{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:66DH5WQBE5VZJCLJDETJPM2USS","short_pith_number":"pith:66DH5WQB","schema_version":"1.0","canonical_sha256":"f7867eda01276b948969192697b3549489c13d7c478eede0d945e7745113743f","source":{"kind":"arxiv","id":"2110.07067","version":2},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Dong Chen, Kaian Chen, Tianyu Shi, Zhaojian Li","submitted_at":"2021-10-13T22:36:40Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks. However, conventional RL approaches learn control policies through trial-and-error interactions with the environment and therefore may cause disastrous consequences such as collisions when testing in real-world traffic. Offline RL has recently emerged as a promising framework to learn effective policies from previously-collected, static datasets without the requirement of active interactions, making it especially appealing for autonomous driving applications. Despite"},"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":"2110.07067","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-10-13T22:36:40Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"cc62cd2f1d6fcce559dc55a35e9ca0e207268091fa996b6d3795e0e62ee79feb","abstract_canon_sha256":"9fe93099b268ac499264dc55b30b7d5260c33925e0a79bfd69a3c051cd395c33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:59.050269Z","signature_b64":"ZeP23lZSr21Pn0aGE+ZECIywQJxGtcHvPw3qh7Q2VskFmAubSgLo4uFhcKsVQzmnkQDHnZJtPXDZBUozt7moBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7867eda01276b948969192697b3549489c13d7c478eede0d945e7745113743f","last_reissued_at":"2026-07-05T03:27:59.049723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:59.049723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Dong Chen, Kaian Chen, Tianyu Shi, Zhaojian Li","submitted_at":"2021-10-13T22:36:40Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks. However, conventional RL approaches learn control policies through trial-and-error interactions with the environment and therefore may cause disastrous consequences such as collisions when testing in real-world traffic. Offline RL has recently emerged as a promising framework to learn effective policies from previously-collected, static datasets without the requirement of active interactions, making it especially appealing for autonomous driving applications. Despite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07067","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/2110.07067/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":"2110.07067","created_at":"2026-07-05T03:27:59.049787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07067v2","created_at":"2026-07-05T03:27:59.049787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07067","created_at":"2026-07-05T03:27:59.049787+00:00"},{"alias_kind":"pith_short_12","alias_value":"66DH5WQBE5VZ","created_at":"2026-07-05T03:27:59.049787+00:00"},{"alias_kind":"pith_short_16","alias_value":"66DH5WQBE5VZJCLJ","created_at":"2026-07-05T03:27:59.049787+00:00"},{"alias_kind":"pith_short_8","alias_value":"66DH5WQB","created_at":"2026-07-05T03:27:59.049787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09559","citing_title":"Safe-RULE: Safe Reinforcement UnLEarning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS","json":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS.json","graph_json":"https://pith.science/api/pith-number/66DH5WQBE5VZJCLJDETJPM2USS/graph.json","events_json":"https://pith.science/api/pith-number/66DH5WQBE5VZJCLJDETJPM2USS/events.json","paper":"https://pith.science/paper/66DH5WQB"},"agent_actions":{"view_html":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS","download_json":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS.json","view_paper":"https://pith.science/paper/66DH5WQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07067&json=true","fetch_graph":"https://pith.science/api/pith-number/66DH5WQBE5VZJCLJDETJPM2USS/graph.json","fetch_events":"https://pith.science/api/pith-number/66DH5WQBE5VZJCLJDETJPM2USS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS/action/storage_attestation","attest_author":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS/action/author_attestation","sign_citation":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS/action/citation_signature","submit_replication":"https://pith.science/pith/66DH5WQBE5VZJCLJDETJPM2USS/action/replication_record"}},"created_at":"2026-07-05T03:27:59.049787+00:00","updated_at":"2026-07-05T03:27:59.049787+00:00"}