{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EZVIDK23DYWNFK4PQDY5U6IEHD","short_pith_number":"pith:EZVIDK23","schema_version":"1.0","canonical_sha256":"266a81ab5b1e2cd2ab8f80f1da790438e18d0d929a31de9feceebe014e8069fa","source":{"kind":"arxiv","id":"2412.03520","version":2},"attestation_state":"computed","paper":{"title":"Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hannan Lu, Ji Tao, Junyu Han, Shudong Wang, Wangmeng Zuo, Xiameng Qin, Xiaohe Wu, Xinyu Zhang","submitted_at":"2024-12-04T18:02:49Z","abstract_excerpt":"Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial, temporal, and view dimensions. However, these approaches often struggle to maintain consistency across dimensions, particularly when handling fast-moving objects that appear at different times and viewpoints. In this paper, we present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverage"},"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":"2412.03520","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:02:49Z","cross_cats_sorted":[],"title_canon_sha256":"46b5e28f15b8ebac32eade39d318289c00878db0ed0439be065b1f82e31b700b","abstract_canon_sha256":"ed9b5c15af0f30cd25f6368829bd916dcc9588d9e9e312173980eb65809ec6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:59.956073Z","signature_b64":"3wXbPSTlJaN449FG1Ca07CJNYN57iJV4Jgug91dM6tAYiKSszDG6hU+7OkoW2t+GzieOYjgpy/3ZlU/rrE5kDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"266a81ab5b1e2cd2ab8f80f1da790438e18d0d929a31de9feceebe014e8069fa","last_reissued_at":"2026-07-05T09:45:59.955579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:59.955579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hannan Lu, Ji Tao, Junyu Han, Shudong Wang, Wangmeng Zuo, Xiameng Qin, Xiaohe Wu, Xinyu Zhang","submitted_at":"2024-12-04T18:02:49Z","abstract_excerpt":"Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial, temporal, and view dimensions. However, these approaches often struggle to maintain consistency across dimensions, particularly when handling fast-moving objects that appear at different times and viewpoints. In this paper, we present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03520","kind":"arxiv","version":2},"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/2412.03520/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":"2412.03520","created_at":"2026-07-05T09:45:59.955643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03520v2","created_at":"2026-07-05T09:45:59.955643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03520","created_at":"2026-07-05T09:45:59.955643+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZVIDK23DYWN","created_at":"2026-07-05T09:45:59.955643+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZVIDK23DYWNFK4P","created_at":"2026-07-05T09:45:59.955643+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZVIDK23","created_at":"2026-07-05T09:45:59.955643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20110","citing_title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26113","citing_title":"AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD","json":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD.json","graph_json":"https://pith.science/api/pith-number/EZVIDK23DYWNFK4PQDY5U6IEHD/graph.json","events_json":"https://pith.science/api/pith-number/EZVIDK23DYWNFK4PQDY5U6IEHD/events.json","paper":"https://pith.science/paper/EZVIDK23"},"agent_actions":{"view_html":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD","download_json":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD.json","view_paper":"https://pith.science/paper/EZVIDK23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03520&json=true","fetch_graph":"https://pith.science/api/pith-number/EZVIDK23DYWNFK4PQDY5U6IEHD/graph.json","fetch_events":"https://pith.science/api/pith-number/EZVIDK23DYWNFK4PQDY5U6IEHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD/action/storage_attestation","attest_author":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD/action/author_attestation","sign_citation":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD/action/citation_signature","submit_replication":"https://pith.science/pith/EZVIDK23DYWNFK4PQDY5U6IEHD/action/replication_record"}},"created_at":"2026-07-05T09:45:59.955643+00:00","updated_at":"2026-07-05T09:45:59.955643+00:00"}