{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MIYECSZLFUZHSI3CIVMHK6UY4O","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":"f4130db33c043979ba49371ab20421ceaaa95d48652f1fb4563c58c6e04bc3d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T04:43:10Z","title_canon_sha256":"61aa1174e576109132e0319e3d80aa68becbcd208158bc870b2c34d754cc7e1f"},"schema_version":"1.0","source":{"id":"2504.03164","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03164","created_at":"2026-07-05T10:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03164v2","created_at":"2026-07-05T10:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03164","created_at":"2026-07-05T10:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"MIYECSZLFUZH","created_at":"2026-07-05T10:45:21Z"},{"alias_kind":"pith_short_16","alias_value":"MIYECSZLFUZHSI3C","created_at":"2026-07-05T10:45:21Z"},{"alias_kind":"pith_short_8","alias_value":"MIYECSZL","created_at":"2026-07-05T10:45:21Z"}],"graph_snapshots":[{"event_id":"sha256:3423854021be12aadc4e3d9057abcf1d55ad3db5d694a47862f4c1637ae455bd","target":"graph","created_at":"2026-07-05T10:45:21Z","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/2504.03164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingrui Mao, Jiwan Jiang, Kexin Tian, Yang Zhou, Yunlong Zhang, Zhengzhong Tu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T04:43:10Z","title":"NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03164","kind":"arxiv","version":2},"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":"sha256:1f6c405e3588b8736584c98ace34303d301d5cba2ed79bfc46a8000e0be9bf8e","target":"record","created_at":"2026-07-05T10:45:21Z","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":"f4130db33c043979ba49371ab20421ceaaa95d48652f1fb4563c58c6e04bc3d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T04:43:10Z","title_canon_sha256":"61aa1174e576109132e0319e3d80aa68becbcd208158bc870b2c34d754cc7e1f"},"schema_version":"1.0","source":{"id":"2504.03164","kind":"arxiv","version":2}},"canonical_sha256":"6230414b2b2d327923624558757a98e38e3847ce56d594f3c019f6c048cca9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6230414b2b2d327923624558757a98e38e3847ce56d594f3c019f6c048cca9f3","first_computed_at":"2026-07-05T10:45:21.070968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:21.070968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0m9GF/WI2eNaBMF52anIYMn4hwNobRBMiem1b9O326nhn1WR2ge2JXwt9q8ZPLLhW6nOYzXwnMS8nH18ANaoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:21.071459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.03164","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f6c405e3588b8736584c98ace34303d301d5cba2ed79bfc46a8000e0be9bf8e","sha256:3423854021be12aadc4e3d9057abcf1d55ad3db5d694a47862f4c1637ae455bd"],"state_sha256":"51b1be67ca08dff415114dda1de67344aac7ec1e616e7561a4086c4067363d00"}