{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2PW4MWMSGOIUKMR7PE636VL4UZ","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":"c768e39e74bb28446311f693e5920e5b49ad7d025dbe126b0817c908f18ce159","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:00:21Z","title_canon_sha256":"e56a190c491f241808721782b45960deb92edd80caf25a89c08626d48905a4d6"},"schema_version":"1.0","source":{"id":"2412.05334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05334","created_at":"2026-07-05T10:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05334v2","created_at":"2026-07-05T10:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05334","created_at":"2026-07-05T10:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"2PW4MWMSGOIU","created_at":"2026-07-05T10:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"2PW4MWMSGOIUKMR7","created_at":"2026-07-05T10:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"2PW4MWMS","created_at":"2026-07-05T10:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:fd52cef284261003535aba08b068e29099329a1c45d07d67f15c151b8574a23c","target":"graph","created_at":"2026-07-05T10:30:59Z","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/2412.05334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop, faithfully recovers the joint distribution of trajectories observed in the real world. Inspired by large language models, tokenized multi-agent policies have recently become the state-of-the-art in traffic simulation. However, they are typically trained through open-loop behavior cloning, and thus suffer from covariate shift when executed in closed-loop during simulation. In this work, we present Closest Among Top-K (CAT-K) rollouts, a simple yet effective closed-loop fine-tuning strategy to mitiga","authors_text":"Boris Ivanovic, Marco Pavone, Maximilian Igl, Peter Karkus, Wenhao Ding, Yuxiao Chen, Zhejun Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:00:21Z","title":"Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05334","kind":"arxiv","version":2},"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:be1e8f7cd0ff3eafd1ca8d76f01acd08e5cdcbbe383cefce84ff1989664afa78","target":"record","created_at":"2026-07-05T10:30:59Z","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":"c768e39e74bb28446311f693e5920e5b49ad7d025dbe126b0817c908f18ce159","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T21:00:21Z","title_canon_sha256":"e56a190c491f241808721782b45960deb92edd80caf25a89c08626d48905a4d6"},"schema_version":"1.0","source":{"id":"2412.05334","kind":"arxiv","version":2}},"canonical_sha256":"d3edc65992339145323f793dbf557ca66cfc6d6c45064e79159fee58e24b3028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3edc65992339145323f793dbf557ca66cfc6d6c45064e79159fee58e24b3028","first_computed_at":"2026-07-05T10:30:59.113755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:59.113755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ZlEsQG1ZILLq0VtuWOIcORPBas3KiqarcCPuLAqms27fpcTFmWuujLTUmuttJMlvgZCtiKLufAuDh3zcjrRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:59.114452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be1e8f7cd0ff3eafd1ca8d76f01acd08e5cdcbbe383cefce84ff1989664afa78","sha256:fd52cef284261003535aba08b068e29099329a1c45d07d67f15c151b8574a23c"],"state_sha256":"24cd92073069886e9b7144d9064107dcc3cac247191a3b2e0d0d24bcd6f938aa"}