{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K26ZSG5EKC7ZW2A2HNQZ7FDLDB","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":"08b74b2557c78249445696d5e8049d9c6cfe847fa8afd01d00455e16956f0ff5","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T23:39:36Z","title_canon_sha256":"328c079522f4880aa2d6ea956bd80d99d69827f9d28a4e36c6e0dbc809c1daf8"},"schema_version":"1.0","source":{"id":"2606.17362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17362","created_at":"2026-06-19T16:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17362v1","created_at":"2026-06-19T16:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17362","created_at":"2026-06-19T16:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"K26ZSG5EKC7Z","created_at":"2026-06-19T16:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"K26ZSG5EKC7ZW2A2","created_at":"2026-06-19T16:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"K26ZSG5E","created_at":"2026-06-19T16:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:995b1504adee18f77a66aba3bca73a24b4b9a93d666b65f8da496a9609a3d7c0","target":"graph","created_at":"2026-06-19T16:10:10Z","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/2606.17362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical grounding. To evaluate driving in a manner that is both interpretable and context-aware, we introduce DriveJudge. DriveJudge is a driving evaluation agent that combines rule-grounded evaluation with Vision","authors_text":"Despoina Paschalidou, Jenny Schmalfuss, Jose M. Alvarez, Kashyap Chitta, Kevin Xie, Sanja Fidler, Xinglong Sun, Xiuming Zhang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T23:39:36Z","title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17362","kind":"arxiv","version":1},"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":"sha256:20634d0e2d6e7abc83c5d758175e2ca7ec382700653764cc2876cf1d3b6ea855","target":"record","created_at":"2026-06-19T16:10:10Z","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":"08b74b2557c78249445696d5e8049d9c6cfe847fa8afd01d00455e16956f0ff5","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T23:39:36Z","title_canon_sha256":"328c079522f4880aa2d6ea956bd80d99d69827f9d28a4e36c6e0dbc809c1daf8"},"schema_version":"1.0","source":{"id":"2606.17362","kind":"arxiv","version":1}},"canonical_sha256":"56bd991ba450bf9b681a3b619f946b184c5fd4c4b29bfce4ad99efa9be4cdf1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56bd991ba450bf9b681a3b619f946b184c5fd4c4b29bfce4ad99efa9be4cdf1e","first_computed_at":"2026-06-19T16:10:10.233739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:10.233739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUh6rHKX6YX1LBvzCDtIhAP/1BB/+1PtbDeMEz8OSzDonNClAaaO2UD6dJDVzj6x3fiVx/IMHp69JIY9cBMvBw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:10.234097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20634d0e2d6e7abc83c5d758175e2ca7ec382700653764cc2876cf1d3b6ea855","sha256:995b1504adee18f77a66aba3bca73a24b4b9a93d666b65f8da496a9609a3d7c0"],"state_sha256":"21bda78584a1204a13ac991811331c5c5603712e93ab8228480fe11101468480"}