{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WNQIGGOEWLGO4ROGQPKP2M4KSA","short_pith_number":"pith:WNQIGGOE","schema_version":"1.0","canonical_sha256":"b3608319c4b2ccee45c683d4fd338a9018060c97ce83857a90b233223efbf354","source":{"kind":"arxiv","id":"2311.01017","version":4},"attestation_state":"computed","paper":{"title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Lunjun Zhang, Raquel Urtasun, Rui Hu, Sergio Casas, Yuwen Xiong, Ze Yang","submitted_at":"2023-11-02T06:21:56Z","abstract_excerpt":"Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous driving has been somewhat less rapid than scaling language models with Generative Pre-trained Transformers (GPT). We identify two reasons as major bottlenecks: dealing with complex and unstructured observation space, and having a scalable generative model. Consequently, we propose Copilot4D, a novel world modeling approach that first tokenizes sensor observations "},"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":"2311.01017","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T06:21:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"2213e6f99c2c6e36b052342e5a0ac3b675304780c05defe7fd29e76aae319d6d","abstract_canon_sha256":"ced79e467416c6882bee0e927f5768e3ab8dbb5fd80c7ab4e88a878205bbd99d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:47.427686Z","signature_b64":"etaKt7OQAgsGks22wRVc9G2BcCIvTFKUGOhGdevvgCltNTYiikgm16PdfmbxjX7t6xyFRvf1aI033jVWccsGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3608319c4b2ccee45c683d4fd338a9018060c97ce83857a90b233223efbf354","last_reissued_at":"2026-07-05T08:02:47.427236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:47.427236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Lunjun Zhang, Raquel Urtasun, Rui Hu, Sergio Casas, Yuwen Xiong, Ze Yang","submitted_at":"2023-11-02T06:21:56Z","abstract_excerpt":"Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous driving has been somewhat less rapid than scaling language models with Generative Pre-trained Transformers (GPT). We identify two reasons as major bottlenecks: dealing with complex and unstructured observation space, and having a scalable generative model. Consequently, we propose Copilot4D, a novel world modeling approach that first tokenizes sensor observations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01017","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/2311.01017/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":"2311.01017","created_at":"2026-07-05T08:02:47.427290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01017v4","created_at":"2026-07-05T08:02:47.427290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01017","created_at":"2026-07-05T08:02:47.427290+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNQIGGOEWLGO","created_at":"2026-07-05T08:02:47.427290+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNQIGGOEWLGO4ROG","created_at":"2026-07-05T08:02:47.427290+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNQIGGOE","created_at":"2026-07-05T08:02:47.427290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31314","citing_title":"AR Forcing: Towards Long-Horizon Robot Navigation World Model","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24354","citing_title":"SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15925","citing_title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08481","citing_title":"Enhancing End-to-End Autonomous Driving with Latent World Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12796","citing_title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23262","citing_title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","ref_index":219,"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":57,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12857","citing_title":"Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":220,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA","json":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA.json","graph_json":"https://pith.science/api/pith-number/WNQIGGOEWLGO4ROGQPKP2M4KSA/graph.json","events_json":"https://pith.science/api/pith-number/WNQIGGOEWLGO4ROGQPKP2M4KSA/events.json","paper":"https://pith.science/paper/WNQIGGOE"},"agent_actions":{"view_html":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA","download_json":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA.json","view_paper":"https://pith.science/paper/WNQIGGOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01017&json=true","fetch_graph":"https://pith.science/api/pith-number/WNQIGGOEWLGO4ROGQPKP2M4KSA/graph.json","fetch_events":"https://pith.science/api/pith-number/WNQIGGOEWLGO4ROGQPKP2M4KSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA/action/storage_attestation","attest_author":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA/action/author_attestation","sign_citation":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA/action/citation_signature","submit_replication":"https://pith.science/pith/WNQIGGOEWLGO4ROGQPKP2M4KSA/action/replication_record"}},"created_at":"2026-07-05T08:02:47.427290+00:00","updated_at":"2026-07-05T08:02:47.427290+00:00"}