{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I5HTDUWEUG6YW7PUHPLGJH5PFM","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":"2da97212dcb69c649823788b05eb2d42557a3235ca1e23597eabb046972c52f0","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T13:21:00Z","title_canon_sha256":"43af6f06717caa430cbc3385174cd0a2a807e9b5bb1741f852085706013d194a"},"schema_version":"1.0","source":{"id":"2209.10341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10341","created_at":"2026-07-05T04:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10341v1","created_at":"2026-07-05T04:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10341","created_at":"2026-07-05T04:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"I5HTDUWEUG6Y","created_at":"2026-07-05T04:59:47Z"},{"alias_kind":"pith_short_16","alias_value":"I5HTDUWEUG6YW7PU","created_at":"2026-07-05T04:59:47Z"},{"alias_kind":"pith_short_8","alias_value":"I5HTDUWE","created_at":"2026-07-05T04:59:47Z"}],"graph_snapshots":[{"event_id":"sha256:e718b5ef79414a3998e3b8db2ec756f7e11ea5c808aa124a1275f6b9f84c4dc6","target":"graph","created_at":"2026-07-05T04:59:47Z","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/2209.10341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LCRL is a software tool that implements model-free Reinforcement Learning (RL) algorithms over unknown Markov Decision Processes (MDPs), synthesising policies that satisfy a given linear temporal specification with maximal probability. LCRL leverages partially deterministic finite-state machines known as Limit Deterministic Buchi Automata (LDBA) to express a given linear temporal specification. A reward function for the RL algorithm is shaped on-the-fly, based on the structure of the LDBA. Theoretical guarantees under proper assumptions ensure the convergence of the RL algorithm to an optimal ","authors_text":"Alessandro Abate, Daniel Kroening, Hosein Hasanbeig","cross_cats":["cs.AI","cs.LO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T13:21:00Z","title":"LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10341","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:d131d333ad40a9edad76a8f49028acc9bfe3731269eea9932ee5f053ff03a9ac","target":"record","created_at":"2026-07-05T04:59:47Z","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":"2da97212dcb69c649823788b05eb2d42557a3235ca1e23597eabb046972c52f0","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T13:21:00Z","title_canon_sha256":"43af6f06717caa430cbc3385174cd0a2a807e9b5bb1741f852085706013d194a"},"schema_version":"1.0","source":{"id":"2209.10341","kind":"arxiv","version":1}},"canonical_sha256":"474f31d2c4a1bd8b7df43bd6649faf2b20f8da0063745ad989b04dc5fc3e641a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"474f31d2c4a1bd8b7df43bd6649faf2b20f8da0063745ad989b04dc5fc3e641a","first_computed_at":"2026-07-05T04:59:47.918042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:47.918042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVzu0EJhlizggWSIap1dN2gZol5gNRU2hlcEbnsk4O4CQRqqZt/f6p8gZnylsSzKIkVas8vJR47XOfA6yBCNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:47.918477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d131d333ad40a9edad76a8f49028acc9bfe3731269eea9932ee5f053ff03a9ac","sha256:e718b5ef79414a3998e3b8db2ec756f7e11ea5c808aa124a1275f6b9f84c4dc6"],"state_sha256":"b4f7819444e8e75fb324fb1ac6204989ad89e65fcacf0451a064d0f17decd27c"}