{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R7BUROFFVQYDTC5CK7ILYX4DNW","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":"520470e44e2dc95ea89ace45b26927215daefbda3380f58ec9730bc26962e73f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-27T13:36:36Z","title_canon_sha256":"e2090a241e3a9125e640d82a863de49c4c5736e252cfa2b29cb45ea790650c58"},"schema_version":"1.0","source":{"id":"2002.12086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12086","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12086v1","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12086","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"R7BUROFFVQYD","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"R7BUROFFVQYDTC5C","created_at":"2026-07-05T00:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"R7BUROFF","created_at":"2026-07-05T00:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:cee6a62cd88d87011d4564db10333a1fe3bc96aeec6908aeae1261d57efefa10","target":"graph","created_at":"2026-07-05T00:44:20Z","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/2002.12086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which ignores low probability catastrophic events withhighly negative impact on the system. On the other hand,risk-averse policies require the probability of undesirableevents to be below a given threshold, but they do not accountfor optimization of the expected payoff. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes","authors_text":"Jiri Vahala, Krishnendu Chatterjee, Petr Novotny, Tomas Brazdil","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-27T13:36:36Z","title":"Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12086","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":"sha256:2ac1552867d031793a207c3b4faa62262f540607f5182b913584ce14dff59826","target":"record","created_at":"2026-07-05T00:44:20Z","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":"520470e44e2dc95ea89ace45b26927215daefbda3380f58ec9730bc26962e73f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-02-27T13:36:36Z","title_canon_sha256":"e2090a241e3a9125e640d82a863de49c4c5736e252cfa2b29cb45ea790650c58"},"schema_version":"1.0","source":{"id":"2002.12086","kind":"arxiv","version":1}},"canonical_sha256":"8fc348b8a5ac30398ba257d0bc5f836dbef9a58784dcd9b5ef682113d758cccf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fc348b8a5ac30398ba257d0bc5f836dbef9a58784dcd9b5ef682113d758cccf","first_computed_at":"2026-07-05T00:44:20.288415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:20.288415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ps1Z2tTteY1Ht1JoBxbehXNpgV8hcjmozT80+O3v4DubRKizYGdI/uRzAI4uxKR2ImlnSGwaKhalgMBQtTlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:20.288828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ac1552867d031793a207c3b4faa62262f540607f5182b913584ce14dff59826","sha256:cee6a62cd88d87011d4564db10333a1fe3bc96aeec6908aeae1261d57efefa10"],"state_sha256":"c70c52bf060e494efc2824cd630e9c06efc9b6bebbf88d56fbd8c1d88452439d"}