{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L7W6LSXA44AXQPHNMUVSBEW2TX","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":"7e17a7807a3ada64094ca326108ff0e94886fd62c354a674b48c6d0a9a5dc583","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-01T22:20:32Z","title_canon_sha256":"3dea3aa1eaef7b2a1bfbfb5fadef8af7aa29ea866ed63ef113d50b529e27ca68"},"schema_version":"1.0","source":{"id":"2409.00858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00858","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00858v2","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00858","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"L7W6LSXA44AX","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"L7W6LSXA44AXQPHN","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"L7W6LSXA","created_at":"2026-07-05T09:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:99c7805f1f54a8432b3e4612f940c463fd73fa8fa41d7e3d5dd7eabec467feef","target":"graph","created_at":"2026-07-05T09:03:23Z","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/2409.00858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the field of autonomous driving, developing safe and trustworthy autonomous driving policies remains a significant challenge. Recently, Reinforcement Learning with Human Feedback (RLHF) has attracted substantial attention due to its potential to enhance training safety and sampling efficiency. Nevertheless, existing RLHF-enabled methods often falter when faced with imperfect human demonstrations, potentially leading to training oscillations or even worse performance than rule-based approaches. Inspired by the human learning process, we propose Physics-enhanced Reinforcement Learning with Hu","authors_text":"Sikai Chen, Zihao Sheng, Zilin Huang","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-01T22:20:32Z","title":"Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00858","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":"sha256:35ea56d0693cb7c02d2017c49ebfeac61a0e8dc1d630ee76a9b62e497b74dc08","target":"record","created_at":"2026-07-05T09:03:23Z","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":"7e17a7807a3ada64094ca326108ff0e94886fd62c354a674b48c6d0a9a5dc583","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-01T22:20:32Z","title_canon_sha256":"3dea3aa1eaef7b2a1bfbfb5fadef8af7aa29ea866ed63ef113d50b529e27ca68"},"schema_version":"1.0","source":{"id":"2409.00858","kind":"arxiv","version":2}},"canonical_sha256":"5fede5cae0e701783ced652b2092da9dd3cf201081514758f62a105a965be896","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fede5cae0e701783ced652b2092da9dd3cf201081514758f62a105a965be896","first_computed_at":"2026-07-05T09:03:23.201048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:23.201048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vaaWEE2jLtOud0BSUQULEpPWyUIPMwvFfcBRp1xecVtE5AyMtcdV7O4K0y6+NMMdzhqaAW20ULdoJkFyAFrkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:23.201543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35ea56d0693cb7c02d2017c49ebfeac61a0e8dc1d630ee76a9b62e497b74dc08","sha256:99c7805f1f54a8432b3e4612f940c463fd73fa8fa41d7e3d5dd7eabec467feef"],"state_sha256":"d58bcc349d536f88d6292567c910ee9c2fa9d79c2385ff98995252d63a88523e"}