{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KJBJV7U3P63C4JIALWKTCNP4YN","short_pith_number":"pith:KJBJV7U3","schema_version":"1.0","canonical_sha256":"52429afe9b7fb62e25005d953135fcc36700a6b8ab30c330a60c59224ccd40e3","source":{"kind":"arxiv","id":"2410.12568","version":2},"attestation_state":"computed","paper":{"title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Guangliang Cheng, Jiaxu Liu, Meng Fang, Sihao Wu, Xiangyu Yin, Xiaowei Huang, Xingyu Zhao, Xinping Yi","submitted_at":"2024-10-16T13:43:00Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require lengthy inference times and face challenges in interacting with real-time autonomous driving environments. A key open question is whether we can effectively leverage the knowledge from LLMs to train an efficient and robust Reinforcement Learning (RL) agent. This paper introduces RAPID, a novel \\underline{\\textbf{R}}obust \\underline{\\textbf{A}}daptive \\underlin"},"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":"2410.12568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-16T13:43:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9c8b8450b017974a34b124712ca8766d6c761d79ab2c3c41fb58a542b4d7bc9","abstract_canon_sha256":"3661446586b2b14499fc2a27cc962769c2affac116db0e2093bf3e9c54a36416"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:15.166348Z","signature_b64":"Anf4FjczN3s9Q+DhPHiiXXX9XNrXbMxPnqewJq2MW859YF3QzrxdhuzOcQ1QupYq0IhUhLXYk2mB10vKZ0GQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52429afe9b7fb62e25005d953135fcc36700a6b8ab30c330a60c59224ccd40e3","last_reissued_at":"2026-07-05T09:23:15.165939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:15.165939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Guangliang Cheng, Jiaxu Liu, Meng Fang, Sihao Wu, Xiangyu Yin, Xiaowei Huang, Xingyu Zhao, Xinping Yi","submitted_at":"2024-10-16T13:43:00Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require lengthy inference times and face challenges in interacting with real-time autonomous driving environments. A key open question is whether we can effectively leverage the knowledge from LLMs to train an efficient and robust Reinforcement Learning (RL) agent. This paper introduces RAPID, a novel \\underline{\\textbf{R}}obust \\underline{\\textbf{A}}daptive \\underlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12568","kind":"arxiv","version":2},"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/2410.12568/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":"2410.12568","created_at":"2026-07-05T09:23:15.166001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12568v2","created_at":"2026-07-05T09:23:15.166001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12568","created_at":"2026-07-05T09:23:15.166001+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJBJV7U3P63C","created_at":"2026-07-05T09:23:15.166001+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJBJV7U3P63C4JIA","created_at":"2026-07-05T09:23:15.166001+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJBJV7U3","created_at":"2026-07-05T09:23:15.166001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15793","citing_title":"HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN","json":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN.json","graph_json":"https://pith.science/api/pith-number/KJBJV7U3P63C4JIALWKTCNP4YN/graph.json","events_json":"https://pith.science/api/pith-number/KJBJV7U3P63C4JIALWKTCNP4YN/events.json","paper":"https://pith.science/paper/KJBJV7U3"},"agent_actions":{"view_html":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN","download_json":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN.json","view_paper":"https://pith.science/paper/KJBJV7U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12568&json=true","fetch_graph":"https://pith.science/api/pith-number/KJBJV7U3P63C4JIALWKTCNP4YN/graph.json","fetch_events":"https://pith.science/api/pith-number/KJBJV7U3P63C4JIALWKTCNP4YN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN/action/storage_attestation","attest_author":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN/action/author_attestation","sign_citation":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN/action/citation_signature","submit_replication":"https://pith.science/pith/KJBJV7U3P63C4JIALWKTCNP4YN/action/replication_record"}},"created_at":"2026-07-05T09:23:15.166001+00:00","updated_at":"2026-07-05T09:23:15.166001+00:00"}