{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K26ZSG5EKC7ZW2A2HNQZ7FDLDB","short_pith_number":"pith:K26ZSG5E","schema_version":"1.0","canonical_sha256":"56bd991ba450bf9b681a3b619f946b184c5fd4c4b29bfce4ad99efa9be4cdf1e","source":{"kind":"arxiv","id":"2606.17362","version":1},"attestation_state":"computed","paper":{"title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Despoina Paschalidou, Jenny Schmalfuss, Jose M. Alvarez, Kashyap Chitta, Kevin Xie, Sanja Fidler, Xinglong Sun, Xiuming Zhang","submitted_at":"2026-06-15T23:39:36Z","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"},"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":"2606.17362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T23:39:36Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"328c079522f4880aa2d6ea956bd80d99d69827f9d28a4e36c6e0dbc809c1daf8","abstract_canon_sha256":"08b74b2557c78249445696d5e8049d9c6cfe847fa8afd01d00455e16956f0ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:10.234097Z","signature_b64":"IUh6rHKX6YX1LBvzCDtIhAP/1BB/+1PtbDeMEz8OSzDonNClAaaO2UD6dJDVzj6x3fiVx/IMHp69JIY9cBMvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56bd991ba450bf9b681a3b619f946b184c5fd4c4b29bfce4ad99efa9be4cdf1e","last_reissued_at":"2026-06-19T16:10:10.233739Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:10.233739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Despoina Paschalidou, Jenny Schmalfuss, Jose M. Alvarez, Kashyap Chitta, Kevin Xie, Sanja Fidler, Xinglong Sun, Xiuming Zhang","submitted_at":"2026-06-15T23:39:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17362","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/2606.17362/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":"2606.17362","created_at":"2026-06-19T16:10:10.233804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17362v1","created_at":"2026-06-19T16:10:10.233804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17362","created_at":"2026-06-19T16:10:10.233804+00:00"},{"alias_kind":"pith_short_12","alias_value":"K26ZSG5EKC7Z","created_at":"2026-06-19T16:10:10.233804+00:00"},{"alias_kind":"pith_short_16","alias_value":"K26ZSG5EKC7ZW2A2","created_at":"2026-06-19T16:10:10.233804+00:00"},{"alias_kind":"pith_short_8","alias_value":"K26ZSG5E","created_at":"2026-06-19T16:10:10.233804+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/K26ZSG5EKC7ZW2A2HNQZ7FDLDB","json":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB.json","graph_json":"https://pith.science/api/pith-number/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/graph.json","events_json":"https://pith.science/api/pith-number/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/events.json","paper":"https://pith.science/paper/K26ZSG5E"},"agent_actions":{"view_html":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB","download_json":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB.json","view_paper":"https://pith.science/paper/K26ZSG5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17362&json=true","fetch_graph":"https://pith.science/api/pith-number/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/graph.json","fetch_events":"https://pith.science/api/pith-number/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/action/storage_attestation","attest_author":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/action/author_attestation","sign_citation":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/action/citation_signature","submit_replication":"https://pith.science/pith/K26ZSG5EKC7ZW2A2HNQZ7FDLDB/action/replication_record"}},"created_at":"2026-06-19T16:10:10.233804+00:00","updated_at":"2026-06-19T16:10:10.233804+00:00"}