{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SXF7B6M6QURY5A2PDQA5CUPQM2","short_pith_number":"pith:SXF7B6M6","canonical_record":{"source":{"id":"2605.19033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:57:13Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"title_canon_sha256":"facdd07522294732040466d80cd3b49be998ba5bd4bc998e16d97f2d5eada573","abstract_canon_sha256":"824d08484f94bba8338a6f9d9143ba64f7db6179bb093f307443df7a840097ab"},"schema_version":"1.0"},"canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","source":{"kind":"arxiv","id":"2605.19033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19033","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19033v1","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19033","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"SXF7B6M6QURY","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"SXF7B6M6QURY5A2P","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"SXF7B6M6","created_at":"2026-05-20T01:05:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SXF7B6M6QURY5A2PDQA5CUPQM2","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:57:13Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"title_canon_sha256":"facdd07522294732040466d80cd3b49be998ba5bd4bc998e16d97f2d5eada573","abstract_canon_sha256":"824d08484f94bba8338a6f9d9143ba64f7db6179bb093f307443df7a840097ab"},"schema_version":"1.0"},"canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:21.352693Z","signature_b64":"5RZojCmvse4tcKrxRcd7RmBk+YiYopudaF1RWUZ/TenxAQbkU6W3kbUEoJdbX1TGROL5qs+cBRHsahvH24qICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","last_reissued_at":"2026-05-20T01:05:21.351861Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:21.351861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19033","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":"2026-05-20T01:05:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8T0jqGE0Ph/TpnNsGtEa+oyCaFdTZiAcPtGnNjVJ3Cm8pPz/l68vRwl/ST9NaMyMjRyx4Y7BcBnPHWtmr0HuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:28:38.364266Z"},"content_sha256":"3e260dbbd0b3cf4d8eb92b34ab4df7c5c41ce7b01f4fabbe5cb7de0086861a5c","schema_version":"1.0","event_id":"sha256:3e260dbbd0b3cf4d8eb92b34ab4df7c5c41ce7b01f4fabbe5cb7de0086861a5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SXF7B6M6QURY5A2PDQA5CUPQM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Behzad Khamidehi, Dongfeng Bai, Ehsan Ahmadi, Fazel Arasteh, Hunter Schofield, Jinjun Shan, Kasra Rezaee, Lili Mou","submitted_at":"2026-05-18T18:57:13Z","abstract_excerpt":"Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a reinforcement-learning-based fine-tuning framework that enhances scenario realism by aligning simulator rollouts with real-world data distributions and provides a method for distilling goal-conditioned controllability in scenario generation. We instantiate RLFTSim on top of a pre-trained simulation model, design a reward that balances fidelity and controllability, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19033","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/2605.19033/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":"2026-05-20T01:05:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w83z/5PiuQhxxy/C4M3pWxeGQdYU4WHtLdiL0RXzmoSU7fiSTVlPZU8jjwCOMJZcD3fbIp7E+GYghGtZKAyvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:28:38.364746Z"},"content_sha256":"be58d7106efc2fc38091a67f5fbffc93ffa38f308dd4fa2473f3ccfabf7bbd4a","schema_version":"1.0","event_id":"sha256:be58d7106efc2fc38091a67f5fbffc93ffa38f308dd4fa2473f3ccfabf7bbd4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/bundle.json","state_url":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/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":"2026-05-24T09:28:38Z","links":{"resolver":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2","bundle":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/bundle.json","state":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SXF7B6M6QURY5A2PDQA5CUPQM2","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":"824d08484f94bba8338a6f9d9143ba64f7db6179bb093f307443df7a840097ab","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:57:13Z","title_canon_sha256":"facdd07522294732040466d80cd3b49be998ba5bd4bc998e16d97f2d5eada573"},"schema_version":"1.0","source":{"id":"2605.19033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19033","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19033v1","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19033","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"SXF7B6M6QURY","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"SXF7B6M6QURY5A2P","created_at":"2026-05-20T01:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"SXF7B6M6","created_at":"2026-05-20T01:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:be58d7106efc2fc38091a67f5fbffc93ffa38f308dd4fa2473f3ccfabf7bbd4a","target":"graph","created_at":"2026-05-20T01:05:21Z","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/2605.19033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a reinforcement-learning-based fine-tuning framework that enhances scenario realism by aligning simulator rollouts with real-world data distributions and provides a method for distilling goal-conditioned controllability in scenario generation. We instantiate RLFTSim on top of a pre-trained simulation model, design a reward that balances fidelity and controllability, ","authors_text":"Behzad Khamidehi, Dongfeng Bai, Ehsan Ahmadi, Fazel Arasteh, Hunter Schofield, Jinjun Shan, Kasra Rezaee, Lili Mou","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:57:13Z","title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19033","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":"sha256:3e260dbbd0b3cf4d8eb92b34ab4df7c5c41ce7b01f4fabbe5cb7de0086861a5c","target":"record","created_at":"2026-05-20T01:05:21Z","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":"824d08484f94bba8338a6f9d9143ba64f7db6179bb093f307443df7a840097ab","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:57:13Z","title_canon_sha256":"facdd07522294732040466d80cd3b49be998ba5bd4bc998e16d97f2d5eada573"},"schema_version":"1.0","source":{"id":"2605.19033","kind":"arxiv","version":1}},"canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","first_computed_at":"2026-05-20T01:05:21.351861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:21.351861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5RZojCmvse4tcKrxRcd7RmBk+YiYopudaF1RWUZ/TenxAQbkU6W3kbUEoJdbX1TGROL5qs+cBRHsahvH24qICg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:21.352693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e260dbbd0b3cf4d8eb92b34ab4df7c5c41ce7b01f4fabbe5cb7de0086861a5c","sha256:be58d7106efc2fc38091a67f5fbffc93ffa38f308dd4fa2473f3ccfabf7bbd4a"],"state_sha256":"f116404493da2a46eb61dd01aac215a264817ec427707c8d9292a07ea87dd2b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1bki/MvLSIl2Dm5rwxZVMkteVIt46ol+mAPZxTZNU0euEWf8gA9zgSl1VrvG7iUXk24++OE6wrAvAXhuzsogAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T09:28:38.367892Z","bundle_sha256":"2c2f44d0cd52658aac054eb3217079ac0627471846c8381914104d3d1e50dc90"}}