{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHZWB4KLNJ5TRGOYT4M3FSUPX3","short_pith_number":"pith:NHZWB4KL","schema_version":"1.0","canonical_sha256":"69f360f14b6a7b3899d89f19b2ca8fbee94279d1b3f781ca9547fb0ea7a53877","source":{"kind":"arxiv","id":"2505.23757","version":1},"attestation_state":"computed","paper":{"title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyu Liu, Hang Zhao, Haohan Chi, Hao Sun, Hao Zhao, Huan-ang Gao, Jianing Liu, Jinwei Li, Kaisen Yang, Leichen Wang, Wenyi Li, Xingtao Hu, Yangcheng Yu, Zeda Wang, Ziming Liu","submitted_at":"2025-05-29T17:59:46Z","abstract_excerpt":"Vision-Language-Action (VLA) models for autonomous driving show promise but falter in unstructured corner case scenarios, largely due to a scarcity of targeted benchmarks. To address this, we introduce Impromptu VLA. Our core contribution is the Impromptu VLA Dataset: over 80,000 meticulously curated video clips, distilled from over 2M source clips sourced from 8 open-source large-scale datasets. This dataset is built upon our novel taxonomy of four challenging unstructured categories and features rich, planning-oriented question-answering annotations and action trajectories. Crucially, experi"},"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":"2505.23757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"1586b928e90ddf854c1503955c748ad4918b3f3cdea0de74c3ce47a2d10cead5","abstract_canon_sha256":"acf0e277b773bc198abd6c1d488845941bf292913c0efda93cf9a71ed817fa69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:13.758499Z","signature_b64":"BYYcOH/FZJqxDm/VdTi5i/iDWVRjoX3C//od63D4+JqwpTXfXKLD8mw+yjuK0IPumhzEEhBv9v+PIQq3w7BnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69f360f14b6a7b3899d89f19b2ca8fbee94279d1b3f781ca9547fb0ea7a53877","last_reissued_at":"2026-07-05T11:12:13.758003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:13.758003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyu Liu, Hang Zhao, Haohan Chi, Hao Sun, Hao Zhao, Huan-ang Gao, Jianing Liu, Jinwei Li, Kaisen Yang, Leichen Wang, Wenyi Li, Xingtao Hu, Yangcheng Yu, Zeda Wang, Ziming Liu","submitted_at":"2025-05-29T17:59:46Z","abstract_excerpt":"Vision-Language-Action (VLA) models for autonomous driving show promise but falter in unstructured corner case scenarios, largely due to a scarcity of targeted benchmarks. To address this, we introduce Impromptu VLA. Our core contribution is the Impromptu VLA Dataset: over 80,000 meticulously curated video clips, distilled from over 2M source clips sourced from 8 open-source large-scale datasets. This dataset is built upon our novel taxonomy of four challenging unstructured categories and features rich, planning-oriented question-answering annotations and action trajectories. Crucially, experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23757","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/2505.23757/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":"2505.23757","created_at":"2026-07-05T11:12:13.758059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23757v1","created_at":"2026-07-05T11:12:13.758059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23757","created_at":"2026-07-05T11:12:13.758059+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHZWB4KLNJ5T","created_at":"2026-07-05T11:12:13.758059+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHZWB4KLNJ5TRGOY","created_at":"2026-07-05T11:12:13.758059+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHZWB4KL","created_at":"2026-07-05T11:12:13.758059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18242","citing_title":"EventDrive: Event Cameras for Vision-Language Driving Intelligence","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01658","citing_title":"Teaching Vision-Language-Action Models What to See and Where to Look","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02774","citing_title":"GeoDrive-Bench: Benchmarking Region-Specific Multimodal Reasoning in Autonomous Driving","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31572","citing_title":"nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31041","citing_title":"Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21061","citing_title":"Grounding Driving VLA via Inverse Kinematics","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15120","citing_title":"CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00088","citing_title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09465","citing_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19675","citing_title":"DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12624","citing_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24086","citing_title":"AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17915","citing_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09059","citing_title":"Learning Vision-Language-Action World Models for Autonomous Driving","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3","json":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3.json","graph_json":"https://pith.science/api/pith-number/NHZWB4KLNJ5TRGOYT4M3FSUPX3/graph.json","events_json":"https://pith.science/api/pith-number/NHZWB4KLNJ5TRGOYT4M3FSUPX3/events.json","paper":"https://pith.science/paper/NHZWB4KL"},"agent_actions":{"view_html":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3","download_json":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3.json","view_paper":"https://pith.science/paper/NHZWB4KL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23757&json=true","fetch_graph":"https://pith.science/api/pith-number/NHZWB4KLNJ5TRGOYT4M3FSUPX3/graph.json","fetch_events":"https://pith.science/api/pith-number/NHZWB4KLNJ5TRGOYT4M3FSUPX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3/action/storage_attestation","attest_author":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3/action/author_attestation","sign_citation":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3/action/citation_signature","submit_replication":"https://pith.science/pith/NHZWB4KLNJ5TRGOYT4M3FSUPX3/action/replication_record"}},"created_at":"2026-07-05T11:12:13.758059+00:00","updated_at":"2026-07-05T11:12:13.758059+00:00"}