{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:77RSEJIDSQIGXODDLTM7O6225V","short_pith_number":"pith:77RSEJID","schema_version":"1.0","canonical_sha256":"ffe322250394106bb8635cd9f77b5aed63906e75c29c957ca93f2594f27867e3","source":{"kind":"arxiv","id":"2412.01407","version":2},"attestation_state":"computed","paper":{"title":"HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Jingcheng Ni, Lewei Lu, Rui Chen, Xiaodong Wang, Yuwen Xiong, Yuxin Guo, Zehuan Wu","submitted_at":"2024-12-02T11:50:35Z","abstract_excerpt":"Generative models have significantly improved the generation and prediction quality on either camera images or LiDAR point clouds for autonomous driving. However, a real-world autonomous driving system uses multiple kinds of input modality, usually cameras and LiDARs, where they contain complementary information for generation, while existing generation methods ignore this crucial feature, resulting in the generated results only covering separate 2D or 3D information. In order to fill the gap in 2D-3D multi-modal joint generation for autonomous driving, in this paper, we propose our framework,"},"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":"2412.01407","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T11:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"7c9a5a1433bf20230ee44b2624e59d83af2b9b10dcf0d48f2752e3a927800864","abstract_canon_sha256":"6ef15c89b86de4918960edfed79f3e8c5d18888cdf40c79bdc2f6668baf15ca1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:38.793336Z","signature_b64":"qLWHIay5EZQE7rMzW8w6l9/Wbevyq/mtmlZrZbTCQjQ7hbr+Mq6tPtgGWxpfzoP9sTQjn72+cZlbK+0FM3n6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe322250394106bb8635cd9f77b5aed63906e75c29c957ca93f2594f27867e3","last_reissued_at":"2026-07-05T09:43:38.792846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:38.792846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Jingcheng Ni, Lewei Lu, Rui Chen, Xiaodong Wang, Yuwen Xiong, Yuxin Guo, Zehuan Wu","submitted_at":"2024-12-02T11:50:35Z","abstract_excerpt":"Generative models have significantly improved the generation and prediction quality on either camera images or LiDAR point clouds for autonomous driving. However, a real-world autonomous driving system uses multiple kinds of input modality, usually cameras and LiDARs, where they contain complementary information for generation, while existing generation methods ignore this crucial feature, resulting in the generated results only covering separate 2D or 3D information. In order to fill the gap in 2D-3D multi-modal joint generation for autonomous driving, in this paper, we propose our framework,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01407","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/2412.01407/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":"2412.01407","created_at":"2026-07-05T09:43:38.792901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01407v2","created_at":"2026-07-05T09:43:38.792901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01407","created_at":"2026-07-05T09:43:38.792901+00:00"},{"alias_kind":"pith_short_12","alias_value":"77RSEJIDSQIG","created_at":"2026-07-05T09:43:38.792901+00:00"},{"alias_kind":"pith_short_16","alias_value":"77RSEJIDSQIGXODD","created_at":"2026-07-05T09:43:38.792901+00:00"},{"alias_kind":"pith_short_8","alias_value":"77RSEJID","created_at":"2026-07-05T09:43:38.792901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.20654","citing_title":"AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18576","citing_title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V","json":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V.json","graph_json":"https://pith.science/api/pith-number/77RSEJIDSQIGXODDLTM7O6225V/graph.json","events_json":"https://pith.science/api/pith-number/77RSEJIDSQIGXODDLTM7O6225V/events.json","paper":"https://pith.science/paper/77RSEJID"},"agent_actions":{"view_html":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V","download_json":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V.json","view_paper":"https://pith.science/paper/77RSEJID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01407&json=true","fetch_graph":"https://pith.science/api/pith-number/77RSEJIDSQIGXODDLTM7O6225V/graph.json","fetch_events":"https://pith.science/api/pith-number/77RSEJIDSQIGXODDLTM7O6225V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V/action/storage_attestation","attest_author":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V/action/author_attestation","sign_citation":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V/action/citation_signature","submit_replication":"https://pith.science/pith/77RSEJIDSQIGXODDLTM7O6225V/action/replication_record"}},"created_at":"2026-07-05T09:43:38.792901+00:00","updated_at":"2026-07-05T09:43:38.792901+00:00"}