{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IJL6NTNBLNYH6BY5V6FQL7S7FF","short_pith_number":"pith:IJL6NTNB","schema_version":"1.0","canonical_sha256":"4257e6cda15b707f071daf8b05fe5f297bf0876efa4b0907a1ef5d6cd5033a92","source":{"kind":"arxiv","id":"2512.24331","version":2},"attestation_state":"computed","paper":{"title":"Spatial-aware Vision Language Model for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ling Feng, Venice Erin Liong, Weijie Wei, Zhipeng Luo","submitted_at":"2025-12-30T16:35:00Z","abstract_excerpt":"While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making presents a critical bottleneck for safety and reliability. Current image-based methods struggle with accurate metric spatial reasoning and geometric inference, leading to unreliable driving policies. To bridge this gap, we propose LVLDrive (LiDAR-Vision-Language), a novel framework specifically designed to upgrade existing VLMs with robust 3D metric spatial u"},"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":"2512.24331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-30T16:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"3192c17dacd272dc7176ab64c72305e533e2679a285ba5afe1b3ca23801eaabf","abstract_canon_sha256":"75d001c0a824882b70c5492bd3e7459bdd5fd6a4e007cad99b6c979d25fec7ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:01.933194Z","signature_b64":"WKgFZN/Qg4ctoaBMc7FfY8xMyQE0Znr0xhYzHmA9x6wH1sfIsvpzD3sZfNanPYq4e+g2j5eZjfDu/aoqpyTrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4257e6cda15b707f071daf8b05fe5f297bf0876efa4b0907a1ef5d6cd5033a92","last_reissued_at":"2026-05-26T02:04:01.932534Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:01.932534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-aware Vision Language Model for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ling Feng, Venice Erin Liong, Weijie Wei, Zhipeng Luo","submitted_at":"2025-12-30T16:35:00Z","abstract_excerpt":"While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making presents a critical bottleneck for safety and reliability. Current image-based methods struggle with accurate metric spatial reasoning and geometric inference, leading to unreliable driving policies. To bridge this gap, we propose LVLDrive (LiDAR-Vision-Language), a novel framework specifically designed to upgrade existing VLMs with robust 3D metric spatial u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.24331","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/2512.24331/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":"2512.24331","created_at":"2026-05-26T02:04:01.932643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.24331v2","created_at":"2026-05-26T02:04:01.932643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.24331","created_at":"2026-05-26T02:04:01.932643+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJL6NTNBLNYH","created_at":"2026-05-26T02:04:01.932643+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJL6NTNBLNYH6BY5","created_at":"2026-05-26T02:04:01.932643+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJL6NTNB","created_at":"2026-05-26T02:04:01.932643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.12833","citing_title":"Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":99,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20191","citing_title":"From Scene to Object: Text-Guided Dual-Gaze Prediction","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF","json":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF.json","graph_json":"https://pith.science/api/pith-number/IJL6NTNBLNYH6BY5V6FQL7S7FF/graph.json","events_json":"https://pith.science/api/pith-number/IJL6NTNBLNYH6BY5V6FQL7S7FF/events.json","paper":"https://pith.science/paper/IJL6NTNB"},"agent_actions":{"view_html":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF","download_json":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF.json","view_paper":"https://pith.science/paper/IJL6NTNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.24331&json=true","fetch_graph":"https://pith.science/api/pith-number/IJL6NTNBLNYH6BY5V6FQL7S7FF/graph.json","fetch_events":"https://pith.science/api/pith-number/IJL6NTNBLNYH6BY5V6FQL7S7FF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF/action/storage_attestation","attest_author":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF/action/author_attestation","sign_citation":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF/action/citation_signature","submit_replication":"https://pith.science/pith/IJL6NTNBLNYH6BY5V6FQL7S7FF/action/replication_record"}},"created_at":"2026-05-26T02:04:01.932643+00:00","updated_at":"2026-05-26T02:04:01.932643+00:00"}