{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SXF7B6M6QURY5A2PDQA5CUPQM2","short_pith_number":"pith:SXF7B6M6","schema_version":"1.0","canonical_sha256":"95cbf0f99e85238e834f1c01d151f0668e1d9e94136e417a8f90b3a6a686001b","source":{"kind":"arxiv","id":"2605.19033","version":1},"attestation_state":"computed","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, "},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.19033","created_at":"2026-05-20T01:05:21.351989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19033v1","created_at":"2026-05-20T01:05:21.351989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19033","created_at":"2026-05-20T01:05:21.351989+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXF7B6M6QURY","created_at":"2026-05-20T01:05:21.351989+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXF7B6M6QURY5A2P","created_at":"2026-05-20T01:05:21.351989+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXF7B6M6","created_at":"2026-05-20T01:05:21.351989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2","json":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2.json","graph_json":"https://pith.science/api/pith-number/SXF7B6M6QURY5A2PDQA5CUPQM2/graph.json","events_json":"https://pith.science/api/pith-number/SXF7B6M6QURY5A2PDQA5CUPQM2/events.json","paper":"https://pith.science/paper/SXF7B6M6"},"agent_actions":{"view_html":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2","download_json":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2.json","view_paper":"https://pith.science/paper/SXF7B6M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19033&json=true","fetch_graph":"https://pith.science/api/pith-number/SXF7B6M6QURY5A2PDQA5CUPQM2/graph.json","fetch_events":"https://pith.science/api/pith-number/SXF7B6M6QURY5A2PDQA5CUPQM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/action/storage_attestation","attest_author":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/action/author_attestation","sign_citation":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/action/citation_signature","submit_replication":"https://pith.science/pith/SXF7B6M6QURY5A2PDQA5CUPQM2/action/replication_record"}},"created_at":"2026-05-20T01:05:21.351989+00:00","updated_at":"2026-05-20T01:05:21.351989+00:00"}