{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7OYF7IPKTYQTTXL7O2N4CULD4J","short_pith_number":"pith:7OYF7IPK","canonical_record":{"source":{"id":"2406.04481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T20:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"99f4cfe9dd2b11d2000f65c1644235a6b1be780eae836c493136cd26ad7ab9ce","abstract_canon_sha256":"a86b49a9585d194c20c2d1a7fc5f09f2e646f546049701cc78a1cecceb4969ad"},"schema_version":"1.0"},"canonical_sha256":"fbb05fa1ea9e2139dd7f769bc15163e26f70493f3d22a1d24626c18242ff0da6","source":{"kind":"arxiv","id":"2406.04481","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04481","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04481v1","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04481","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"7OYF7IPKTYQT","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"7OYF7IPKTYQTTXL7","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"7OYF7IPK","created_at":"2026-07-05T09:17:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7OYF7IPKTYQTTXL7O2N4CULD4J","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T20:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"99f4cfe9dd2b11d2000f65c1644235a6b1be780eae836c493136cd26ad7ab9ce","abstract_canon_sha256":"a86b49a9585d194c20c2d1a7fc5f09f2e646f546049701cc78a1cecceb4969ad"},"schema_version":"1.0"},"canonical_sha256":"fbb05fa1ea9e2139dd7f769bc15163e26f70493f3d22a1d24626c18242ff0da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:13.627133Z","signature_b64":"sIVkQzKKrCmfcxplF6HLtkI6YWi34IhX97ecXtzGiErD/140Dhe8DrMGNRDfl6xiA/jgHe9OZgKbjvZ47qqpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb05fa1ea9e2139dd7f769bc15163e26f70493f3d22a1d24626c18242ff0da6","last_reissued_at":"2026-07-05T09:17:13.626675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:13.626675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04481","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O00XftjVYDWkwH23jQ8HaUhEKda9NNOyVGEP7U3aMfOCVtc7lQHKfWdNEkXQcOlzCJ0t5GpHcRgdOH5+jgnKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:02:11.026324Z"},"content_sha256":"f809ee4428366f39d9d2566fb924c2e430274dbb17d74915415dcbe086303b00","schema_version":"1.0","event_id":"sha256:f809ee4428366f39d9d2566fb924c2e430274dbb17d74915415dcbe086303b00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7OYF7IPKTYQTTXL7O2N4CULD4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jorge Ortiz, Navid Salami Pargoo, Peter J. Jin, Yuan Sun","submitted_at":"2024-06-06T20:10:34Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is popular in large language models (LLMs), whereas traditional Reinforcement Learning (RL) often falls short. Current autonomous driving methods typically utilize either human feedback in machine learning, including RL, or LLMs. Most feedback guides the car agent's learning process (e.g., controlling the car). RLHF is usually applied in the fine-tuning step, requiring direct human \"preferences,\" which are not commonly used in optimizing autonomous driving models. In this research, we innovatively combine RLHF and LLMs to enhance autonomous dri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04481","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/2406.04481/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/G5gBH6peS8dvJ8JUdREv3craRIUu3bEz00KsaWyrEhgh3xDKGvHTtqoxnr7T1ZMo+GJBMLErm/94WbDy9xGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:02:11.026975Z"},"content_sha256":"42933014c8dfc95d8a6ddde60397c73255cf386973bdfc0779421efe29288749","schema_version":"1.0","event_id":"sha256:42933014c8dfc95d8a6ddde60397c73255cf386973bdfc0779421efe29288749"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/bundle.json","state_url":"https://pith.science/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T13:02:11Z","links":{"resolver":"https://pith.science/pith/7OYF7IPKTYQTTXL7O2N4CULD4J","bundle":"https://pith.science/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/bundle.json","state":"https://pith.science/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OYF7IPKTYQTTXL7O2N4CULD4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7OYF7IPKTYQTTXL7O2N4CULD4J","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":"a86b49a9585d194c20c2d1a7fc5f09f2e646f546049701cc78a1cecceb4969ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T20:10:34Z","title_canon_sha256":"99f4cfe9dd2b11d2000f65c1644235a6b1be780eae836c493136cd26ad7ab9ce"},"schema_version":"1.0","source":{"id":"2406.04481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04481","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04481v1","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04481","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"7OYF7IPKTYQT","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"7OYF7IPKTYQTTXL7","created_at":"2026-07-05T09:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"7OYF7IPK","created_at":"2026-07-05T09:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:42933014c8dfc95d8a6ddde60397c73255cf386973bdfc0779421efe29288749","target":"graph","created_at":"2026-07-05T09:17:13Z","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/2406.04481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is popular in large language models (LLMs), whereas traditional Reinforcement Learning (RL) often falls short. Current autonomous driving methods typically utilize either human feedback in machine learning, including RL, or LLMs. Most feedback guides the car agent's learning process (e.g., controlling the car). RLHF is usually applied in the fine-tuning step, requiring direct human \"preferences,\" which are not commonly used in optimizing autonomous driving models. In this research, we innovatively combine RLHF and LLMs to enhance autonomous dri","authors_text":"Jorge Ortiz, Navid Salami Pargoo, Peter J. Jin, Yuan Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T20:10:34Z","title":"Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04481","kind":"arxiv","version":1},"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:f809ee4428366f39d9d2566fb924c2e430274dbb17d74915415dcbe086303b00","target":"record","created_at":"2026-07-05T09:17:13Z","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":"a86b49a9585d194c20c2d1a7fc5f09f2e646f546049701cc78a1cecceb4969ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-06T20:10:34Z","title_canon_sha256":"99f4cfe9dd2b11d2000f65c1644235a6b1be780eae836c493136cd26ad7ab9ce"},"schema_version":"1.0","source":{"id":"2406.04481","kind":"arxiv","version":1}},"canonical_sha256":"fbb05fa1ea9e2139dd7f769bc15163e26f70493f3d22a1d24626c18242ff0da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbb05fa1ea9e2139dd7f769bc15163e26f70493f3d22a1d24626c18242ff0da6","first_computed_at":"2026-07-05T09:17:13.626675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:13.626675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIVkQzKKrCmfcxplF6HLtkI6YWi34IhX97ecXtzGiErD/140Dhe8DrMGNRDfl6xiA/jgHe9OZgKbjvZ47qqpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:13.627133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f809ee4428366f39d9d2566fb924c2e430274dbb17d74915415dcbe086303b00","sha256:42933014c8dfc95d8a6ddde60397c73255cf386973bdfc0779421efe29288749"],"state_sha256":"508b9ddf919e4269f6f2fa7a9b80d967f39d47169fb7e372300a0f015aa37e04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"19v9DdB5jYsPvxTBWMooi3Eliwjgqg8Y7owUzouHYP1WmpqzeH7c3QtJxvipA5qSBHhkra6uMsTuTWI1hmZADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:02:11.030155Z","bundle_sha256":"576f96bc9d918bf18584196c2e91d455f654ea327ac02207fa01f4d586af4b71"}}