{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:64FOZWIWFANZ7ELEYYTC2J343Y","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":"20e698ab355faff7c79b2936a6a8db0e5c443f7112c3830693f4441e351cc079","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-21T13:10:58Z","title_canon_sha256":"dabec740dcc527d5f584229e119492245079f884eacdf55efa4308c3781b5add"},"schema_version":"1.0","source":{"id":"2402.13785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13785","created_at":"2026-07-05T10:27:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13785v2","created_at":"2026-07-05T10:27:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13785","created_at":"2026-07-05T10:27:07Z"},{"alias_kind":"pith_short_12","alias_value":"64FOZWIWFANZ","created_at":"2026-07-05T10:27:07Z"},{"alias_kind":"pith_short_16","alias_value":"64FOZWIWFANZ7ELE","created_at":"2026-07-05T10:27:07Z"},{"alias_kind":"pith_short_8","alias_value":"64FOZWIW","created_at":"2026-07-05T10:27:07Z"}],"graph_snapshots":[{"event_id":"sha256:cbe7037ce7e0612d50cd29fec528831ef723b0f14f48919f2bf3c8e1eb749745","target":"graph","created_at":"2026-07-05T10:27:07Z","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/2402.13785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel framework to controller design in environments with a two-level structure: a known high-level graph (\"map\") in which each vertex is populated by a Markov decision process, called a \"room\". The framework \"separates concerns\" by using different design techniques for low- and high-level tasks. We apply reactive synthesis for high-level tasks: given a specification as a logical formula over the high-level graph and a collection of low-level policies obtained together with \"concise\" latent structures, we construct a \"planner\" that selects which low-level policy to apply in each r","authors_text":"Anna Lukina, Ann Now\\'e, Christian Schilling, Florent Delgrange, Guillermo A. P\\'erez, Guy Avni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-21T13:10:58Z","title":"Composing Reinforcement Learning Policies, with Formal Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13785","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":"sha256:1798842d9bb0728f9cd231c1ce28fa18dcb2898847f42b7f5c4e1d295189f4b4","target":"record","created_at":"2026-07-05T10:27:07Z","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":"20e698ab355faff7c79b2936a6a8db0e5c443f7112c3830693f4441e351cc079","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-21T13:10:58Z","title_canon_sha256":"dabec740dcc527d5f584229e119492245079f884eacdf55efa4308c3781b5add"},"schema_version":"1.0","source":{"id":"2402.13785","kind":"arxiv","version":2}},"canonical_sha256":"f70aecd916281b9f9164c6262d277cde3e312ead492ed2009d176515ccf07942","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f70aecd916281b9f9164c6262d277cde3e312ead492ed2009d176515ccf07942","first_computed_at":"2026-07-05T10:27:07.870659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:07.870659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"825nbsK8Raq5WNtKs5BZLCgyiIyS3fhs7AkrlccMKhYbWT6WHqDh1vTVxESN/w4EOFvppyxaRRREdDMZtxoACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:07.871200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1798842d9bb0728f9cd231c1ce28fa18dcb2898847f42b7f5c4e1d295189f4b4","sha256:cbe7037ce7e0612d50cd29fec528831ef723b0f14f48919f2bf3c8e1eb749745"],"state_sha256":"f397f80446337382cecbbad523e562347f0dd771162d4971ba3d9b1d70f3c266"}