{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X7LGMLX7PDZADBAF6SOWJYQ4JY","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":"0ec7a83949788c53e06ecd2051407aff2c52be5c6823003262d1418c6c3b8e6e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T03:14:04Z","title_canon_sha256":"ba562e3aaab8eef881a9434048224f584cf92f512da83f7c25cb6d1d2022c1d3"},"schema_version":"1.0","source":{"id":"2506.08052","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08052","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08052v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08052","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"X7LGMLX7PDZA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"X7LGMLX7PDZADBAF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"X7LGMLX7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:50574936af538e61ebfe60d1e846bc318e00b03783e968d1c512997667ea02d6","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ReCogDrive achieves state-of-the-art performance on the NAVSIM and Bench2Drive benchmarks while demonstrating strong scene comprehension across diverse driving scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The hierarchical data pipeline (generation, refinement, quality control) successfully instills transferable human driving cognition into the VLM without introducing dataset-specific biases that limit generalization to real-world conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ReCogDrive combines a vision-language model for cognition with a reinforced diffusion planner to generate feasible, safe driving trajectories."}],"snapshot_sha256":"55f72864b9aded7b041f4abd791c40db0758cf1b3f7110230602fb4836f27ad4"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"63586337561cb13aa62e45ff9c91453416dd1b783f351f272298a207a362121b"},"paper":{"abstract_excerpt":"Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate trajectory planning as a language modeling task, where physical actions are output in the language space, potentially leading to issues such as format-violating outputs, infeasible actions, and slow inference speeds. In this paper, we propose ReCogDrive, a novel Reinforced Cognitive framework for end-to-end autonomous Driving, unifying driving understanding and pla","authors_text":"Bing Wang, Fang Li, Gangwei Xu, Guang Chen, Haiyang Sun, Hangjun Ye, Kaixin Xiong, Kun Ma, Lijun Zhou, Long Chen, Sixu Yan, Wenyu Liu, Xiangyu Guo, Xinggang Wang, Yongkang Li","cross_cats":["cs.RO"],"headline":"ReCogDrive combines a vision-language model for cognition with a reinforced diffusion planner to generate feasible, safe driving trajectories.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T03:14:04Z","title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving"},"references":{"count":45,"internal_anchors":22,"resolved_work":45,"sample":[{"cited_arxiv_id":"2412.08905","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Phi-4 Technical Report","work_id":"b6274271-7af9-4ee8-993b-ba1ba4205ba8","year":null},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Is a 3d-tokenized LLM the key to reliable autonomous driving? CoRR, abs/2405.18361, 2024","work_id":"f6f04e40-cb7f-4d15-b4d7-b0a9b79c2f2a","year":null},{"cited_arxiv_id":"2503.14734","doi":"","is_internal_anchor":true,"ref_index":4,"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","year":null},{"cited_arxiv_id":"2410.24164","doi":"","is_internal_anchor":true,"ref_index":5,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","year":null}],"snapshot_sha256":"fbde30c0d11113843533d5bd0d40b2e88d6f96e3cfbdc1395d1312af96d22b92"},"source":{"id":"2506.08052","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T07:32:02.372355Z","id":"dfee4c2c-5de7-4b1e-bcb9-aaa919fcdc8f","model_set":{"reader":"grok-4.3"},"one_line_summary":"ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ReCogDrive combines a vision-language model for cognition with a reinforced diffusion planner to generate feasible, safe driving trajectories.","strongest_claim":"ReCogDrive achieves state-of-the-art performance on the NAVSIM and Bench2Drive benchmarks while demonstrating strong scene comprehension across diverse driving scenarios.","weakest_assumption":"The hierarchical data pipeline (generation, refinement, quality control) successfully instills transferable human driving cognition into the VLM without introducing dataset-specific biases that limit generalization to real-world conditions."}},"verdict_id":"dfee4c2c-5de7-4b1e-bcb9-aaa919fcdc8f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:51ff2957eb31286925135c322ef452d726ecdec789889bf8f91a26e5984af1ff","target":"record","created_at":"2026-05-17T23:38:53Z","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":"0ec7a83949788c53e06ecd2051407aff2c52be5c6823003262d1418c6c3b8e6e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T03:14:04Z","title_canon_sha256":"ba562e3aaab8eef881a9434048224f584cf92f512da83f7c25cb6d1d2022c1d3"},"schema_version":"1.0","source":{"id":"2506.08052","kind":"arxiv","version":2}},"canonical_sha256":"bfd6662eff78f2018405f49d64e21c4e19e4814f77ee640dee879085f68a7a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfd6662eff78f2018405f49d64e21c4e19e4814f77ee640dee879085f68a7a56","first_computed_at":"2026-05-17T23:38:53.119256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.119256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3YUz46y/JJskdC/gHl9lgJhgP0SiTN6OJPn/kT/Hs+5jnxUGnSbP7o75C+jBHoVFEvQ2W23g2S7Dlf8i6E3DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.119769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08052","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51ff2957eb31286925135c322ef452d726ecdec789889bf8f91a26e5984af1ff","sha256:50574936af538e61ebfe60d1e846bc318e00b03783e968d1c512997667ea02d6"],"state_sha256":"9ff92abed205267f420223f7f921bb8a9bff1a564ac9fe45ebad1880c4cd6a31"}