{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6EJBA5AG3AR2L3OE7SEASGJOFT","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":"a905801329b189deb6d020a29eef2fa5f4b968615392752017310b274adb83f8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:12:39Z","title_canon_sha256":"b11f8c164254cbae532411ffce7c41e9769c7a9bd7e0bb84d159906f565ff31d"},"schema_version":"1.0","source":{"id":"2503.12772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12772","created_at":"2026-07-05T11:49:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12772v2","created_at":"2026-07-05T11:49:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12772","created_at":"2026-07-05T11:49:08Z"},{"alias_kind":"pith_short_12","alias_value":"6EJBA5AG3AR2","created_at":"2026-07-05T11:49:08Z"},{"alias_kind":"pith_short_16","alias_value":"6EJBA5AG3AR2L3OE","created_at":"2026-07-05T11:49:08Z"},{"alias_kind":"pith_short_8","alias_value":"6EJBA5AG","created_at":"2026-07-05T11:49:08Z"}],"graph_snapshots":[{"event_id":"sha256:f3425e3dd7b51f314126d3494c7169ec06cc3b18031b94a093dfe85d03d29bf3","target":"graph","created_at":"2026-07-05T11:49:08Z","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/2503.12772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multi-modal large language models (MLLMs) have demonstrated strong performance across various domains; however, their ability to comprehend driving scenes remains less proven. The complexity of driving scenarios, which includes multi-view information, poses significant challenges for existing MLLMs. In this paper, we introduce NuPlanQA-Eval, a multi-view, multi-modal evaluation benchmark for driving scene understanding. To further support generalization to multi-view driving scenarios, we also propose NuPlanQA-1M, a large-scale dataset comprising 1M real-world visual questio","authors_text":"Ahmadreza Moradipari, Can Cui, Kyungtae Han, Rohit Gupta, Sung-Yeon Park, Yunsheng Ma, Ziran Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:12:39Z","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12772","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":"sha256:36ebf2c06d4e41721bd306ce9bdbe61d7bc969bd8d22e4adbc6bdfd15335a5e6","target":"record","created_at":"2026-07-05T11:49:08Z","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":"a905801329b189deb6d020a29eef2fa5f4b968615392752017310b274adb83f8","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:12:39Z","title_canon_sha256":"b11f8c164254cbae532411ffce7c41e9769c7a9bd7e0bb84d159906f565ff31d"},"schema_version":"1.0","source":{"id":"2503.12772","kind":"arxiv","version":2}},"canonical_sha256":"f112107406d823a5edc4fc8809192e2cd716ecd27d9517aa3a10d7aa21ef0d07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f112107406d823a5edc4fc8809192e2cd716ecd27d9517aa3a10d7aa21ef0d07","first_computed_at":"2026-07-05T11:49:08.330818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:08.330818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XB9Ol2zDqTMX4Wy98n8mgOi+rTF3P0xQe5raor46+vfLS0PeWShUT8QSWSbnYclYt6dgbs8LYLGmFWoc2oYEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:08.331307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36ebf2c06d4e41721bd306ce9bdbe61d7bc969bd8d22e4adbc6bdfd15335a5e6","sha256:f3425e3dd7b51f314126d3494c7169ec06cc3b18031b94a093dfe85d03d29bf3"],"state_sha256":"0a3284fff291818c5d560c7de4c2de68e66e237f6dfc0638af6e1745c483454d"}