{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2IAUZRHSDXJRC42A5N3K6KPJWN","short_pith_number":"pith:2IAUZRHS","schema_version":"1.0","canonical_sha256":"d2014cc4f21dd3117340eb76af29e9b372b990aa4e22be8420bbdd7e8da7d25e","source":{"kind":"arxiv","id":"2412.09627","version":1},"attestation_state":"computed","paper":{"title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Zetian Xia","submitted_at":"2024-12-12T18:59:59Z","abstract_excerpt":"End-to-end autonomous driving has received increasing attention due to its potential to learn from large amounts of data. However, most existing methods are still open-loop and suffer from weak scalability, lack of high-order interactions, and inefficient decision-making. In this paper, we explore a closed-loop framework for autonomous driving and propose a large Driving wOrld modEl (Doe-1) for unified perception, prediction, and planning. We formulate autonomous driving as a next-token generation problem and use multi-modal tokens to accomplish different tasks. Specifically, we use free-form "},"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":"2412.09627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8a315858791f1e62960e8a51ae7cf33c4036d99ef5dff9096ae51b5556848435","abstract_canon_sha256":"8a97ece060c536e063827fcdbc102e55d30fe6dea84ce2ef3e3db26378d2637e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:27.542207Z","signature_b64":"dvO08jEVwA2IOyZWdGTkFEFCpHDKJ1mpn7v2bUHZgc+VBTWMimxj7/RLZhnZ9mQNsBbIHouXrhjRsfxJcLoZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2014cc4f21dd3117340eb76af29e9b372b990aa4e22be8420bbdd7e8da7d25e","last_reissued_at":"2026-07-05T09:48:27.541714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:27.541714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Zetian Xia","submitted_at":"2024-12-12T18:59:59Z","abstract_excerpt":"End-to-end autonomous driving has received increasing attention due to its potential to learn from large amounts of data. However, most existing methods are still open-loop and suffer from weak scalability, lack of high-order interactions, and inefficient decision-making. In this paper, we explore a closed-loop framework for autonomous driving and propose a large Driving wOrld modEl (Doe-1) for unified perception, prediction, and planning. We formulate autonomous driving as a next-token generation problem and use multi-modal tokens to accomplish different tasks. Specifically, we use free-form "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09627","kind":"arxiv","version":1},"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/2412.09627/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":"2412.09627","created_at":"2026-07-05T09:48:27.541774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09627v1","created_at":"2026-07-05T09:48:27.541774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09627","created_at":"2026-07-05T09:48:27.541774+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IAUZRHSDXJR","created_at":"2026-07-05T09:48:27.541774+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IAUZRHSDXJRC42A","created_at":"2026-07-05T09:48:27.541774+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IAUZRHS","created_at":"2026-07-05T09:48:27.541774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27038","citing_title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22089","citing_title":"LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12796","citing_title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17685","citing_title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28196","citing_title":"HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09059","citing_title":"Learning Vision-Language-Action World Models for Autonomous Driving","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":229,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN","json":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN.json","graph_json":"https://pith.science/api/pith-number/2IAUZRHSDXJRC42A5N3K6KPJWN/graph.json","events_json":"https://pith.science/api/pith-number/2IAUZRHSDXJRC42A5N3K6KPJWN/events.json","paper":"https://pith.science/paper/2IAUZRHS"},"agent_actions":{"view_html":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN","download_json":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN.json","view_paper":"https://pith.science/paper/2IAUZRHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09627&json=true","fetch_graph":"https://pith.science/api/pith-number/2IAUZRHSDXJRC42A5N3K6KPJWN/graph.json","fetch_events":"https://pith.science/api/pith-number/2IAUZRHSDXJRC42A5N3K6KPJWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN/action/storage_attestation","attest_author":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN/action/author_attestation","sign_citation":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN/action/citation_signature","submit_replication":"https://pith.science/pith/2IAUZRHSDXJRC42A5N3K6KPJWN/action/replication_record"}},"created_at":"2026-07-05T09:48:27.541774+00:00","updated_at":"2026-07-05T09:48:27.541774+00:00"}