{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QHUNTCVKPQTXYNRPC6CIT6P4IR","short_pith_number":"pith:QHUNTCVK","schema_version":"1.0","canonical_sha256":"81e8d98aaa7c277c362f178489f9fc446cae87d337d97325faf367ee20c91ac6","source":{"kind":"arxiv","id":"2606.08525","version":1},"attestation_state":"computed","paper":{"title":"DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Fang Li, Fangzhen Li, Guang Chen, Haiyang Sun, Hangjun Ye, Hongwei Xie, Jiong Deng, Long Chen, Qimao Chen, Yang Ji, Yi Zhang, Yuechen Luo, Zehan Zhang","submitted_at":"2026-06-07T09:05:49Z","abstract_excerpt":"Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded v"},"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":"2606.08525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T09:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"29cad9cf381bc0050a57c00dd49ee672315b851f546331c267e36a5953f0df47","abstract_canon_sha256":"d66a6dcc1c473229838760ef6aa1ad5b4ecd0cbc7217138920c2a89bb5c40e70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:39.064621Z","signature_b64":"uEIJZABoOSPJwL5z1kXFE9hbHiGVk6BRmk+sDYB1GCKrcr3R/Gfa79vr9J9VKiMmGLP9r/EuyY7YIkO6TrkwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e8d98aaa7c277c362f178489f9fc446cae87d337d97325faf367ee20c91ac6","last_reissued_at":"2026-06-09T01:05:39.064200Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:39.064200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Wang, Fang Li, Fangzhen Li, Guang Chen, Haiyang Sun, Hangjun Ye, Hongwei Xie, Jiong Deng, Long Chen, Qimao Chen, Yang Ji, Yi Zhang, Yuechen Luo, Zehan Zhang","submitted_at":"2026-06-07T09:05:49Z","abstract_excerpt":"Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08525","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/2606.08525/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":"2606.08525","created_at":"2026-06-09T01:05:39.064256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08525v1","created_at":"2026-06-09T01:05:39.064256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08525","created_at":"2026-06-09T01:05:39.064256+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHUNTCVKPQTX","created_at":"2026-06-09T01:05:39.064256+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHUNTCVKPQTXYNRP","created_at":"2026-06-09T01:05:39.064256+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHUNTCVK","created_at":"2026-06-09T01:05:39.064256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00399","citing_title":"DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR","json":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR.json","graph_json":"https://pith.science/api/pith-number/QHUNTCVKPQTXYNRPC6CIT6P4IR/graph.json","events_json":"https://pith.science/api/pith-number/QHUNTCVKPQTXYNRPC6CIT6P4IR/events.json","paper":"https://pith.science/paper/QHUNTCVK"},"agent_actions":{"view_html":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR","download_json":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR.json","view_paper":"https://pith.science/paper/QHUNTCVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08525&json=true","fetch_graph":"https://pith.science/api/pith-number/QHUNTCVKPQTXYNRPC6CIT6P4IR/graph.json","fetch_events":"https://pith.science/api/pith-number/QHUNTCVKPQTXYNRPC6CIT6P4IR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR/action/storage_attestation","attest_author":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR/action/author_attestation","sign_citation":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR/action/citation_signature","submit_replication":"https://pith.science/pith/QHUNTCVKPQTXYNRPC6CIT6P4IR/action/replication_record"}},"created_at":"2026-06-09T01:05:39.064256+00:00","updated_at":"2026-06-09T01:05:39.064256+00:00"}