{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X6VARXWSTEBZ6ZSO5BDO5FA5SD","short_pith_number":"pith:X6VARXWS","schema_version":"1.0","canonical_sha256":"bfaa08ded299039f664ee846ee941d90f9cd8ad7a8086248156cc5a2e92c7efd","source":{"kind":"arxiv","id":"2508.21824","version":1},"attestation_state":"computed","paper":{"title":"DriveQA: Passing the Driving Knowledge Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eshed Ohn-Bar, Maolin Wei, Wanzhou Liu","submitted_at":"2025-08-29T17:59:53Z","abstract_excerpt":"If a Large Language Model (LLM) were to take a driving knowledge test today, would it pass? Beyond standard spatial and visual question-answering (QA) tasks on current autonomous driving benchmarks, driving knowledge tests require a complete understanding of all traffic rules, signage, and right-of-way principles. To pass this test, human drivers must discern various edge cases that rarely appear in real-world datasets. In this work, we present DriveQA, an extensive open-source text and vision-based benchmark that exhaustively covers traffic regulations and scenarios. Through our experiments u"},"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":"2508.21824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"98ccd869c2069e378d0efa034c2a271fc926f4c524af3be8b097529c5bc4c26e","abstract_canon_sha256":"162d2b69b6a813eeefaa6c028f3a1ea95b3632dc4ea599ba2be31e07c5c73e00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:50.692708Z","signature_b64":"OxZxYwttT+39jBslUUQoIYJDKuBZTJf4eb7ofATENaHFLnEwinBc+5pBsUjij5Yp+mvOCUlcz8mzCrK3y/oTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfaa08ded299039f664ee846ee941d90f9cd8ad7a8086248156cc5a2e92c7efd","last_reissued_at":"2026-07-05T12:01:50.692011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:50.692011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveQA: Passing the Driving Knowledge Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eshed Ohn-Bar, Maolin Wei, Wanzhou Liu","submitted_at":"2025-08-29T17:59:53Z","abstract_excerpt":"If a Large Language Model (LLM) were to take a driving knowledge test today, would it pass? Beyond standard spatial and visual question-answering (QA) tasks on current autonomous driving benchmarks, driving knowledge tests require a complete understanding of all traffic rules, signage, and right-of-way principles. To pass this test, human drivers must discern various edge cases that rarely appear in real-world datasets. In this work, we present DriveQA, an extensive open-source text and vision-based benchmark that exhaustively covers traffic regulations and scenarios. Through our experiments u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21824","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/2508.21824/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":"2508.21824","created_at":"2026-07-05T12:01:50.692081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21824v1","created_at":"2026-07-05T12:01:50.692081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21824","created_at":"2026-07-05T12:01:50.692081+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6VARXWSTEBZ","created_at":"2026-07-05T12:01:50.692081+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6VARXWSTEBZ6ZSO","created_at":"2026-07-05T12:01:50.692081+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6VARXWS","created_at":"2026-07-05T12:01:50.692081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.00088","citing_title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19035","citing_title":"OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08457","citing_title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD","json":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD.json","graph_json":"https://pith.science/api/pith-number/X6VARXWSTEBZ6ZSO5BDO5FA5SD/graph.json","events_json":"https://pith.science/api/pith-number/X6VARXWSTEBZ6ZSO5BDO5FA5SD/events.json","paper":"https://pith.science/paper/X6VARXWS"},"agent_actions":{"view_html":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD","download_json":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD.json","view_paper":"https://pith.science/paper/X6VARXWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21824&json=true","fetch_graph":"https://pith.science/api/pith-number/X6VARXWSTEBZ6ZSO5BDO5FA5SD/graph.json","fetch_events":"https://pith.science/api/pith-number/X6VARXWSTEBZ6ZSO5BDO5FA5SD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD/action/storage_attestation","attest_author":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD/action/author_attestation","sign_citation":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD/action/citation_signature","submit_replication":"https://pith.science/pith/X6VARXWSTEBZ6ZSO5BDO5FA5SD/action/replication_record"}},"created_at":"2026-07-05T12:01:50.692081+00:00","updated_at":"2026-07-05T12:01:50.692081+00:00"}