{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XEPVC3JTPHCJKNYZBNTTKMVMQH","short_pith_number":"pith:XEPVC3JT","schema_version":"1.0","canonical_sha256":"b91f516d3379c49537190b673532ac81c629eeffb6580f42690401bc198f762a","source":{"kind":"arxiv","id":"2503.22231","version":2},"attestation_state":"computed","paper":{"title":"CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Haiyang Sun, Kaixin Xiong, Lijun Zhou, Ming Lu, Tong Lu, Yishen Ji, Zhenxin Zhu, Zhiqi Li, Ziyue Zhu","submitted_at":"2025-03-28T08:27:05Z","abstract_excerpt":"Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout conditions (e.g., HD maps and bounding boxes), can produce photorealistic driving videos, achieving controllable multi-view videos with high 3D consistency remains a major challenge. To tackle this, we introduce a novel spatial adaptive generation framework, CoGen, which leverages advances in 3D generation to improve performance in two key aspects: (i) To e"},"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":"2503.22231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T08:27:05Z","cross_cats_sorted":[],"title_canon_sha256":"b11da65d1e3bd347ac46fefa880ab559ed05fa8a0250255c6c3234730ebe4359","abstract_canon_sha256":"6d4a9c183e9797f97becafcd070b86541f8d52783b67261ac1b5b4daf7912183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:43.904798Z","signature_b64":"0+0T8xCei6bFiSto9mRs3+ON0GeKtlcbEDmKV1VknDhdsirTrQzxBwZWhrqOKA4Tu9JkFN/IFbCNUEoDCKPPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91f516d3379c49537190b673532ac81c629eeffb6580f42690401bc198f762a","last_reissued_at":"2026-07-05T10:44:43.904289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:43.904289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Haiyang Sun, Kaixin Xiong, Lijun Zhou, Ming Lu, Tong Lu, Yishen Ji, Zhenxin Zhu, Zhiqi Li, Ziyue Zhu","submitted_at":"2025-03-28T08:27:05Z","abstract_excerpt":"Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout conditions (e.g., HD maps and bounding boxes), can produce photorealistic driving videos, achieving controllable multi-view videos with high 3D consistency remains a major challenge. To tackle this, we introduce a novel spatial adaptive generation framework, CoGen, which leverages advances in 3D generation to improve performance in two key aspects: (i) To e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22231","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/2503.22231/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":"2503.22231","created_at":"2026-07-05T10:44:43.904356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22231v2","created_at":"2026-07-05T10:44:43.904356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22231","created_at":"2026-07-05T10:44:43.904356+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEPVC3JTPHCJ","created_at":"2026-07-05T10:44:43.904356+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEPVC3JTPHCJKNYZ","created_at":"2026-07-05T10:44:43.904356+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEPVC3JT","created_at":"2026-07-05T10:44:43.904356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":35,"is_internal_anchor":false},{"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08719","citing_title":"LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH","json":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH.json","graph_json":"https://pith.science/api/pith-number/XEPVC3JTPHCJKNYZBNTTKMVMQH/graph.json","events_json":"https://pith.science/api/pith-number/XEPVC3JTPHCJKNYZBNTTKMVMQH/events.json","paper":"https://pith.science/paper/XEPVC3JT"},"agent_actions":{"view_html":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH","download_json":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH.json","view_paper":"https://pith.science/paper/XEPVC3JT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22231&json=true","fetch_graph":"https://pith.science/api/pith-number/XEPVC3JTPHCJKNYZBNTTKMVMQH/graph.json","fetch_events":"https://pith.science/api/pith-number/XEPVC3JTPHCJKNYZBNTTKMVMQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH/action/storage_attestation","attest_author":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH/action/author_attestation","sign_citation":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH/action/citation_signature","submit_replication":"https://pith.science/pith/XEPVC3JTPHCJKNYZBNTTKMVMQH/action/replication_record"}},"created_at":"2026-07-05T10:44:43.904356+00:00","updated_at":"2026-07-05T10:44:43.904356+00:00"}