{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UYMMIDOLMCVEZ33G4EV5MI3JTY","short_pith_number":"pith:UYMMIDOL","schema_version":"1.0","canonical_sha256":"a618c40dcb60aa4cef66e12bd623699e329e39ab30845b365340200c74f3b0f9","source":{"kind":"arxiv","id":"2508.02028","version":2},"attestation_state":"computed","paper":{"title":"Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishan Liu, Jiangfan Liu, Lu Wang, Mingchuan Zhang, Siyuan Liang, Tianyuan Zhang, Ting Jin, Xianglong Liu","submitted_at":"2025-08-04T03:43:23Z","abstract_excerpt":"Vision-Language Models (VLMs) have recently emerged as a promising paradigm in autonomous driving (AD). However, current performance evaluation protocols for VLM-based AD systems (ADVLMs) are predominantly confined to open-loop settings with static inputs, neglecting the more realistic and informative closed-loop setting that captures interactive behavior, feedback resilience, and real-world safety. To address this, we introduce Bench2ADVLM, a unified hierarchical closed-loop evaluation framework for real-time, interactive assessment of ADVLMs across both simulation and physical platforms. Ins"},"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":"2508.02028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T03:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"d7a10be182b2b3d4a9110b294a9b10514f0bc988df8ab13b99b8bd97fd541b4e","abstract_canon_sha256":"cf1ece42164b74c98fc7ac397adb676ecf8e4f591bdaeccccde7a0f5d0f455b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:22.043434Z","signature_b64":"RG0MInaPV1NVh0IQTi7yM2F2FPNYKCjwmg3yDimEUfEVuQHkWpnbDPys2pCVUKUsPGya2iRiPFy4vBsHemi/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a618c40dcb60aa4cef66e12bd623699e329e39ab30845b365340200c74f3b0f9","last_reissued_at":"2026-07-05T11:56:22.042981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:22.042981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishan Liu, Jiangfan Liu, Lu Wang, Mingchuan Zhang, Siyuan Liang, Tianyuan Zhang, Ting Jin, Xianglong Liu","submitted_at":"2025-08-04T03:43:23Z","abstract_excerpt":"Vision-Language Models (VLMs) have recently emerged as a promising paradigm in autonomous driving (AD). However, current performance evaluation protocols for VLM-based AD systems (ADVLMs) are predominantly confined to open-loop settings with static inputs, neglecting the more realistic and informative closed-loop setting that captures interactive behavior, feedback resilience, and real-world safety. To address this, we introduce Bench2ADVLM, a unified hierarchical closed-loop evaluation framework for real-time, interactive assessment of ADVLMs across both simulation and physical platforms. Ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02028","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/2508.02028/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":"2508.02028","created_at":"2026-07-05T11:56:22.043037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02028v2","created_at":"2026-07-05T11:56:22.043037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02028","created_at":"2026-07-05T11:56:22.043037+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYMMIDOLMCVE","created_at":"2026-07-05T11:56:22.043037+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYMMIDOLMCVEZ33G","created_at":"2026-07-05T11:56:22.043037+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYMMIDOL","created_at":"2026-07-05T11:56:22.043037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10386","citing_title":"GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04488","citing_title":"A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY","json":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY.json","graph_json":"https://pith.science/api/pith-number/UYMMIDOLMCVEZ33G4EV5MI3JTY/graph.json","events_json":"https://pith.science/api/pith-number/UYMMIDOLMCVEZ33G4EV5MI3JTY/events.json","paper":"https://pith.science/paper/UYMMIDOL"},"agent_actions":{"view_html":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY","download_json":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY.json","view_paper":"https://pith.science/paper/UYMMIDOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02028&json=true","fetch_graph":"https://pith.science/api/pith-number/UYMMIDOLMCVEZ33G4EV5MI3JTY/graph.json","fetch_events":"https://pith.science/api/pith-number/UYMMIDOLMCVEZ33G4EV5MI3JTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY/action/storage_attestation","attest_author":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY/action/author_attestation","sign_citation":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY/action/citation_signature","submit_replication":"https://pith.science/pith/UYMMIDOLMCVEZ33G4EV5MI3JTY/action/replication_record"}},"created_at":"2026-07-05T11:56:22.043037+00:00","updated_at":"2026-07-05T11:56:22.043037+00:00"}