{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:46UE23XN7B2WZWCZKA5KAWKEHW","short_pith_number":"pith:46UE23XN","schema_version":"1.0","canonical_sha256":"e7a84d6eedf8756cd859503aa059443da3ad4fa6219712752bacc297167f9bbd","source":{"kind":"arxiv","id":"2305.14836","version":2},"attestation_state":"computed","paper":{"title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Chen, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu-Gang Jiang","submitted_at":"2023-05-24T07:40:50Z","abstract_excerpt":"We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. Compared to traditional VQA tasks, VQA in autonomous driving scenario presents more challenges. Firstly, the raw visual data are multi-modal, including images and point clouds captured by camera and LiDAR, respectively. Secondly, the data are multi-frame due to the continuous, real-time acquisition. Thirdly, the outdoor scenes exhibit both moving foreground and static background. Existing VQA benchmarks fail to adequately addres"},"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":"2305.14836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T07:40:50Z","cross_cats_sorted":[],"title_canon_sha256":"9c81680c00c0aaec98c3e0133141838ebf333c9cc6da7604b0a699d1ce8347e2","abstract_canon_sha256":"cda9f90422219015ce519be884f84ab443fb2eae1157b0f26e2b5eb758b3a2f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:02.624804Z","signature_b64":"PpW6VNEK4K9s83RZ4kTgcvLr64m5b1heeozMjteHHgfVKo0bKxcR7/5JW/aholAl9mDJ5RnBH2f/touit7okDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a84d6eedf8756cd859503aa059443da3ad4fa6219712752bacc297167f9bbd","last_reissued_at":"2026-07-05T07:47:02.624334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:02.624334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Chen, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu-Gang Jiang","submitted_at":"2023-05-24T07:40:50Z","abstract_excerpt":"We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. Compared to traditional VQA tasks, VQA in autonomous driving scenario presents more challenges. Firstly, the raw visual data are multi-modal, including images and point clouds captured by camera and LiDAR, respectively. Secondly, the data are multi-frame due to the continuous, real-time acquisition. Thirdly, the outdoor scenes exhibit both moving foreground and static background. Existing VQA benchmarks fail to adequately addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14836","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/2305.14836/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":"2305.14836","created_at":"2026-07-05T07:47:02.624391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14836v2","created_at":"2026-07-05T07:47:02.624391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14836","created_at":"2026-07-05T07:47:02.624391+00:00"},{"alias_kind":"pith_short_12","alias_value":"46UE23XN7B2W","created_at":"2026-07-05T07:47:02.624391+00:00"},{"alias_kind":"pith_short_16","alias_value":"46UE23XN7B2WZWCZ","created_at":"2026-07-05T07:47:02.624391+00:00"},{"alias_kind":"pith_short_8","alias_value":"46UE23XN","created_at":"2026-07-05T07:47:02.624391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22913","citing_title":"Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21222","citing_title":"FleetAgent: Teleoperation Assistant for Autonomous Fleets via Vectorized V2N Messages","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05269","citing_title":"B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2402.12289","citing_title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20460","citing_title":"CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08212","citing_title":"Vision-Language Foundation Models for Comprehensive Automated Pavement Condition Assessment","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW","json":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW.json","graph_json":"https://pith.science/api/pith-number/46UE23XN7B2WZWCZKA5KAWKEHW/graph.json","events_json":"https://pith.science/api/pith-number/46UE23XN7B2WZWCZKA5KAWKEHW/events.json","paper":"https://pith.science/paper/46UE23XN"},"agent_actions":{"view_html":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW","download_json":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW.json","view_paper":"https://pith.science/paper/46UE23XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14836&json=true","fetch_graph":"https://pith.science/api/pith-number/46UE23XN7B2WZWCZKA5KAWKEHW/graph.json","fetch_events":"https://pith.science/api/pith-number/46UE23XN7B2WZWCZKA5KAWKEHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW/action/storage_attestation","attest_author":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW/action/author_attestation","sign_citation":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW/action/citation_signature","submit_replication":"https://pith.science/pith/46UE23XN7B2WZWCZKA5KAWKEHW/action/replication_record"}},"created_at":"2026-07-05T07:47:02.624391+00:00","updated_at":"2026-07-05T07:47:02.624391+00:00"}