{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L7W6LSXA44AXQPHNMUVSBEW2TX","short_pith_number":"pith:L7W6LSXA","schema_version":"1.0","canonical_sha256":"5fede5cae0e701783ced652b2092da9dd3cf201081514758f62a105a965be896","source":{"kind":"arxiv","id":"2409.00858","version":2},"attestation_state":"computed","paper":{"title":"Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Sikai Chen, Zihao Sheng, Zilin Huang","submitted_at":"2024-09-01T22:20:32Z","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"},"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":"2409.00858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-01T22:20:32Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"3dea3aa1eaef7b2a1bfbfb5fadef8af7aa29ea866ed63ef113d50b529e27ca68","abstract_canon_sha256":"7e17a7807a3ada64094ca326108ff0e94886fd62c354a674b48c6d0a9a5dc583"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:23.201543Z","signature_b64":"vaaWEE2jLtOud0BSUQULEpPWyUIPMwvFfcBRp1xecVtE5AyMtcdV7O4K0y6+NMMdzhqaAW20ULdoJkFyAFrkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fede5cae0e701783ced652b2092da9dd3cf201081514758f62a105a965be896","last_reissued_at":"2026-07-05T09:03:23.201048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:23.201048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Sikai Chen, Zihao Sheng, Zilin Huang","submitted_at":"2024-09-01T22:20:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00858","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/2409.00858/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":"2409.00858","created_at":"2026-07-05T09:03:23.201098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00858v2","created_at":"2026-07-05T09:03:23.201098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00858","created_at":"2026-07-05T09:03:23.201098+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7W6LSXA44AX","created_at":"2026-07-05T09:03:23.201098+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7W6LSXA44AXQPHN","created_at":"2026-07-05T09:03:23.201098+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7W6LSXA","created_at":"2026-07-05T09:03:23.201098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18511","citing_title":"Large Language Model guided Deep Reinforcement Learning for Decision Making in Autonomous Driving","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX","json":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX.json","graph_json":"https://pith.science/api/pith-number/L7W6LSXA44AXQPHNMUVSBEW2TX/graph.json","events_json":"https://pith.science/api/pith-number/L7W6LSXA44AXQPHNMUVSBEW2TX/events.json","paper":"https://pith.science/paper/L7W6LSXA"},"agent_actions":{"view_html":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX","download_json":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX.json","view_paper":"https://pith.science/paper/L7W6LSXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00858&json=true","fetch_graph":"https://pith.science/api/pith-number/L7W6LSXA44AXQPHNMUVSBEW2TX/graph.json","fetch_events":"https://pith.science/api/pith-number/L7W6LSXA44AXQPHNMUVSBEW2TX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX/action/storage_attestation","attest_author":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX/action/author_attestation","sign_citation":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX/action/citation_signature","submit_replication":"https://pith.science/pith/L7W6LSXA44AXQPHNMUVSBEW2TX/action/replication_record"}},"created_at":"2026-07-05T09:03:23.201098+00:00","updated_at":"2026-07-05T09:03:23.201098+00:00"}