{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UYMMIDOLMCVEZ33G4EV5MI3JTY","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":"cf1ece42164b74c98fc7ac397adb676ecf8e4f591bdaeccccde7a0f5d0f455b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T03:43:23Z","title_canon_sha256":"d7a10be182b2b3d4a9110b294a9b10514f0bc988df8ab13b99b8bd97fd541b4e"},"schema_version":"1.0","source":{"id":"2508.02028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02028","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02028v2","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02028","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"UYMMIDOLMCVE","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"UYMMIDOLMCVEZ33G","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"UYMMIDOL","created_at":"2026-07-05T11:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:0e77bc526aed4a95ee34e89324f736633f26a45ac2aa1140068b95a762ccb441","target":"graph","created_at":"2026-07-05T11:56:22Z","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/2508.02028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aishan Liu, Jiangfan Liu, Lu Wang, Mingchuan Zhang, Siyuan Liang, Tianyuan Zhang, Ting Jin, Xianglong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T03:43:23Z","title":"Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02028","kind":"arxiv","version":2},"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":"sha256:5affa654bda5816394197faa3c752ac6c5471dcdb333cebd0b4cf970a5e4c642","target":"record","created_at":"2026-07-05T11:56:22Z","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":"cf1ece42164b74c98fc7ac397adb676ecf8e4f591bdaeccccde7a0f5d0f455b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T03:43:23Z","title_canon_sha256":"d7a10be182b2b3d4a9110b294a9b10514f0bc988df8ab13b99b8bd97fd541b4e"},"schema_version":"1.0","source":{"id":"2508.02028","kind":"arxiv","version":2}},"canonical_sha256":"a618c40dcb60aa4cef66e12bd623699e329e39ab30845b365340200c74f3b0f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a618c40dcb60aa4cef66e12bd623699e329e39ab30845b365340200c74f3b0f9","first_computed_at":"2026-07-05T11:56:22.042981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:22.042981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RG0MInaPV1NVh0IQTi7yM2F2FPNYKCjwmg3yDimEUfEVuQHkWpnbDPys2pCVUKUsPGya2iRiPFy4vBsHemi/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:22.043434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5affa654bda5816394197faa3c752ac6c5471dcdb333cebd0b4cf970a5e4c642","sha256:0e77bc526aed4a95ee34e89324f736633f26a45ac2aa1140068b95a762ccb441"],"state_sha256":"341bb62bfb6c22d37a78c7db8d53d8a9d50f8818aa9d6b94cdb7459407fd4e4b"}