{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MIYECSZLFUZHSI3CIVMHK6UY4O","short_pith_number":"pith:MIYECSZL","schema_version":"1.0","canonical_sha256":"6230414b2b2d327923624558757a98e38e3847ce56d594f3c019f6c048cca9f3","source":{"kind":"arxiv","id":"2504.03164","version":2},"attestation_state":"computed","paper":{"title":"NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingrui Mao, Jiwan Jiang, Kexin Tian, Yang Zhou, Yunlong Zhang, Zhengzhong Tu","submitted_at":"2025-04-04T04:43:10Z","abstract_excerpt":"Recent advancements in Vision-Language Models (VLMs) have demonstrated strong potential for autonomous driving tasks. However, their spatial understanding and reasoning-key capabilities for autonomous driving-still exhibit significant limitations. Notably, none of the existing benchmarks systematically evaluate VLMs' spatial reasoning capabilities in driving scenarios. To fill this gap, we propose NuScenes-SpatialQA, the first large-scale ground-truth-based Question-Answer (QA) benchmark specifically designed to evaluate the spatial understanding and reasoning capabilities of VLMs in autonomou"},"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":"2504.03164","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T04:43:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61aa1174e576109132e0319e3d80aa68becbcd208158bc870b2c34d754cc7e1f","abstract_canon_sha256":"f4130db33c043979ba49371ab20421ceaaa95d48652f1fb4563c58c6e04bc3d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:21.071459Z","signature_b64":"0m9GF/WI2eNaBMF52anIYMn4hwNobRBMiem1b9O326nhn1WR2ge2JXwt9q8ZPLLhW6nOYzXwnMS8nH18ANaoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6230414b2b2d327923624558757a98e38e3847ce56d594f3c019f6c048cca9f3","last_reissued_at":"2026-07-05T10:45:21.070968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:21.070968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingrui Mao, Jiwan Jiang, Kexin Tian, Yang Zhou, Yunlong Zhang, Zhengzhong Tu","submitted_at":"2025-04-04T04:43:10Z","abstract_excerpt":"Recent advancements in Vision-Language Models (VLMs) have demonstrated strong potential for autonomous driving tasks. However, their spatial understanding and reasoning-key capabilities for autonomous driving-still exhibit significant limitations. Notably, none of the existing benchmarks systematically evaluate VLMs' spatial reasoning capabilities in driving scenarios. To fill this gap, we propose NuScenes-SpatialQA, the first large-scale ground-truth-based Question-Answer (QA) benchmark specifically designed to evaluate the spatial understanding and reasoning capabilities of VLMs in autonomou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03164","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/2504.03164/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":"2504.03164","created_at":"2026-07-05T10:45:21.071027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03164v2","created_at":"2026-07-05T10:45:21.071027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03164","created_at":"2026-07-05T10:45:21.071027+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIYECSZLFUZH","created_at":"2026-07-05T10:45:21.071027+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIYECSZLFUZHSI3C","created_at":"2026-07-05T10:45:21.071027+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIYECSZL","created_at":"2026-07-05T10:45:21.071027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07642","citing_title":"Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01608","citing_title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","ref_index":33,"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":85,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11635","citing_title":"Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09573","citing_title":"More than the Sum: Panorama-Language Models for Adverse Omni-Scenes","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22868","citing_title":"Probing Visual Planning in Image Editing Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01731","citing_title":"Lateral String Stability for Vehicle Platoons: Formulation, Definition, and Analysis","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O","json":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O.json","graph_json":"https://pith.science/api/pith-number/MIYECSZLFUZHSI3CIVMHK6UY4O/graph.json","events_json":"https://pith.science/api/pith-number/MIYECSZLFUZHSI3CIVMHK6UY4O/events.json","paper":"https://pith.science/paper/MIYECSZL"},"agent_actions":{"view_html":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O","download_json":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O.json","view_paper":"https://pith.science/paper/MIYECSZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03164&json=true","fetch_graph":"https://pith.science/api/pith-number/MIYECSZLFUZHSI3CIVMHK6UY4O/graph.json","fetch_events":"https://pith.science/api/pith-number/MIYECSZLFUZHSI3CIVMHK6UY4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O/action/storage_attestation","attest_author":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O/action/author_attestation","sign_citation":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O/action/citation_signature","submit_replication":"https://pith.science/pith/MIYECSZLFUZHSI3CIVMHK6UY4O/action/replication_record"}},"created_at":"2026-07-05T10:45:21.071027+00:00","updated_at":"2026-07-05T10:45:21.071027+00:00"}