{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CD3UBNPFIEHL3BFNEKHTP72TM","short_pith_number":"pith:2CD3UBNP","schema_version":"1.0","canonical_sha256":"d087ba05af2a0875ec25691479bffa9b0f538fd3e77dbdf3332005f090687440","source":{"kind":"arxiv","id":"2412.09600","version":1},"attestation_state":"computed","paper":{"title":"Owl-1: Omni World Model for Consistent Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Jie Zhou, Jiwen Lu, Pengfei Wan, Wenzhao Zheng, Xin Tao, Yuan Gao, Yuanhui Huang","submitted_at":"2024-12-12T18:59:01Z","abstract_excerpt":"Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video generation by iteratively calling the VGMs, using the last-frame output as the condition for the next-round generation. However, the last frame only contains short-term fine-grained information about the scene, resulting in inconsistency in the long horizon. To address this, we propose an Omni World modeL (Owl-1) to produce long-term coherent and comprehensive"},"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":"2412.09600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"26642f0da10d37507fc9800a9177eaf90629f07331233a23ecc81ee1c1d1346e","abstract_canon_sha256":"b8847cd5cdcb70627dfd951063c5490bec124b99bdd0462d2a0fa3d4cbc554db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:26.998424Z","signature_b64":"4HCO4Dz23EAh15f0Q8fq2Rbn1G/Ia+XKjAWHD6cCT7ISzvj34xG8JAt/oL6koABea4Xpiy7GRoO4uH6LcrjhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d087ba05af2a0875ec25691479bffa9b0f538fd3e77dbdf3332005f090687440","last_reissued_at":"2026-07-05T09:48:26.997935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:26.997935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Owl-1: Omni World Model for Consistent Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Jie Zhou, Jiwen Lu, Pengfei Wan, Wenzhao Zheng, Xin Tao, Yuan Gao, Yuanhui Huang","submitted_at":"2024-12-12T18:59:01Z","abstract_excerpt":"Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video generation by iteratively calling the VGMs, using the last-frame output as the condition for the next-round generation. However, the last frame only contains short-term fine-grained information about the scene, resulting in inconsistency in the long horizon. To address this, we propose an Omni World modeL (Owl-1) to produce long-term coherent and comprehensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09600","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/2412.09600/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":"2412.09600","created_at":"2026-07-05T09:48:26.997994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09600v1","created_at":"2026-07-05T09:48:26.997994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09600","created_at":"2026-07-05T09:48:26.997994+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CD3UBNPFIEH","created_at":"2026-07-05T09:48:26.997994+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CD3UBNPFIEHL3BF","created_at":"2026-07-05T09:48:26.997994+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CD3UBNP","created_at":"2026-07-05T09:48:26.997994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17590","citing_title":"TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19957","citing_title":"World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17428","citing_title":"Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM","json":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM.json","graph_json":"https://pith.science/api/pith-number/2CD3UBNPFIEHL3BFNEKHTP72TM/graph.json","events_json":"https://pith.science/api/pith-number/2CD3UBNPFIEHL3BFNEKHTP72TM/events.json","paper":"https://pith.science/paper/2CD3UBNP"},"agent_actions":{"view_html":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM","download_json":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM.json","view_paper":"https://pith.science/paper/2CD3UBNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09600&json=true","fetch_graph":"https://pith.science/api/pith-number/2CD3UBNPFIEHL3BFNEKHTP72TM/graph.json","fetch_events":"https://pith.science/api/pith-number/2CD3UBNPFIEHL3BFNEKHTP72TM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM/action/storage_attestation","attest_author":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM/action/author_attestation","sign_citation":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM/action/citation_signature","submit_replication":"https://pith.science/pith/2CD3UBNPFIEHL3BFNEKHTP72TM/action/replication_record"}},"created_at":"2026-07-05T09:48:26.997994+00:00","updated_at":"2026-07-05T09:48:26.997994+00:00"}