{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:46UE23XN7B2WZWCZKA5KAWKEHW","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":"cda9f90422219015ce519be884f84ab443fb2eae1157b0f26e2b5eb758b3a2f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T07:40:50Z","title_canon_sha256":"9c81680c00c0aaec98c3e0133141838ebf333c9cc6da7604b0a699d1ce8347e2"},"schema_version":"1.0","source":{"id":"2305.14836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14836","created_at":"2026-07-05T07:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14836v2","created_at":"2026-07-05T07:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14836","created_at":"2026-07-05T07:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"46UE23XN7B2W","created_at":"2026-07-05T07:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"46UE23XN7B2WZWCZ","created_at":"2026-07-05T07:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"46UE23XN","created_at":"2026-07-05T07:47:02Z"}],"graph_snapshots":[{"event_id":"sha256:d8ccb97e916fbd9f2c92a4f435200bbd9982446ae50780be1179b22ea378b285","target":"graph","created_at":"2026-07-05T07:47:02Z","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/2305.14836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingjing Chen, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu-Gang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T07:40:50Z","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14836","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":"sha256:346e085f5e8d3697bee79df6b350fbf26d36eb21c3cc11856203dd857dc12de6","target":"record","created_at":"2026-07-05T07:47:02Z","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":"cda9f90422219015ce519be884f84ab443fb2eae1157b0f26e2b5eb758b3a2f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T07:40:50Z","title_canon_sha256":"9c81680c00c0aaec98c3e0133141838ebf333c9cc6da7604b0a699d1ce8347e2"},"schema_version":"1.0","source":{"id":"2305.14836","kind":"arxiv","version":2}},"canonical_sha256":"e7a84d6eedf8756cd859503aa059443da3ad4fa6219712752bacc297167f9bbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7a84d6eedf8756cd859503aa059443da3ad4fa6219712752bacc297167f9bbd","first_computed_at":"2026-07-05T07:47:02.624334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:02.624334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PpW6VNEK4K9s83RZ4kTgcvLr64m5b1heeozMjteHHgfVKo0bKxcR7/5JW/aholAl9mDJ5RnBH2f/touit7okDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:02.624804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:346e085f5e8d3697bee79df6b350fbf26d36eb21c3cc11856203dd857dc12de6","sha256:d8ccb97e916fbd9f2c92a4f435200bbd9982446ae50780be1179b22ea378b285"],"state_sha256":"e5f44ec5f85a75af2d4bb69c7570a6d65212ec12b1169fbe527eb4da2dcd4946"}