{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PQHGOG6BIICBFSA7G4KFDN2URQ","short_pith_number":"pith:PQHGOG6B","schema_version":"1.0","canonical_sha256":"7c0e671bc1420412c81f371451b7548c3a29bb29885e214c27a4ccd4ba93e226","source":{"kind":"arxiv","id":"2408.04447","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Lu Liu, Maonan Wang, Xi Xiong, Yuting Wang","submitted_at":"2024-08-08T13:18:53Z","abstract_excerpt":"The burgeoning field of autonomous driving necessitates the seamless integration of autonomous vehicles (AVs) with human-driven vehicles, calling for more predictable AV behavior and enhanced interaction with human drivers. Human-like driving, particularly during lane-changing maneuvers on highways, is a critical area of research due to its significant impact on safety and traffic flow. Traditional rule-based decision-making approaches often fail to encapsulate the nuanced boundaries of human behavior in diverse driving scenarios, while crafting reward functions for learning-based methods intr"},"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":"2408.04447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-08-08T13:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"498c297f4e67078b0dbea286c9722e75e145bd68f6888c19f8557e3bcc193378","abstract_canon_sha256":"8936c6e7037b54a48969ffe2a3f147eaac1bf70beb2bfb89646e927a98d68bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:33.427796Z","signature_b64":"wT8lUFU3B3Xue4sI7ah2OqDVsBVWqZC8A2jl9+6FKOesTnzxQFUHu+QmGM0J0/PfU2Dh7GEfyh79OZSpuqGcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c0e671bc1420412c81f371451b7548c3a29bb29885e214c27a4ccd4ba93e226","last_reissued_at":"2026-07-05T08:53:33.427392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:33.427392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Lu Liu, Maonan Wang, Xi Xiong, Yuting Wang","submitted_at":"2024-08-08T13:18:53Z","abstract_excerpt":"The burgeoning field of autonomous driving necessitates the seamless integration of autonomous vehicles (AVs) with human-driven vehicles, calling for more predictable AV behavior and enhanced interaction with human drivers. Human-like driving, particularly during lane-changing maneuvers on highways, is a critical area of research due to its significant impact on safety and traffic flow. Traditional rule-based decision-making approaches often fail to encapsulate the nuanced boundaries of human behavior in diverse driving scenarios, while crafting reward functions for learning-based methods intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04447","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/2408.04447/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":"2408.04447","created_at":"2026-07-05T08:53:33.427448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04447v1","created_at":"2026-07-05T08:53:33.427448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04447","created_at":"2026-07-05T08:53:33.427448+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQHGOG6BIICB","created_at":"2026-07-05T08:53:33.427448+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQHGOG6BIICBFSA7","created_at":"2026-07-05T08:53:33.427448+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQHGOG6B","created_at":"2026-07-05T08:53:33.427448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19033","citing_title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ","json":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ.json","graph_json":"https://pith.science/api/pith-number/PQHGOG6BIICBFSA7G4KFDN2URQ/graph.json","events_json":"https://pith.science/api/pith-number/PQHGOG6BIICBFSA7G4KFDN2URQ/events.json","paper":"https://pith.science/paper/PQHGOG6B"},"agent_actions":{"view_html":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ","download_json":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ.json","view_paper":"https://pith.science/paper/PQHGOG6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04447&json=true","fetch_graph":"https://pith.science/api/pith-number/PQHGOG6BIICBFSA7G4KFDN2URQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PQHGOG6BIICBFSA7G4KFDN2URQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ/action/storage_attestation","attest_author":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ/action/author_attestation","sign_citation":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ/action/citation_signature","submit_replication":"https://pith.science/pith/PQHGOG6BIICBFSA7G4KFDN2URQ/action/replication_record"}},"created_at":"2026-07-05T08:53:33.427448+00:00","updated_at":"2026-07-05T08:53:33.427448+00:00"}