{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZHKYBZRPEX3JG5TBZIFQJBQQSU","short_pith_number":"pith:ZHKYBZRP","canonical_record":{"source":{"id":"2309.00709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-01T19:29:53Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"a8f2fb4185caaaf1d6f408d80fb87d4c61e0970637f3885896278489252fee7f","abstract_canon_sha256":"c6f15434d4ed2c47bad2394c1c3fb6eca37bc8d7833e1883979ef5ee64e9d222"},"schema_version":"1.0"},"canonical_sha256":"c9d580e62f25f6937661ca0b048610953c9bcc914697411499716668be07913d","source":{"kind":"arxiv","id":"2309.00709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00709","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00709v1","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00709","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZHKYBZRPEX3J","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZHKYBZRPEX3JG5TB","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZHKYBZRP","created_at":"2026-07-05T06:47:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZHKYBZRPEX3JG5TBZIFQJBQQSU","target":"record","payload":{"canonical_record":{"source":{"id":"2309.00709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-01T19:29:53Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"a8f2fb4185caaaf1d6f408d80fb87d4c61e0970637f3885896278489252fee7f","abstract_canon_sha256":"c6f15434d4ed2c47bad2394c1c3fb6eca37bc8d7833e1883979ef5ee64e9d222"},"schema_version":"1.0"},"canonical_sha256":"c9d580e62f25f6937661ca0b048610953c9bcc914697411499716668be07913d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:05.793904Z","signature_b64":"E3zk8HCpBLLgmExDHhxuNYEHR46iX8uqh4tfEjXcn6CkRdeMijECcoIkfKi9SegDTgMKYyevKNx1BHz/XeqJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9d580e62f25f6937661ca0b048610953c9bcc914697411499716668be07913d","last_reissued_at":"2026-07-05T06:47:05.793347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:05.793347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.00709","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":"2026-07-05T06:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPP9WhKxYY5jZGpE5Gatc9bFGZkXPmaY4qk0dHMIlhMZywyjNoQ55/KBcnR1/5o1Yte5ik/noxr8zXga/uBzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:10:13.737298Z"},"content_sha256":"698ab821904e2086aa5b5f32248f17add17bbd22f1f133de24f9609ce8fbfb9f","schema_version":"1.0","event_id":"sha256:698ab821904e2086aa5b5f32248f17add17bbd22f1f133de24f9609ce8fbfb9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZHKYBZRPEX3JG5TBZIFQJBQQSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Human Feedback for Realistic Traffic Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Boris Ivanovic, Chaowei Xiao, Marco Pavone, Yulong Cao","submitted_at":"2023-09-01T19:29:53Z","abstract_excerpt":"In light of the challenges and costs of real-world testing, autonomous vehicle developers often rely on testing in simulation for the creation of reliable systems. A key element of effective simulation is the incorporation of realistic traffic models that align with human knowledge, an aspect that has proven challenging due to the need to balance realism and diversity. This works aims to address this by developing a framework that employs reinforcement learning with human preference (RLHF) to enhance the realism of existing traffic models. This study also identifies two main challenges: captur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00709","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/2309.00709/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":"2026-07-05T06:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86bJF7bXz0IdCiNjnc9c/uSJH95bS78jgrRVTJYw3xCRVBUUgKO6XytLIoGMQIFz8kLQomzWgZ5xoEV+ZQf6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:10:13.737821Z"},"content_sha256":"e77929b3e46e0d351c9a195aeabdc3cccfe9920e4833a8c95760ddd415022570","schema_version":"1.0","event_id":"sha256:e77929b3e46e0d351c9a195aeabdc3cccfe9920e4833a8c95760ddd415022570"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/bundle.json","state_url":"https://pith.science/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/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":"2026-08-18T23:10:13Z","links":{"resolver":"https://pith.science/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU","bundle":"https://pith.science/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/bundle.json","state":"https://pith.science/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHKYBZRPEX3JG5TBZIFQJBQQSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZHKYBZRPEX3JG5TBZIFQJBQQSU","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":"c6f15434d4ed2c47bad2394c1c3fb6eca37bc8d7833e1883979ef5ee64e9d222","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-01T19:29:53Z","title_canon_sha256":"a8f2fb4185caaaf1d6f408d80fb87d4c61e0970637f3885896278489252fee7f"},"schema_version":"1.0","source":{"id":"2309.00709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00709","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00709v1","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00709","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZHKYBZRPEX3J","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZHKYBZRPEX3JG5TB","created_at":"2026-07-05T06:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZHKYBZRP","created_at":"2026-07-05T06:47:05Z"}],"graph_snapshots":[{"event_id":"sha256:e77929b3e46e0d351c9a195aeabdc3cccfe9920e4833a8c95760ddd415022570","target":"graph","created_at":"2026-07-05T06:47:05Z","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/2309.00709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In light of the challenges and costs of real-world testing, autonomous vehicle developers often rely on testing in simulation for the creation of reliable systems. A key element of effective simulation is the incorporation of realistic traffic models that align with human knowledge, an aspect that has proven challenging due to the need to balance realism and diversity. This works aims to address this by developing a framework that employs reinforcement learning with human preference (RLHF) to enhance the realism of existing traffic models. This study also identifies two main challenges: captur","authors_text":"Boris Ivanovic, Chaowei Xiao, Marco Pavone, Yulong Cao","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-01T19:29:53Z","title":"Reinforcement Learning with Human Feedback for Realistic Traffic Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00709","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":"sha256:698ab821904e2086aa5b5f32248f17add17bbd22f1f133de24f9609ce8fbfb9f","target":"record","created_at":"2026-07-05T06:47:05Z","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":"c6f15434d4ed2c47bad2394c1c3fb6eca37bc8d7833e1883979ef5ee64e9d222","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-01T19:29:53Z","title_canon_sha256":"a8f2fb4185caaaf1d6f408d80fb87d4c61e0970637f3885896278489252fee7f"},"schema_version":"1.0","source":{"id":"2309.00709","kind":"arxiv","version":1}},"canonical_sha256":"c9d580e62f25f6937661ca0b048610953c9bcc914697411499716668be07913d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d580e62f25f6937661ca0b048610953c9bcc914697411499716668be07913d","first_computed_at":"2026-07-05T06:47:05.793347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:05.793347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E3zk8HCpBLLgmExDHhxuNYEHR46iX8uqh4tfEjXcn6CkRdeMijECcoIkfKi9SegDTgMKYyevKNx1BHz/XeqJDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:05.793904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:698ab821904e2086aa5b5f32248f17add17bbd22f1f133de24f9609ce8fbfb9f","sha256:e77929b3e46e0d351c9a195aeabdc3cccfe9920e4833a8c95760ddd415022570"],"state_sha256":"b0c6925b45ad9fb93b97b9048578de47f746a8a47f8d18e235877c21bd8fa203"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGTD2/jPrRfxv+J+wXg8e4IGxFkY4Z/jcfGmQcL+H4SYlJtr7JOVBoiPb08CRekiD3eZjzvJArQbPukm4x0xBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:10:13.741478Z","bundle_sha256":"042442b9eeb6cc40e872ad1994c8f90551a3371ec40e758800e6e558ebbad8db"}}