{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:66DH5WQBE5VZJCLJDETJPM2USS","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":"9fe93099b268ac499264dc55b30b7d5260c33925e0a79bfd69a3c051cd395c33","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-10-13T22:36:40Z","title_canon_sha256":"cc62cd2f1d6fcce559dc55a35e9ca0e207268091fa996b6d3795e0e62ee79feb"},"schema_version":"1.0","source":{"id":"2110.07067","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07067","created_at":"2026-07-05T03:27:59Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07067v2","created_at":"2026-07-05T03:27:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07067","created_at":"2026-07-05T03:27:59Z"},{"alias_kind":"pith_short_12","alias_value":"66DH5WQBE5VZ","created_at":"2026-07-05T03:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"66DH5WQBE5VZJCLJ","created_at":"2026-07-05T03:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"66DH5WQB","created_at":"2026-07-05T03:27:59Z"}],"graph_snapshots":[{"event_id":"sha256:d06d4f684244d201b7c78cdec785076e339baf91dc0449037a82370aecdfea20","target":"graph","created_at":"2026-07-05T03:27:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.07067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dong Chen, Kaian Chen, Tianyu Shi, Zhaojian Li","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-10-13T22:36:40Z","title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07067","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:080e497c67e921a3c8df5faa183248c0f4483de8b2cb2ea2a3e5d4fd1a8c835d","target":"record","created_at":"2026-07-05T03:27:59Z","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":"9fe93099b268ac499264dc55b30b7d5260c33925e0a79bfd69a3c051cd395c33","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-10-13T22:36:40Z","title_canon_sha256":"cc62cd2f1d6fcce559dc55a35e9ca0e207268091fa996b6d3795e0e62ee79feb"},"schema_version":"1.0","source":{"id":"2110.07067","kind":"arxiv","version":2}},"canonical_sha256":"f7867eda01276b948969192697b3549489c13d7c478eede0d945e7745113743f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7867eda01276b948969192697b3549489c13d7c478eede0d945e7745113743f","first_computed_at":"2026-07-05T03:27:59.049723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:59.049723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZeP23lZSr21Pn0aGE+ZECIywQJxGtcHvPw3qh7Q2VskFmAubSgLo4uFhcKsVQzmnkQDHnZJtPXDZBUozt7moBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:59.050269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07067","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:080e497c67e921a3c8df5faa183248c0f4483de8b2cb2ea2a3e5d4fd1a8c835d","sha256:d06d4f684244d201b7c78cdec785076e339baf91dc0449037a82370aecdfea20"],"state_sha256":"23f92ecc82c0d85c43717c707dcad700986bd224c0fb8825b7200eced0804db2"}