{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DJIJWGQAMI6K2IVXWJSGXF47TE","short_pith_number":"pith:DJIJWGQA","schema_version":"1.0","canonical_sha256":"1a509b1a00623cad22b7b2646b979f992d4f30102d5c71e757c82bcfa027884c","source":{"kind":"arxiv","id":"2412.04842","version":3},"attestation_state":"computed","paper":{"title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haifeng Xia, Jingcheng Ni, Rui Chen, Siyu Xia, Yichen Liu, Yuxin Guo, Zehuan Wu","submitted_at":"2024-12-06T08:27:53Z","abstract_excerpt":"The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos remains a significant challenge. To address this, we present UniMLVG, a unified framework designed to generate extended street multi-perspective videos under precise control. By integrating single- and multi-view driving videos into the training data, our approach updates a DiT-based diffusion model equipped with cross-frame and cross-view modules across three sta"},"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":"2412.04842","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T08:27:53Z","cross_cats_sorted":[],"title_canon_sha256":"8a5ab037a14d7262e0704a53fcf5783397849f9d3b88915e5b4a46de58e124cc","abstract_canon_sha256":"828ddb26cbe5e663d163c06581d123bddf5b66ae73bf03bd42c6eede7c08d25b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:14.830904Z","signature_b64":"7Y5fb8ZqFAIUKUWDpLt5VKcXDXow2V35jvVPydHhKOTixW/b9YDb611kVlsfayXmCFQLuU26/ZMdV+UvL7EDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a509b1a00623cad22b7b2646b979f992d4f30102d5c71e757c82bcfa027884c","last_reissued_at":"2026-07-05T10:25:14.830280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:14.830280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haifeng Xia, Jingcheng Ni, Rui Chen, Siyu Xia, Yichen Liu, Yuxin Guo, Zehuan Wu","submitted_at":"2024-12-06T08:27:53Z","abstract_excerpt":"The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos remains a significant challenge. To address this, we present UniMLVG, a unified framework designed to generate extended street multi-perspective videos under precise control. By integrating single- and multi-view driving videos into the training data, our approach updates a DiT-based diffusion model equipped with cross-frame and cross-view modules across three sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04842","kind":"arxiv","version":3},"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/2412.04842/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":"2412.04842","created_at":"2026-07-05T10:25:14.830348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04842v3","created_at":"2026-07-05T10:25:14.830348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04842","created_at":"2026-07-05T10:25:14.830348+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJIJWGQAMI6K","created_at":"2026-07-05T10:25:14.830348+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJIJWGQAMI6K2IVX","created_at":"2026-07-05T10:25:14.830348+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJIJWGQA","created_at":"2026-07-05T10:25:14.830348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06516","citing_title":"Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17536","citing_title":"OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26113","citing_title":"AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.20523","citing_title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18993","citing_title":"AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE","json":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE.json","graph_json":"https://pith.science/api/pith-number/DJIJWGQAMI6K2IVXWJSGXF47TE/graph.json","events_json":"https://pith.science/api/pith-number/DJIJWGQAMI6K2IVXWJSGXF47TE/events.json","paper":"https://pith.science/paper/DJIJWGQA"},"agent_actions":{"view_html":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE","download_json":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE.json","view_paper":"https://pith.science/paper/DJIJWGQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04842&json=true","fetch_graph":"https://pith.science/api/pith-number/DJIJWGQAMI6K2IVXWJSGXF47TE/graph.json","fetch_events":"https://pith.science/api/pith-number/DJIJWGQAMI6K2IVXWJSGXF47TE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE/action/storage_attestation","attest_author":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE/action/author_attestation","sign_citation":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE/action/citation_signature","submit_replication":"https://pith.science/pith/DJIJWGQAMI6K2IVXWJSGXF47TE/action/replication_record"}},"created_at":"2026-07-05T10:25:14.830348+00:00","updated_at":"2026-07-05T10:25:14.830348+00:00"}