{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7DS6TEBOUDI5YDK5BNEM5WPYOF","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":"3167398f99c123852e61a8f0463a657f07a5da0b38cf8d575f18212413c90e1e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T18:56:02Z","title_canon_sha256":"252affcc5a8f8486a399891d938d308cdb69c73adaa274e81d9fe28d4df7aa15"},"schema_version":"1.0","source":{"id":"2502.15672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15672","created_at":"2026-07-05T10:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15672v1","created_at":"2026-07-05T10:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15672","created_at":"2026-07-05T10:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"7DS6TEBOUDI5","created_at":"2026-07-05T10:18:05Z"},{"alias_kind":"pith_short_16","alias_value":"7DS6TEBOUDI5YDK5","created_at":"2026-07-05T10:18:05Z"},{"alias_kind":"pith_short_8","alias_value":"7DS6TEBO","created_at":"2026-07-05T10:18:05Z"}],"graph_snapshots":[{"event_id":"sha256:6291a0b3e3fb412e394aa24d5fee2e05e51498a9f86846e1ef7b8f6ea1558f42","target":"graph","created_at":"2026-07-05T10:18:05Z","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/2502.15672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training transfers to real-world driving. VaViM is a simple auto-regressive video model that predicts frames using spatio-temporal token sequences. We show that it captures the semantics and dynamics of driving scenes. VaVAM, the video-action model, leverages the learned representations of VaViM to generate driving trajectories through imitation learning. Together, the mod","authors_text":"Alexandre Boulch, Andrei Bursuc, David Hurych, Eduardo Valle, Elias Ramzi, \\'Eloi Zablocki, Florent Bartoccioni, Loick Chambon, Matthieu Cord, Mickael Chen, Renaud Marlet, Serkan Odabas, Shashanka Venkataramanan, Spyros Gidaris, Tuan-Hung Vu, Victor Besnier, Yihong Xu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T18:56:02Z","title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15672","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":"sha256:82336698f9fd9d4bc31823df7e06b098b9eb1c241785713e6d98396caf42dafc","target":"record","created_at":"2026-07-05T10:18:05Z","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":"3167398f99c123852e61a8f0463a657f07a5da0b38cf8d575f18212413c90e1e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T18:56:02Z","title_canon_sha256":"252affcc5a8f8486a399891d938d308cdb69c73adaa274e81d9fe28d4df7aa15"},"schema_version":"1.0","source":{"id":"2502.15672","kind":"arxiv","version":1}},"canonical_sha256":"f8e5e9902ea0d1dc0d5d0b48ced9f871534ff7349fa93898aa9bb664bc9abd99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8e5e9902ea0d1dc0d5d0b48ced9f871534ff7349fa93898aa9bb664bc9abd99","first_computed_at":"2026-07-05T10:18:05.507974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:05.507974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twnkOm8QGw/DG5ef4wxmYKi2ZMzhz9OIAtZuuetKRdTSfpP0RXHF74FvIb2DcTT/WvZMf6rjWBOU/fnwELa7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:05.508453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82336698f9fd9d4bc31823df7e06b098b9eb1c241785713e6d98396caf42dafc","sha256:6291a0b3e3fb412e394aa24d5fee2e05e51498a9f86846e1ef7b8f6ea1558f42"],"state_sha256":"2b5f35a9a8e5a74b4b33d59d5af067f7165af9acf0234431a3346bfdee84c675"}