{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7C6EF6QQTSLWIHKKF63TFNZ34U","short_pith_number":"pith:7C6EF6QQ","schema_version":"1.0","canonical_sha256":"f8bc42fa109c97641d4a2fb732b73be50a12fe93ce39c243bfc1e0f532d2ca80","source":{"kind":"arxiv","id":"2406.01349","version":3},"attestation_state":"computed","paper":{"title":"Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Lin, Dong Han, Enhui Ma, Haiyang Sun, Junpeng Jiang, Kaicheng Yu, Kun Zhan, Lijun Zhou, Peng Jia, Tao Tang, Xianpeng Lang, Zhan Zhang","submitted_at":"2024-06-03T14:13:13Z","abstract_excerpt":"Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spa"},"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":"2406.01349","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T14:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"07a59fe513c4395af7e6d1ae0995bafffe1f6c194e685941eb931fb963364845","abstract_canon_sha256":"6a09c41566e3488cb64d8062ee80e6a7be0f73502fbae6b0a836616478af009d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:27.596360Z","signature_b64":"7r5Uba/4QZQsJdzweUVje7PQ+FPFmKIBFQpVl5xqGIy/DTt0IUCMWZp+Qt0YA2JvEm88XxQfRcthGbhbayDxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8bc42fa109c97641d4a2fb732b73be50a12fe93ce39c243bfc1e0f532d2ca80","last_reissued_at":"2026-07-05T08:28:27.595893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:27.595893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Lin, Dong Han, Enhui Ma, Haiyang Sun, Junpeng Jiang, Kaicheng Yu, Kun Zhan, Lijun Zhou, Peng Jia, Tao Tang, Xianpeng Lang, Zhan Zhang","submitted_at":"2024-06-03T14:13:13Z","abstract_excerpt":"Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01349","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/2406.01349/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":"2406.01349","created_at":"2026-07-05T08:28:27.595950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01349v3","created_at":"2026-07-05T08:28:27.595950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01349","created_at":"2026-07-05T08:28:27.595950+00:00"},{"alias_kind":"pith_short_12","alias_value":"7C6EF6QQTSLW","created_at":"2026-07-05T08:28:27.595950+00:00"},{"alias_kind":"pith_short_16","alias_value":"7C6EF6QQTSLWIHKK","created_at":"2026-07-05T08:28:27.595950+00:00"},{"alias_kind":"pith_short_8","alias_value":"7C6EF6QQ","created_at":"2026-07-05T08:28:27.595950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"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":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21372","citing_title":"Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07661","citing_title":"Optimization-Guided Diffusion for Interactive Scene Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":53,"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":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28196","citing_title":"HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25329","citing_title":"ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U","json":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U.json","graph_json":"https://pith.science/api/pith-number/7C6EF6QQTSLWIHKKF63TFNZ34U/graph.json","events_json":"https://pith.science/api/pith-number/7C6EF6QQTSLWIHKKF63TFNZ34U/events.json","paper":"https://pith.science/paper/7C6EF6QQ"},"agent_actions":{"view_html":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U","download_json":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U.json","view_paper":"https://pith.science/paper/7C6EF6QQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01349&json=true","fetch_graph":"https://pith.science/api/pith-number/7C6EF6QQTSLWIHKKF63TFNZ34U/graph.json","fetch_events":"https://pith.science/api/pith-number/7C6EF6QQTSLWIHKKF63TFNZ34U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U/action/storage_attestation","attest_author":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U/action/author_attestation","sign_citation":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U/action/citation_signature","submit_replication":"https://pith.science/pith/7C6EF6QQTSLWIHKKF63TFNZ34U/action/replication_record"}},"created_at":"2026-07-05T08:28:27.595950+00:00","updated_at":"2026-07-05T08:28:27.595950+00:00"}