{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UXRSKYHI2RD6PSMUVMTQXQPOCX","short_pith_number":"pith:UXRSKYHI","schema_version":"1.0","canonical_sha256":"a5e32560e8d447e7c994ab270bc1ee15e1fdc8ee8b9a00fc8b0ea6fa434e2f31","source":{"kind":"arxiv","id":"2505.20171","version":1},"attestation_state":"computed","paper":{"title":"Long-Context State-Space Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Berlin Chen, Eli Shechtman, Gordon Wetzstein, Richard Zhang, Ryan Po, Tri Dao, Xun Huang, Yotam Nitzan","submitted_at":"2025-05-26T16:12:41Z","abstract_excerpt":"Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with processing extended sequences in attention layers. To overcome this limitation, we propose a novel architecture leveraging state-space models (SSMs) to extend temporal memory without compromising computational efficiency. Unlike previous approaches that retrofit SSMs for non-causal vision tasks, our method fully exploits the inherent advantages of SSMs in causa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.20171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T16:12:41Z","cross_cats_sorted":[],"title_canon_sha256":"737ca54f96c766af60fce9cf8f707dec2eef71624536948fa04a3a03927631d2","abstract_canon_sha256":"716d94f30e0d2b67654b1deae3c0afd3184a802c3e90028f25188bfcb6e8c173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.622356Z","signature_b64":"d5EoUdWocnDS76b5Ll3TJuba+cWEaN+mXLVFhd1fF8LF08jdfQ1N/IvIDYBbHn9lZMUaDSlHtZW7nA3jQRPCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5e32560e8d447e7c994ab270bc1ee15e1fdc8ee8b9a00fc8b0ea6fa434e2f31","last_reissued_at":"2026-07-05T11:09:53.621831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.621831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Context State-Space Video World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Berlin Chen, Eli Shechtman, Gordon Wetzstein, Richard Zhang, Ryan Po, Tri Dao, Xun Huang, Yotam Nitzan","submitted_at":"2025-05-26T16:12:41Z","abstract_excerpt":"Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with processing extended sequences in attention layers. To overcome this limitation, we propose a novel architecture leveraging state-space models (SSMs) to extend temporal memory without compromising computational efficiency. Unlike previous approaches that retrofit SSMs for non-causal vision tasks, our method fully exploits the inherent advantages of SSMs in causa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20171","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20171/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.20171","created_at":"2026-07-05T11:09:53.621892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20171v1","created_at":"2026-07-05T11:09:53.621892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20171","created_at":"2026-07-05T11:09:53.621892+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXRSKYHI2RD6","created_at":"2026-07-05T11:09:53.621892+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXRSKYHI2RD6PSMU","created_at":"2026-07-05T11:09:53.621892+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXRSKYHI","created_at":"2026-07-05T11:09:53.621892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07763","citing_title":"Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09803","citing_title":"Echo-Memory: A Controlled Study of Memory in Action World Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31734","citing_title":"MemLearner: Learning to Query Context memory for Video World Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27677","citing_title":"DIM-WAM: World-Action Modeling with Diverse Historical Event Memory","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17423","citing_title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13009","citing_title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08009","citing_title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX","json":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX.json","graph_json":"https://pith.science/api/pith-number/UXRSKYHI2RD6PSMUVMTQXQPOCX/graph.json","events_json":"https://pith.science/api/pith-number/UXRSKYHI2RD6PSMUVMTQXQPOCX/events.json","paper":"https://pith.science/paper/UXRSKYHI"},"agent_actions":{"view_html":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX","download_json":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX.json","view_paper":"https://pith.science/paper/UXRSKYHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20171&json=true","fetch_graph":"https://pith.science/api/pith-number/UXRSKYHI2RD6PSMUVMTQXQPOCX/graph.json","fetch_events":"https://pith.science/api/pith-number/UXRSKYHI2RD6PSMUVMTQXQPOCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX/action/storage_attestation","attest_author":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX/action/author_attestation","sign_citation":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX/action/citation_signature","submit_replication":"https://pith.science/pith/UXRSKYHI2RD6PSMUVMTQXQPOCX/action/replication_record"}},"created_at":"2026-07-05T11:09:53.621892+00:00","updated_at":"2026-07-05T11:09:53.621892+00:00"}