{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3MRXIZVPDUPFUU5XWJOUQXO7UG","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":"294c08dbca4c2516e1e6308899e97f5dd7c395a0ca8398d228456c7e14278572","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-29T02:10:19Z","title_canon_sha256":"500d15a03829db62524665bcb3fb665c5696c3ebf13fc0c6efbb156559c0c37b"},"schema_version":"1.0","source":{"id":"2403.19918","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19918","created_at":"2026-07-05T09:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19918v3","created_at":"2026-07-05T09:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19918","created_at":"2026-07-05T09:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"3MRXIZVPDUPF","created_at":"2026-07-05T09:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"3MRXIZVPDUPFUU5X","created_at":"2026-07-05T09:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"3MRXIZVP","created_at":"2026-07-05T09:20:22Z"}],"graph_snapshots":[{"event_id":"sha256:5b7f01319042fdf257a40fce9a6512f314128624d375ef937c2e4ab4b2e56456","target":"graph","created_at":"2026-07-05T09:20:22Z","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/2403.19918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However, agents replayed from offline data are not reactive and hard to intuitively control. Existing approaches address these challenges by proposing methods that rely on heuristics or generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned off","authors_text":"Anthony Gosselin, Bruno Carrez, Christopher Pal, Felix Heide, Florian Golemo, Liam Paull, Luke Rowe, Roger Girgis","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-29T02:10:19Z","title":"CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19918","kind":"arxiv","version":3},"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":"sha256:20e330a951d7e6353326cef11f9e63fd4a34b916f04762c4bd561b871caa59a5","target":"record","created_at":"2026-07-05T09:20:22Z","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":"294c08dbca4c2516e1e6308899e97f5dd7c395a0ca8398d228456c7e14278572","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-29T02:10:19Z","title_canon_sha256":"500d15a03829db62524665bcb3fb665c5696c3ebf13fc0c6efbb156559c0c37b"},"schema_version":"1.0","source":{"id":"2403.19918","kind":"arxiv","version":3}},"canonical_sha256":"db237466af1d1e5a53b7b25d485ddfa1ae59fa373437e22b202f147a0623c377","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db237466af1d1e5a53b7b25d485ddfa1ae59fa373437e22b202f147a0623c377","first_computed_at":"2026-07-05T09:20:22.898943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:22.898943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+VcBsTh5Sm+Zr/Rr7NKH+G/vi3QWhxFPRI0BLQAzeA9anAZuYUdyBwjrp8zo6zF6kwm45h5DP3ji4TDLaVjKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:22.899453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19918","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20e330a951d7e6353326cef11f9e63fd4a34b916f04762c4bd561b871caa59a5","sha256:5b7f01319042fdf257a40fce9a6512f314128624d375ef937c2e4ab4b2e56456"],"state_sha256":"7c806bb008d1179dcaa3189d88ef9b5df59e525b3f77e4f812ea487cd89b2146"}