{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRLXM534C3HQJTRU2KSCO47AJJ","short_pith_number":"pith:MRLXM534","schema_version":"1.0","canonical_sha256":"645776777c16cf04ce34d2a42773e04a6d17e457ca8dad79f1ae4e405ea118da","source":{"kind":"arxiv","id":"2503.21505","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dechang Zhu, Haiqiang Liu, Jiangtong Zhu, Meng Tian, Xinhai Zhao, Yue Li, Yueyi Zhang, Zhenyu Lin, Zhiwei Xiong, Zining Wang","submitted_at":"2025-03-27T13:45:47Z","abstract_excerpt":"Existing benchmarks for Vision-Language Model (VLM) on autonomous driving (AD) primarily assess interpretability through open-form visual question answering (QA) within coarse-grained tasks, which remain insufficient to assess capabilities in complex driving scenarios. To this end, we introduce $\\textbf{VLADBench}$, a challenging and fine-grained dataset featuring close-form QAs that progress from static foundational knowledge and elements to advanced reasoning for dynamic on-road situations. The elaborate $\\textbf{VLADBench}$ spans 5 key domains: Traffic Knowledge Understanding, General Eleme"},"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":"2503.21505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T13:45:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"210ad493b54361574a8a268c58b6f89b21434eee8afb2873506dccc26be2bd2c","abstract_canon_sha256":"e49a59b0b72e9afebfb1e2a82b8729606005715252562f56d863a650344a3074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:26.479145Z","signature_b64":"fzSyyAonbu4WZCaSCbO5DIZby/sFk4K10zaZPULwDjVTwWVbAXZjCawxXjxkCuHcdGgRkSRRc/XABiggEYCXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"645776777c16cf04ce34d2a42773e04a6d17e457ca8dad79f1ae4e405ea118da","last_reissued_at":"2026-07-05T10:40:26.478641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:26.478641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dechang Zhu, Haiqiang Liu, Jiangtong Zhu, Meng Tian, Xinhai Zhao, Yue Li, Yueyi Zhang, Zhenyu Lin, Zhiwei Xiong, Zining Wang","submitted_at":"2025-03-27T13:45:47Z","abstract_excerpt":"Existing benchmarks for Vision-Language Model (VLM) on autonomous driving (AD) primarily assess interpretability through open-form visual question answering (QA) within coarse-grained tasks, which remain insufficient to assess capabilities in complex driving scenarios. To this end, we introduce $\\textbf{VLADBench}$, a challenging and fine-grained dataset featuring close-form QAs that progress from static foundational knowledge and elements to advanced reasoning for dynamic on-road situations. The elaborate $\\textbf{VLADBench}$ spans 5 key domains: Traffic Knowledge Understanding, General Eleme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21505","kind":"arxiv","version":1},"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/2503.21505/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":"2503.21505","created_at":"2026-07-05T10:40:26.478709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21505v1","created_at":"2026-07-05T10:40:26.478709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21505","created_at":"2026-07-05T10:40:26.478709+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRLXM534C3HQ","created_at":"2026-07-05T10:40:26.478709+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRLXM534C3HQJTRU","created_at":"2026-07-05T10:40:26.478709+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRLXM534","created_at":"2026-07-05T10:40:26.478709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07649","citing_title":"Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07649","citing_title":"Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ","json":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ.json","graph_json":"https://pith.science/api/pith-number/MRLXM534C3HQJTRU2KSCO47AJJ/graph.json","events_json":"https://pith.science/api/pith-number/MRLXM534C3HQJTRU2KSCO47AJJ/events.json","paper":"https://pith.science/paper/MRLXM534"},"agent_actions":{"view_html":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ","download_json":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ.json","view_paper":"https://pith.science/paper/MRLXM534","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21505&json=true","fetch_graph":"https://pith.science/api/pith-number/MRLXM534C3HQJTRU2KSCO47AJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MRLXM534C3HQJTRU2KSCO47AJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ/action/storage_attestation","attest_author":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ/action/author_attestation","sign_citation":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ/action/citation_signature","submit_replication":"https://pith.science/pith/MRLXM534C3HQJTRU2KSCO47AJJ/action/replication_record"}},"created_at":"2026-07-05T10:40:26.478709+00:00","updated_at":"2026-07-05T10:40:26.478709+00:00"}