{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:655PGJ7AYVTW6O6XPWTX5UQCWZ","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":"5644a13cb7dc9bc6031012a2f72e55cfafc7b0f55ad7d7d26828316b13dbb463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-02T01:54:22Z","title_canon_sha256":"418b2b5f2fb02852b30138f8a84ad6b09896b1ff32da637f511e86868982685f"},"schema_version":"1.0","source":{"id":"2401.00988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00988","created_at":"2026-07-05T07:29:32Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00988v1","created_at":"2026-07-05T07:29:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00988","created_at":"2026-07-05T07:29:32Z"},{"alias_kind":"pith_short_12","alias_value":"655PGJ7AYVTW","created_at":"2026-07-05T07:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"655PGJ7AYVTW6O6X","created_at":"2026-07-05T07:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"655PGJ7A","created_at":"2026-07-05T07:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:be77cd76d6e23f817c4dcbcc77267ab6ae91f52972a72588eb0cc4764e0156c7","target":"graph","created_at":"2026-07-05T07:29:32Z","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/2401.00988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of multimodal large language models (MLLMs) has spurred interest in language-based driving tasks. However, existing research typically focuses on limited tasks and often omits key multi-view and temporal information which is crucial for robust autonomous driving. To bridge these gaps, we introduce NuInstruct, a novel dataset with 91K multi-view video-QA pairs across 17 subtasks, where each task demands holistic information (e.g., temporal, multi-view, and spatial), significantly elevating the challenge level. To obtain NuInstruct, we propose a novel SQL-based method to generate instru","authors_text":"Hang Xu, Jinahua Han, Wei Zhang, Xiaodan Liang, Xiaomeng Li, Xinpeng Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-02T01:54:22Z","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00988","kind":"arxiv","version":1},"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":"sha256:83a26d47a70e69efd4abc35d0dbe0c59996f431378d9d1b8e96f725cb872abf0","target":"record","created_at":"2026-07-05T07:29:32Z","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":"5644a13cb7dc9bc6031012a2f72e55cfafc7b0f55ad7d7d26828316b13dbb463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-02T01:54:22Z","title_canon_sha256":"418b2b5f2fb02852b30138f8a84ad6b09896b1ff32da637f511e86868982685f"},"schema_version":"1.0","source":{"id":"2401.00988","kind":"arxiv","version":1}},"canonical_sha256":"f77af327e0c5676f3bd77da77ed202b640bd779a7b64fb18382f9864b24811f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f77af327e0c5676f3bd77da77ed202b640bd779a7b64fb18382f9864b24811f9","first_computed_at":"2026-07-05T07:29:32.548215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:32.548215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"24h8el25zzgEbp9NrAqab6ziKK7KHzzrV4pE+bG32vJXOqLs9zsK6ZzTx2C7B9uGMNrB7/an0Ri5q+/afOGaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:32.548680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83a26d47a70e69efd4abc35d0dbe0c59996f431378d9d1b8e96f725cb872abf0","sha256:be77cd76d6e23f817c4dcbcc77267ab6ae91f52972a72588eb0cc4764e0156c7"],"state_sha256":"e9b6b3d75a2ea44bb062ee5d9f2ca0abf624281cab70d3d91960d84ed413154a"}