{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUQUHDCEZEMB5NW5OFEBCHD3DI","short_pith_number":"pith:NUQUHDCE","schema_version":"1.0","canonical_sha256":"6d21438c44c9181eb6dd7148111c7b1a1e88f02c56867ff0620a38f98a8f04ee","source":{"kind":"arxiv","id":"2601.14702","version":2},"attestation_state":"computed","paper":{"title":"Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Tianjian Gao, Weitong Lian, Yichen Zhu, Yifei Wang, Yu Zhang, Zecong Tang, Zhejun Cui, Zixu Wang","submitted_at":"2026-01-21T06:29:09Z","abstract_excerpt":"Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abilities, opening new possibilities for autonomous driving; however, existing benchmarks often evaluate perception and decision-making separately, limit failure analysis with choice-only formats, or introduce evaluation bias through LLM-scored long-form outputs. To address these issues, we present Drive-P2D, a progressive perception-to-decision benchmark with 6,650 questions across Object, Scene, and Decision levels. Drive"},"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":"2601.14702","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-21T06:29:09Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"4ef374f658dc0c2c6f8e55006a5ab753c89bbc987be71a563177189048e1cd37","abstract_canon_sha256":"674b8cadf0027b7414a387a4f2151b83108e9c30afc47d8aeda6378ee2bd655b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:42.873332Z","signature_b64":"RC0XGOTBcCXTopcQI0m258mO37dOfxqo0ymDsrptwcsUtY/988jk3GtukaKR9Sg1UiP4hAJOmPB+JNW0b9teBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d21438c44c9181eb6dd7148111c7b1a1e88f02c56867ff0620a38f98a8f04ee","last_reissued_at":"2026-05-27T01:05:42.872622Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:42.872622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Tianjian Gao, Weitong Lian, Yichen Zhu, Yifei Wang, Yu Zhang, Zecong Tang, Zhejun Cui, Zixu Wang","submitted_at":"2026-01-21T06:29:09Z","abstract_excerpt":"Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abilities, opening new possibilities for autonomous driving; however, existing benchmarks often evaluate perception and decision-making separately, limit failure analysis with choice-only formats, or introduce evaluation bias through LLM-scored long-form outputs. To address these issues, we present Drive-P2D, a progressive perception-to-decision benchmark with 6,650 questions across Object, Scene, and Decision levels. Drive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14702","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/2601.14702/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":"2601.14702","created_at":"2026-05-27T01:05:42.872723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.14702v2","created_at":"2026-05-27T01:05:42.872723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14702","created_at":"2026-05-27T01:05:42.872723+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUQUHDCEZEMB","created_at":"2026-05-27T01:05:42.872723+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUQUHDCEZEMB5NW5","created_at":"2026-05-27T01:05:42.872723+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUQUHDCE","created_at":"2026-05-27T01:05:42.872723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI","json":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI.json","graph_json":"https://pith.science/api/pith-number/NUQUHDCEZEMB5NW5OFEBCHD3DI/graph.json","events_json":"https://pith.science/api/pith-number/NUQUHDCEZEMB5NW5OFEBCHD3DI/events.json","paper":"https://pith.science/paper/NUQUHDCE"},"agent_actions":{"view_html":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI","download_json":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI.json","view_paper":"https://pith.science/paper/NUQUHDCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.14702&json=true","fetch_graph":"https://pith.science/api/pith-number/NUQUHDCEZEMB5NW5OFEBCHD3DI/graph.json","fetch_events":"https://pith.science/api/pith-number/NUQUHDCEZEMB5NW5OFEBCHD3DI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI/action/storage_attestation","attest_author":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI/action/author_attestation","sign_citation":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI/action/citation_signature","submit_replication":"https://pith.science/pith/NUQUHDCEZEMB5NW5OFEBCHD3DI/action/replication_record"}},"created_at":"2026-05-27T01:05:42.872723+00:00","updated_at":"2026-05-27T01:05:42.872723+00:00"}