{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F46R2GUG7RR2U2WSTV4N4FXHT4","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":"5e68687496c933b34fca4d7fba53da06cf972a76ca27475749a684d91bb9c0c1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T16:53:56Z","title_canon_sha256":"ea6d12f515aaad2d938c81f77fc24541bbc9396b8d78acd9e2cd5db7b9d1ce3e"},"schema_version":"1.0","source":{"id":"2201.12243","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12243","created_at":"2026-07-05T05:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12243v2","created_at":"2026-07-05T05:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12243","created_at":"2026-07-05T05:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"F46R2GUG7RR2","created_at":"2026-07-05T05:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"F46R2GUG7RR2U2WS","created_at":"2026-07-05T05:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"F46R2GUG","created_at":"2026-07-05T05:52:51Z"}],"graph_snapshots":[{"event_id":"sha256:070a0c0a509da6e71e13becd3f7b26fe9849e6fd0c5d769148f44a86265be5bc","target":"graph","created_at":"2026-07-05T05:52:51Z","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/2201.12243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal verification \\emph{after} the controller has been learned, it is sometimes difficult to obtain any certificate, even after many iterations between learning and verification. To address this challenge, we propose a framework that jointly conducts reinforcement learning and formal verification by formulating and solving a novel bilevel optimization problem, which","authors_text":"Chao Huang, Qi Zhu, Simon Zhan, Yixuan Wang, Zhaoran Wang, Zhilu Wang, Zhuoran Yang","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T16:53:56Z","title":"Joint Differentiable Optimization and Verification for Certified Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12243","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":"sha256:805d05e961d2ddecb8f0b21b99148488d98c9758b87d5c51ac19df7dd9715278","target":"record","created_at":"2026-07-05T05:52:51Z","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":"5e68687496c933b34fca4d7fba53da06cf972a76ca27475749a684d91bb9c0c1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T16:53:56Z","title_canon_sha256":"ea6d12f515aaad2d938c81f77fc24541bbc9396b8d78acd9e2cd5db7b9d1ce3e"},"schema_version":"1.0","source":{"id":"2201.12243","kind":"arxiv","version":2}},"canonical_sha256":"2f3d1d1a86fc63aa6ad29d78de16e79f33d989e6e068e001e9daea81f7657d38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f3d1d1a86fc63aa6ad29d78de16e79f33d989e6e068e001e9daea81f7657d38","first_computed_at":"2026-07-05T05:52:51.863542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:51.863542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYE+YReoqn8nhb/g9O8kjW5HHxpUPmVEA1BwN2bkNgOsecM/3FMCr3nIFyddwxCAXwEW3eHVwYCHM5v/SoqTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:51.864010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12243","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:805d05e961d2ddecb8f0b21b99148488d98c9758b87d5c51ac19df7dd9715278","sha256:070a0c0a509da6e71e13becd3f7b26fe9849e6fd0c5d769148f44a86265be5bc"],"state_sha256":"4a2792b214e47bb1688fbaa9dafedcfee086ddddec6c341c0d567f2685443664"}