V","created_at":"2026-07-05T10:33:54Z"}],"graph_snapshots":[{"event_id":"sha256:be8a592c22307edc6f5e28fc6c19503c5f6c3bc52803bfac2f401b831ab605ef","target":"graph","created_at":"2026-07-05T10:33:54Z","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/2503.14070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of tokens. In this paper, we propose Diagonal Decoding (DiagD), a training-free inference acceleration algorithm for autoregressively pre-trained models that exploits spatial and temporal correlations in videos. Our method generates tokens along diagonal paths in the spatial-temporal token grid, enabling parallel decoding within each frame as well as partially ","authors_text":"Haoyu Wu, Jiang Bian, Junliang Guo, Katja Hofmann, Tabish Rashid, Tianyu He, Tim Pearce, Yang Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T09:42:55Z","title":"Fast Autoregressive Video Generation with Diagonal Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14070","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":"sha256:9e2dec64753effa4c69ef15ea7702b792b69d170ffeb191609aaa98661dfcf4e","target":"record","created_at":"2026-07-05T10:33:54Z","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":"b51eeafcae0d3c0acd78532f8608bfa472fc5e62f8d3fbe30e974c81dee28525","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T09:42:55Z","title_canon_sha256":"198e55f98d6ba9ab5245d3dabbfea1d6ecfd7c14f99180c248931d6ba693c1a3"},"schema_version":"1.0","source":{"id":"2503.14070","kind":"arxiv","version":1}},"canonical_sha256":"bb2b8aa3751b7201848e5a3f65d5f5be0e6f4af8c46a101ada4225d879a651a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb2b8aa3751b7201848e5a3f65d5f5be0e6f4af8c46a101ada4225d879a651a9","first_computed_at":"2026-07-05T10:33:54.486940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:54.486940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4mNZhDsqi2ta/Whg3bDdiEL1qe2EBrrq2EpFnDYdEtoHmA6K1lBc5du3qeMoKsN/w2gvtqmJ0b5RdEP72nl8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:54.487936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e2dec64753effa4c69ef15ea7702b792b69d170ffeb191609aaa98661dfcf4e","sha256:be8a592c22307edc6f5e28fc6c19503c5f6c3bc52803bfac2f401b831ab605ef"],"state_sha256":"7df5b3203cae6da99336041c2c7f0aaa9528336c0fede8a3f5ec3f7fceae2330"}