{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U6JNUKXXLJLEJ76CSNGVGULTLY","short_pith_number":"pith:U6JNUKXX","schema_version":"1.0","canonical_sha256":"a792da2af75a5644ffc2934d5351735e294d79d10673293043677ae160a1d3e9","source":{"kind":"arxiv","id":"2310.14414","version":2},"attestation_state":"computed","paper":{"title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alois C. Knoll, Bare Luka Zagar, Ekim Yurtsever, Hu Cao, Mingyu Liu, Walter Zimmer, Xingcheng Zhou","submitted_at":"2023-10-22T21:06:10Z","abstract_excerpt":"The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs). By incorporating language data, driving systems can gain a better understanding of real-world environments, thereby enhancing driving safety and efficiency. In this work, we present a comprehensive and systematic survey of the advances in vision language models in this domain, encompassing perception and understanding, navigation and planning, decision-making and control, end-"},"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":"2310.14414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-22T21:06:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"233568f4ef43ddc774e528739c61d05c15782afefb4059b647ca6c8dfdf12d1f","abstract_canon_sha256":"ca29012e9b921293d5b03512ad72fb456e4dc8f3e6388c45763e2fb1defa320e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:38.620256Z","signature_b64":"c1lNgzfLQfY80k9p4Luf+wcb/LAOJn8oHTjCOP33kidKiMJ5lRWrsKPG/MhB27yASMg6kxrGDHqCjjkbVoqxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a792da2af75a5644ffc2934d5351735e294d79d10673293043677ae160a1d3e9","last_reissued_at":"2026-07-05T08:35:38.619772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:38.619772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alois C. Knoll, Bare Luka Zagar, Ekim Yurtsever, Hu Cao, Mingyu Liu, Walter Zimmer, Xingcheng Zhou","submitted_at":"2023-10-22T21:06:10Z","abstract_excerpt":"The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs). By incorporating language data, driving systems can gain a better understanding of real-world environments, thereby enhancing driving safety and efficiency. In this work, we present a comprehensive and systematic survey of the advances in vision language models in this domain, encompassing perception and understanding, navigation and planning, decision-making and control, end-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14414","kind":"arxiv","version":2},"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/2310.14414/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":"2310.14414","created_at":"2026-07-05T08:35:38.619832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14414v2","created_at":"2026-07-05T08:35:38.619832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14414","created_at":"2026-07-05T08:35:38.619832+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6JNUKXXLJLE","created_at":"2026-07-05T08:35:38.619832+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6JNUKXXLJLEJ76C","created_at":"2026-07-05T08:35:38.619832+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6JNUKXX","created_at":"2026-07-05T08:35:38.619832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17209","citing_title":"LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05442","citing_title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY","json":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY.json","graph_json":"https://pith.science/api/pith-number/U6JNUKXXLJLEJ76CSNGVGULTLY/graph.json","events_json":"https://pith.science/api/pith-number/U6JNUKXXLJLEJ76CSNGVGULTLY/events.json","paper":"https://pith.science/paper/U6JNUKXX"},"agent_actions":{"view_html":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY","download_json":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY.json","view_paper":"https://pith.science/paper/U6JNUKXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14414&json=true","fetch_graph":"https://pith.science/api/pith-number/U6JNUKXXLJLEJ76CSNGVGULTLY/graph.json","fetch_events":"https://pith.science/api/pith-number/U6JNUKXXLJLEJ76CSNGVGULTLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY/action/storage_attestation","attest_author":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY/action/author_attestation","sign_citation":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY/action/citation_signature","submit_replication":"https://pith.science/pith/U6JNUKXXLJLEJ76CSNGVGULTLY/action/replication_record"}},"created_at":"2026-07-05T08:35:38.619832+00:00","updated_at":"2026-07-05T08:35:38.619832+00:00"}