{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5K2ADKD3MBKDXOIO6D6WXE6P63","short_pith_number":"pith:5K2ADKD3","schema_version":"1.0","canonical_sha256":"eab401a87b60543bb90ef0fd6b93cff6c468aaa30745326219c97c9c9e7bea2b","source":{"kind":"arxiv","id":"2506.07497","version":4},"attestation_state":"computed","paper":{"title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Gangwei Xu, Guang Chen, Haiyang Sun, Hangjun Ye, Kaixin Xiong, Lijun Zhou, Shaoqing Xu, Wenyu Liu, Xiangyu Guo, Xinggang Wang, Zhanqian Wu, Ziyang Xu","submitted_at":"2025-06-09T07:20:49Z","abstract_excerpt":"We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-"},"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":"2506.07497","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:20:49Z","cross_cats_sorted":[],"title_canon_sha256":"323d1af4cd2311376ac52eb05ba889bdfea1b41722f24adad67cdb55d425195a","abstract_canon_sha256":"0fc1e2cdf7b4607c8d00b637df6cd1fc4cba1a8622eb030e62f7b7d12e67198c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:53.418114Z","signature_b64":"0RDR+KiMFxfVA8MyVTwfe8mNPd6q2KjP0bYiw0eD4t+TtmX6Csk4OlKkSPMm4tbtAKc7NTNQNVtjGF6qbDKVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eab401a87b60543bb90ef0fd6b93cff6c468aaa30745326219c97c9c9e7bea2b","last_reissued_at":"2026-07-05T11:24:53.417622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:53.417622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Gangwei Xu, Guang Chen, Haiyang Sun, Hangjun Ye, Kaixin Xiong, Lijun Zhou, Shaoqing Xu, Wenyu Liu, Xiangyu Guo, Xinggang Wang, Zhanqian Wu, Ziyang Xu","submitted_at":"2025-06-09T07:20:49Z","abstract_excerpt":"We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07497","kind":"arxiv","version":4},"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/2506.07497/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":"2506.07497","created_at":"2026-07-05T11:24:53.417682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07497v4","created_at":"2026-07-05T11:24:53.417682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07497","created_at":"2026-07-05T11:24:53.417682+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K2ADKD3MBKD","created_at":"2026-07-05T11:24:53.417682+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K2ADKD3MBKDXOIO","created_at":"2026-07-05T11:24:53.417682+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K2ADKD3","created_at":"2026-07-05T11:24:53.417682+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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27504","citing_title":"ReWorld: Learning Better Representations for World Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10426","citing_title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10426","citing_title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15805","citing_title":"From Seeing to Simulating: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63","json":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63.json","graph_json":"https://pith.science/api/pith-number/5K2ADKD3MBKDXOIO6D6WXE6P63/graph.json","events_json":"https://pith.science/api/pith-number/5K2ADKD3MBKDXOIO6D6WXE6P63/events.json","paper":"https://pith.science/paper/5K2ADKD3"},"agent_actions":{"view_html":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63","download_json":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63.json","view_paper":"https://pith.science/paper/5K2ADKD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07497&json=true","fetch_graph":"https://pith.science/api/pith-number/5K2ADKD3MBKDXOIO6D6WXE6P63/graph.json","fetch_events":"https://pith.science/api/pith-number/5K2ADKD3MBKDXOIO6D6WXE6P63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63/action/storage_attestation","attest_author":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63/action/author_attestation","sign_citation":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63/action/citation_signature","submit_replication":"https://pith.science/pith/5K2ADKD3MBKDXOIO6D6WXE6P63/action/replication_record"}},"created_at":"2026-07-05T11:24:53.417682+00:00","updated_at":"2026-07-05T11:24:53.417682+00:00"}