{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EPDCMMR6PUDDNH4FNCUSLD7F4E","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":"e21cf8977bb5e72eeadb8cd1713781decd61d897574038d33a2f0bd6f5286511","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-01T10:24:54Z","title_canon_sha256":"3831853accf70cbc06703ee3f7752744575fc219384bc68ae8d71247af6987b2"},"schema_version":"1.0","source":{"id":"2504.00626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00626","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00626v2","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00626","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"EPDCMMR6PUDD","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_16","alias_value":"EPDCMMR6PUDDNH4F","created_at":"2026-07-05T11:44:47Z"},{"alias_kind":"pith_short_8","alias_value":"EPDCMMR6","created_at":"2026-07-05T11:44:47Z"}],"graph_snapshots":[{"event_id":"sha256:ffcf8e6e7ae22a3d035135eaa9639540568739e0200c0000907b3e1873c6bf0d","target":"graph","created_at":"2026-07-05T11:44:47Z","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/2504.00626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a sample-based, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. To approximate the effects of stochasticies in the optimal control formulation and to fulfil the probabilistic CBF condition, a sample-based approach with guarantees is employed. Furthermore, to counterba","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-01T10:24:54Z","title":"Probabilistically safe and efficient model-based reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00626","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":"sha256:47c29759388c1482ce9382843397a95290e946f1e56517e5b2b2d2fd07eac77d","target":"record","created_at":"2026-07-05T11:44:47Z","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":"e21cf8977bb5e72eeadb8cd1713781decd61d897574038d33a2f0bd6f5286511","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-01T10:24:54Z","title_canon_sha256":"3831853accf70cbc06703ee3f7752744575fc219384bc68ae8d71247af6987b2"},"schema_version":"1.0","source":{"id":"2504.00626","kind":"arxiv","version":2}},"canonical_sha256":"23c626323e7d06369f8568a9258fe5e10a5e0cdbf9785d44677df197069a1323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23c626323e7d06369f8568a9258fe5e10a5e0cdbf9785d44677df197069a1323","first_computed_at":"2026-07-05T11:44:47.400162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:47.400162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OxL4FD28/ZTxt9qbwJjgTb60t65+vx/o/+TtRfJH1Dd1KHovukJK19PJRy/Mtjymo7leb5z6fnYvAcnps+q7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:47.400812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47c29759388c1482ce9382843397a95290e946f1e56517e5b2b2d2fd07eac77d","sha256:ffcf8e6e7ae22a3d035135eaa9639540568739e0200c0000907b3e1873c6bf0d"],"state_sha256":"6d14e68c2a3e64021c287b0eab37656a2bac6c9147f9e639fcfcef512d689d3c"}