{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ACEYQLKAEHAGMPFWCX6MUMC5L","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":"b38653c3378cf9ed6b14d5551e6e4d567130aff050c2b10eea8d8f8870c139f6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T16:50:02Z","title_canon_sha256":"afa4e50a0d2618ba4a7b947b09c84e8fb2d2cd95448649bee119ba0bfacb70e5"},"schema_version":"1.0","source":{"id":"2506.24044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.24044","created_at":"2026-07-05T11:29:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.24044v1","created_at":"2026-07-05T11:29:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24044","created_at":"2026-07-05T11:29:32Z"},{"alias_kind":"pith_short_12","alias_value":"2ACEYQLKAEHA","created_at":"2026-07-05T11:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"2ACEYQLKAEHAGMPF","created_at":"2026-07-05T11:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"2ACEYQLK","created_at":"2026-07-05T11:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:9743429b745462b6edaf918b2baf6305d0475385b5c5d3cb8d4976af45e89c03","target":"graph","created_at":"2026-07-05T11:29:32Z","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/2506.24044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA f","authors_text":"Diange Yang, Hao Ye, Kangan Qian, Kun Jiang, Lijun Sun, Menglin Kong, SeongJin Choi, Sicong Jiang, Sikai Chen, Siwen Jiao, Tianze Zhu, Tuopu Wen, Xin Zhao, Yang Zhong, Yihong Tang, Yunlong Wang, Zheng Fu, Ziang Luo, Zihao Sheng, Zilin Huang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T16:50:02Z","title":"A Survey on Vision-Language-Action Models for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24044","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:bf1442ddbea435c223aa1c44adebaa79cf36821622895ddcfacff315be61c59b","target":"record","created_at":"2026-07-05T11:29:32Z","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":"b38653c3378cf9ed6b14d5551e6e4d567130aff050c2b10eea8d8f8870c139f6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T16:50:02Z","title_canon_sha256":"afa4e50a0d2618ba4a7b947b09c84e8fb2d2cd95448649bee119ba0bfacb70e5"},"schema_version":"1.0","source":{"id":"2506.24044","kind":"arxiv","version":1}},"canonical_sha256":"d0044c416a010e0331e5b0afe65182eae384af0299b196ca7b23183e2bb05b4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0044c416a010e0331e5b0afe65182eae384af0299b196ca7b23183e2bb05b4c","first_computed_at":"2026-07-05T11:29:32.273340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:32.273340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNPWzZOEEe31m+R9fnFvhKYuMubH8ZJp8gRx0CD7y8SUJz4SuI+x8gNSyTUZ+UNMRvdI99iz+XCfVFhEgj25AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:32.273881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.24044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf1442ddbea435c223aa1c44adebaa79cf36821622895ddcfacff315be61c59b","sha256:9743429b745462b6edaf918b2baf6305d0475385b5c5d3cb8d4976af45e89c03"],"state_sha256":"7708342a412e2b8c34d58f69c07f07120019bdb5ed1d3cc3952de394399a2074"}