{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJS2QHHDTM42SZK6LCS5QWRZ7D","short_pith_number":"pith:PJS2QHHD","schema_version":"1.0","canonical_sha256":"7a65a81ce39b39a9655e58a5d85a39f8ffe9c48b7e5b9d5f2d5756a66de49ca4","source":{"kind":"arxiv","id":"2412.10822","version":1},"attestation_state":"computed","paper":{"title":"Automated Driving with Evolution Capability: A Reinforcement Learning Method with Monotonic Performance Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Haoran Wang, Jia Hu, Tian Xu, Xuerun Yan","submitted_at":"2024-12-14T13:03:58Z","abstract_excerpt":"Reinforcement Learning (RL) offers a promising solution to enable evolutionary automated driving. However, the conventional RL method is always concerned with risk performance. The updated policy may not obtain a performance enhancement, even leading to performance deterioration. To address this challenge, this research proposes a High Confidence Policy Improvement Reinforcement Learning-based (HCPI-RL) planner. It is intended to achieve the monotonic evolution of automated driving. A novel RL policy update paradigm is designed to enable the newly learned policy performance consistently surpas"},"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":"2412.10822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-12-14T13:03:58Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"8a4537689fbad4954a63829c02ab6f703f41f7b410bcced30bdd3e73fe179a1b","abstract_canon_sha256":"b8a6d9f953d98fc5bb18ac31fc193efdd9cda756738cb55f4577e86aed7cbf15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:23.139708Z","signature_b64":"fnI8GBVew/HMJ2xhuTCRPslUOzdT1YkyqD6nfPWQ13W8vzwAhnh2xxEghPGmo1ZCKDJRbX7H8AF1xqPoLk5uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a65a81ce39b39a9655e58a5d85a39f8ffe9c48b7e5b9d5f2d5756a66de49ca4","last_reissued_at":"2026-07-05T09:49:23.139249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:23.139249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Driving with Evolution Capability: A Reinforcement Learning Method with Monotonic Performance Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Haoran Wang, Jia Hu, Tian Xu, Xuerun Yan","submitted_at":"2024-12-14T13:03:58Z","abstract_excerpt":"Reinforcement Learning (RL) offers a promising solution to enable evolutionary automated driving. However, the conventional RL method is always concerned with risk performance. The updated policy may not obtain a performance enhancement, even leading to performance deterioration. To address this challenge, this research proposes a High Confidence Policy Improvement Reinforcement Learning-based (HCPI-RL) planner. It is intended to achieve the monotonic evolution of automated driving. A novel RL policy update paradigm is designed to enable the newly learned policy performance consistently surpas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10822","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/2412.10822/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":"2412.10822","created_at":"2026-07-05T09:49:23.139308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10822v1","created_at":"2026-07-05T09:49:23.139308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10822","created_at":"2026-07-05T09:49:23.139308+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJS2QHHDTM42","created_at":"2026-07-05T09:49:23.139308+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJS2QHHDTM42SZK6","created_at":"2026-07-05T09:49:23.139308+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJS2QHHD","created_at":"2026-07-05T09:49:23.139308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.03795","citing_title":"MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D","json":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D.json","graph_json":"https://pith.science/api/pith-number/PJS2QHHDTM42SZK6LCS5QWRZ7D/graph.json","events_json":"https://pith.science/api/pith-number/PJS2QHHDTM42SZK6LCS5QWRZ7D/events.json","paper":"https://pith.science/paper/PJS2QHHD"},"agent_actions":{"view_html":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D","download_json":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D.json","view_paper":"https://pith.science/paper/PJS2QHHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10822&json=true","fetch_graph":"https://pith.science/api/pith-number/PJS2QHHDTM42SZK6LCS5QWRZ7D/graph.json","fetch_events":"https://pith.science/api/pith-number/PJS2QHHDTM42SZK6LCS5QWRZ7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D/action/storage_attestation","attest_author":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D/action/author_attestation","sign_citation":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D/action/citation_signature","submit_replication":"https://pith.science/pith/PJS2QHHDTM42SZK6LCS5QWRZ7D/action/replication_record"}},"created_at":"2026-07-05T09:49:23.139308+00:00","updated_at":"2026-07-05T09:49:23.139308+00:00"}