{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YQE564U47ZM7F75VT2D22KGGX2","short_pith_number":"pith:YQE564U4","schema_version":"1.0","canonical_sha256":"c409df729cfe59f2ffb59e87ad28c6be8a77029ecd5e73a0a157fd866f2f7ab4","source":{"kind":"arxiv","id":"2501.11260","version":4},"attestation_state":"computed","paper":{"title":"A Survey of World Models for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Tuo Feng, Wenguan Wang, Yi Yang","submitted_at":"2025-01-20T04:00:02Z","abstract_excerpt":"Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin technology, offering high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics. This paper systematically reviews recent advances in world models for autonomous driving, proposing a three-tiered taxonomy: (i) Generation of Future Physical World, covering Image-, BEV-, OG-, and PC-based gen"},"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":"2501.11260","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-01-20T04:00:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1dc58666a850f76e29b8345bc88ecf6779d73b5d8fd2ab12449cd5f310de6eb5","abstract_canon_sha256":"ebb3c70bb4cd4b782f9a1abcd459d607662a893ab7bd2607d364a467eb2b1c6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:57.744122Z","signature_b64":"7N28DnF4BO4WxlsWw2+NLdcmWek3lhge14KBBj/MH7mrwO4V67YkbKfSFxbmz3viaP7YQDvu18jgn4oRpQzaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c409df729cfe59f2ffb59e87ad28c6be8a77029ecd5e73a0a157fd866f2f7ab4","last_reissued_at":"2026-07-05T12:07:57.743608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:57.743608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of World Models for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Tuo Feng, Wenguan Wang, Yi Yang","submitted_at":"2025-01-20T04:00:02Z","abstract_excerpt":"Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin technology, offering high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics. This paper systematically reviews recent advances in world models for autonomous driving, proposing a three-tiered taxonomy: (i) Generation of Future Physical World, covering Image-, BEV-, OG-, and PC-based gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11260","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/2501.11260/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":"2501.11260","created_at":"2026-07-05T12:07:57.743667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11260v4","created_at":"2026-07-05T12:07:57.743667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11260","created_at":"2026-07-05T12:07:57.743667+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQE564U47ZM7","created_at":"2026-07-05T12:07:57.743667+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQE564U47ZM7F75V","created_at":"2026-07-05T12:07:57.743667+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQE564U4","created_at":"2026-07-05T12:07:57.743667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21172","citing_title":"BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09803","citing_title":"Echo-Memory: A Controlled Study of Memory in Action World Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01935","citing_title":"Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28384","citing_title":"A Query-Driven Communication-Efficient Digital Twins Design for Autonomous Driving","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27038","citing_title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18208","citing_title":"Looped World Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22456","citing_title":"Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20540","citing_title":"Advancing Open-source World Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01346","citing_title":"Safety, Security, and Cognitive Risks in World Models","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02714","citing_title":"ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11550","citing_title":"The DAWN of World-Action Interactive Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09701","citing_title":"DriveFuture: Future-Aware Latent World Models for Autonomous Driving","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11707","citing_title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17651","citing_title":"Infrastructure-Centric World Models: Bridging Temporal Depth and Spatial Breadth for Roadside Perception","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2","json":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2.json","graph_json":"https://pith.science/api/pith-number/YQE564U47ZM7F75VT2D22KGGX2/graph.json","events_json":"https://pith.science/api/pith-number/YQE564U47ZM7F75VT2D22KGGX2/events.json","paper":"https://pith.science/paper/YQE564U4"},"agent_actions":{"view_html":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2","download_json":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2.json","view_paper":"https://pith.science/paper/YQE564U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11260&json=true","fetch_graph":"https://pith.science/api/pith-number/YQE564U47ZM7F75VT2D22KGGX2/graph.json","fetch_events":"https://pith.science/api/pith-number/YQE564U47ZM7F75VT2D22KGGX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2/action/storage_attestation","attest_author":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2/action/author_attestation","sign_citation":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2/action/citation_signature","submit_replication":"https://pith.science/pith/YQE564U47ZM7F75VT2D22KGGX2/action/replication_record"}},"created_at":"2026-07-05T12:07:57.743667+00:00","updated_at":"2026-07-05T12:07:57.743667+00:00"}