{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHUAFX7VT46T2YQCMWHY2MZNR4","short_pith_number":"pith:NHUAFX7V","schema_version":"1.0","canonical_sha256":"69e802dff59f3d3d6202658f8d332d8f1d5d84ef14f3e8451652bd05301c1009","source":{"kind":"arxiv","id":"2405.04390","version":1},"attestation_state":"computed","paper":{"title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Dai, Chen Min, Dawei Zhao, Jianshu Li, Jian Zhao, Junliang Xing, Lei Jin, Liang Xiao, Liping Jing, Xinli Xu, Yiming Nie, Yulan Guo, Zheng Zhu","submitted_at":"2024-05-07T15:14:20Z","abstract_excerpt":"Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or 3D pre-text tasks, overlooking the temporal characteristics of autonomous driving as a 4D scene understanding task. In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \\emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal"},"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":"2405.04390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T15:14:20Z","cross_cats_sorted":[],"title_canon_sha256":"8a3221fcc769974472aab1738cd92633b692f304ea0893d9638b75b18b8b676c","abstract_canon_sha256":"73d81eb45ed14539f84b980e4964a3061352a841fe3b1fac3d256cecc2ff0119"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:36.562349Z","signature_b64":"yAwWCdbkFXHADunzMQOnjDgThnm4BfEoLEqvx44AtBEpOJ0RWS8tAse/yw8EWgrFId6Wf7cK8J8OJ3D2ep+7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69e802dff59f3d3d6202658f8d332d8f1d5d84ef14f3e8451652bd05301c1009","last_reissued_at":"2026-07-05T08:16:36.561854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:36.561854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Dai, Chen Min, Dawei Zhao, Jianshu Li, Jian Zhao, Junliang Xing, Lei Jin, Liang Xiao, Liping Jing, Xinli Xu, Yiming Nie, Yulan Guo, Zheng Zhu","submitted_at":"2024-05-07T15:14:20Z","abstract_excerpt":"Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or 3D pre-text tasks, overlooking the temporal characteristics of autonomous driving as a 4D scene understanding task. In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \\emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04390","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/2405.04390/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":"2405.04390","created_at":"2026-07-05T08:16:36.561913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04390v1","created_at":"2026-07-05T08:16:36.561913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04390","created_at":"2026-07-05T08:16:36.561913+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHUAFX7VT46T","created_at":"2026-07-05T08:16:36.561913+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHUAFX7VT46T2YQC","created_at":"2026-07-05T08:16:36.561913+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHUAFX7V","created_at":"2026-07-05T08:16:36.561913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12987","citing_title":"Diffusion Transformer World-Action Model for AV Scene Prediction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08481","citing_title":"Enhancing End-to-End Autonomous Driving with Latent World Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4","json":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4.json","graph_json":"https://pith.science/api/pith-number/NHUAFX7VT46T2YQCMWHY2MZNR4/graph.json","events_json":"https://pith.science/api/pith-number/NHUAFX7VT46T2YQCMWHY2MZNR4/events.json","paper":"https://pith.science/paper/NHUAFX7V"},"agent_actions":{"view_html":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4","download_json":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4.json","view_paper":"https://pith.science/paper/NHUAFX7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04390&json=true","fetch_graph":"https://pith.science/api/pith-number/NHUAFX7VT46T2YQCMWHY2MZNR4/graph.json","fetch_events":"https://pith.science/api/pith-number/NHUAFX7VT46T2YQCMWHY2MZNR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4/action/storage_attestation","attest_author":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4/action/author_attestation","sign_citation":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4/action/citation_signature","submit_replication":"https://pith.science/pith/NHUAFX7VT46T2YQCMWHY2MZNR4/action/replication_record"}},"created_at":"2026-07-05T08:16:36.561913+00:00","updated_at":"2026-07-05T08:16:36.561913+00:00"}