{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OHG6RQEA4BFIPGX2N5VSLOJIK2","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":"c2fc3177c77d08a5697ffa23e67a89bb3ba243f379395eeea033ff554127909b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T08:22:50Z","title_canon_sha256":"5efe78921e0aed4e37ce0530e0dc3386c510c7f4da88753de7b0f823fdb2428d"},"schema_version":"1.0","source":{"id":"2502.12632","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12632","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12632v3","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12632","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_12","alias_value":"OHG6RQEA4BFI","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_16","alias_value":"OHG6RQEA4BFIPGX2","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_8","alias_value":"OHG6RQEA","created_at":"2026-07-05T11:33:20Z"}],"graph_snapshots":[{"event_id":"sha256:48bb6f3d40dd723eb25fcf56a34164d97353379a3f1ec26eec757844ecb25bf3","target":"graph","created_at":"2026-07-05T11:33:20Z","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/2502.12632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segm","authors_text":"Agrim Gupta, Dan Kondratyuk, David Ross, Irfan Essa, Jinwoo Shin, Jonathan Huang, Jos\\'e Lezama, Meera Hahn, Sihyun Yu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T08:22:50Z","title":"MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12632","kind":"arxiv","version":3},"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:c7e3fd1eeccf4525dfc35614488a4eaa07db16991a1ea36aa4139db8d06f3940","target":"record","created_at":"2026-07-05T11:33:20Z","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":"c2fc3177c77d08a5697ffa23e67a89bb3ba243f379395eeea033ff554127909b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T08:22:50Z","title_canon_sha256":"5efe78921e0aed4e37ce0530e0dc3386c510c7f4da88753de7b0f823fdb2428d"},"schema_version":"1.0","source":{"id":"2502.12632","kind":"arxiv","version":3}},"canonical_sha256":"71cde8c080e04a879afa6f6b25b928569850845d1852d92528c3023510a5b25d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71cde8c080e04a879afa6f6b25b928569850845d1852d92528c3023510a5b25d","first_computed_at":"2026-07-05T11:33:20.133851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:20.133851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NU5AqUgljATGWpjmOTA8yl3DpMeFNUHGUZrUc8itAr/fwaScccJNhTtLJsw1fBI6792BBkgXgT0sDNqZU1BvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:20.134420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12632","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7e3fd1eeccf4525dfc35614488a4eaa07db16991a1ea36aa4139db8d06f3940","sha256:48bb6f3d40dd723eb25fcf56a34164d97353379a3f1ec26eec757844ecb25bf3"],"state_sha256":"0f9924e6ab62bea2e6387112373e423582192c76c58bbdf711a5c1e90d5fe87c"}