{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5K2ADKD3MBKDXOIO6D6WXE6P63","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0fc1e2cdf7b4607c8d00b637df6cd1fc4cba1a8622eb030e62f7b7d12e67198c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:20:49Z","title_canon_sha256":"323d1af4cd2311376ac52eb05ba889bdfea1b41722f24adad67cdb55d425195a"},"schema_version":"1.0","source":{"id":"2506.07497","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07497","created_at":"2026-07-05T11:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07497v4","created_at":"2026-07-05T11:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07497","created_at":"2026-07-05T11:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"5K2ADKD3MBKD","created_at":"2026-07-05T11:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"5K2ADKD3MBKDXOIO","created_at":"2026-07-05T11:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"5K2ADKD3","created_at":"2026-07-05T11:24:53Z"}],"graph_snapshots":[{"event_id":"sha256:d09c81110d68da16f364243a96ae479172b11ee7310cdc680358b0a55ea4ec1c","target":"graph","created_at":"2026-07-05T11:24:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:20:49Z","title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07497","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3731ab06b88e000dc697a3508b379fcbb8738b4937def0b2a84ffc976ad67953","target":"record","created_at":"2026-07-05T11:24:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0fc1e2cdf7b4607c8d00b637df6cd1fc4cba1a8622eb030e62f7b7d12e67198c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:20:49Z","title_canon_sha256":"323d1af4cd2311376ac52eb05ba889bdfea1b41722f24adad67cdb55d425195a"},"schema_version":"1.0","source":{"id":"2506.07497","kind":"arxiv","version":4}},"canonical_sha256":"eab401a87b60543bb90ef0fd6b93cff6c468aaa30745326219c97c9c9e7bea2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eab401a87b60543bb90ef0fd6b93cff6c468aaa30745326219c97c9c9e7bea2b","first_computed_at":"2026-07-05T11:24:53.417622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:53.417622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RDR+KiMFxfVA8MyVTwfe8mNPd6q2KjP0bYiw0eD4t+TtmX6Csk4OlKkSPMm4tbtAKc7NTNQNVtjGF6qbDKVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:53.418114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07497","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3731ab06b88e000dc697a3508b379fcbb8738b4937def0b2a84ffc976ad67953","sha256:d09c81110d68da16f364243a96ae479172b11ee7310cdc680358b0a55ea4ec1c"],"state_sha256":"69b4acc858d596cac72201076cc600bf05e61966c7cb250a64cf6a9b560c538e"}