{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NHUAFX7VT46T2YQCMWHY2MZNR4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"73d81eb45ed14539f84b980e4964a3061352a841fe3b1fac3d256cecc2ff0119","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T15:14:20Z","title_canon_sha256":"8a3221fcc769974472aab1738cd92633b692f304ea0893d9638b75b18b8b676c"},"schema_version":"1.0","source":{"id":"2405.04390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04390","created_at":"2026-07-05T08:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04390v1","created_at":"2026-07-05T08:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04390","created_at":"2026-07-05T08:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"NHUAFX7VT46T","created_at":"2026-07-05T08:16:36Z"},{"alias_kind":"pith_short_16","alias_value":"NHUAFX7VT46T2YQC","created_at":"2026-07-05T08:16:36Z"},{"alias_kind":"pith_short_8","alias_value":"NHUAFX7V","created_at":"2026-07-05T08:16:36Z"}],"graph_snapshots":[{"event_id":"sha256:7ffc524afaa184c57ea54aa4c8b966b7ef5de468d389df15445e323d8255d996","target":"graph","created_at":"2026-07-05T08:16:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.04390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T15:14:20Z","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04390","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0033d3f417aa2be9c6576724e69e824344a7ce218fc4bce9793bba84d98445f2","target":"record","created_at":"2026-07-05T08:16:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"73d81eb45ed14539f84b980e4964a3061352a841fe3b1fac3d256cecc2ff0119","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T15:14:20Z","title_canon_sha256":"8a3221fcc769974472aab1738cd92633b692f304ea0893d9638b75b18b8b676c"},"schema_version":"1.0","source":{"id":"2405.04390","kind":"arxiv","version":1}},"canonical_sha256":"69e802dff59f3d3d6202658f8d332d8f1d5d84ef14f3e8451652bd05301c1009","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69e802dff59f3d3d6202658f8d332d8f1d5d84ef14f3e8451652bd05301c1009","first_computed_at":"2026-07-05T08:16:36.561854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:36.561854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yAwWCdbkFXHADunzMQOnjDgThnm4BfEoLEqvx44AtBEpOJ0RWS8tAse/yw8EWgrFId6Wf7cK8J8OJ3D2ep+7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:36.562349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0033d3f417aa2be9c6576724e69e824344a7ce218fc4bce9793bba84d98445f2","sha256:7ffc524afaa184c57ea54aa4c8b966b7ef5de468d389df15445e323d8255d996"],"state_sha256":"02be13a76e3a369714f16985e80047a6c99c255a916760348200c630da51305a"}