{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6EJBA5AG3AR2L3OE7SEASGJOFT","short_pith_number":"pith:6EJBA5AG","schema_version":"1.0","canonical_sha256":"f112107406d823a5edc4fc8809192e2cd716ecd27d9517aa3a10d7aa21ef0d07","source":{"kind":"arxiv","id":"2503.12772","version":2},"attestation_state":"computed","paper":{"title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ahmadreza Moradipari, Can Cui, Kyungtae Han, Rohit Gupta, Sung-Yeon Park, Yunsheng Ma, Ziran Wang","submitted_at":"2025-03-17T03:12:39Z","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"},"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":"2503.12772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:12:39Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b11f8c164254cbae532411ffce7c41e9769c7a9bd7e0bb84d159906f565ff31d","abstract_canon_sha256":"a905801329b189deb6d020a29eef2fa5f4b968615392752017310b274adb83f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:08.331307Z","signature_b64":"XB9Ol2zDqTMX4Wy98n8mgOi+rTF3P0xQe5raor46+vfLS0PeWShUT8QSWSbnYclYt6dgbs8LYLGmFWoc2oYEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f112107406d823a5edc4fc8809192e2cd716ecd27d9517aa3a10d7aa21ef0d07","last_reissued_at":"2026-07-05T11:49:08.330818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:08.330818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ahmadreza Moradipari, Can Cui, Kyungtae Han, Rohit Gupta, Sung-Yeon Park, Yunsheng Ma, Ziran Wang","submitted_at":"2025-03-17T03:12:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12772","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/2503.12772/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":"2503.12772","created_at":"2026-07-05T11:49:08.330877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12772v2","created_at":"2026-07-05T11:49:08.330877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12772","created_at":"2026-07-05T11:49:08.330877+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EJBA5AG3AR2","created_at":"2026-07-05T11:49:08.330877+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EJBA5AG3AR2L3OE","created_at":"2026-07-05T11:49:08.330877+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EJBA5AG","created_at":"2026-07-05T11:49:08.330877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21222","citing_title":"FleetAgent: Teleoperation Assistant for Autonomous Fleets via Vectorized V2N Messages","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25944","citing_title":"NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving","ref_index":23,"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":92,"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":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19710","citing_title":"SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT","json":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT.json","graph_json":"https://pith.science/api/pith-number/6EJBA5AG3AR2L3OE7SEASGJOFT/graph.json","events_json":"https://pith.science/api/pith-number/6EJBA5AG3AR2L3OE7SEASGJOFT/events.json","paper":"https://pith.science/paper/6EJBA5AG"},"agent_actions":{"view_html":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT","download_json":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT.json","view_paper":"https://pith.science/paper/6EJBA5AG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12772&json=true","fetch_graph":"https://pith.science/api/pith-number/6EJBA5AG3AR2L3OE7SEASGJOFT/graph.json","fetch_events":"https://pith.science/api/pith-number/6EJBA5AG3AR2L3OE7SEASGJOFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT/action/storage_attestation","attest_author":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT/action/author_attestation","sign_citation":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT/action/citation_signature","submit_replication":"https://pith.science/pith/6EJBA5AG3AR2L3OE7SEASGJOFT/action/replication_record"}},"created_at":"2026-07-05T11:49:08.330877+00:00","updated_at":"2026-07-05T11:49:08.330877+00:00"}