{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M2OUD657TYWKUIZG443AIQFKI7","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":"6089c838b478a5b40a554f5dfd94ed7ef7f93dce9380f97322994b55976f5889","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T08:33:08Z","title_canon_sha256":"d883e25790f951a786ec05d241d403ad27ba7dc0970be1b5099c2832adb8e20a"},"schema_version":"1.0","source":{"id":"2301.11592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11592","created_at":"2026-07-05T07:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11592v2","created_at":"2026-07-05T07:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11592","created_at":"2026-07-05T07:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"M2OUD657TYWK","created_at":"2026-07-05T07:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"M2OUD657TYWKUIZG","created_at":"2026-07-05T07:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"M2OUD657","created_at":"2026-07-05T07:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:561ab7ab88be8235943c2804d74e08cb58097ad61e85d4d0927f1ed1563f30e4","target":"graph","created_at":"2026-07-05T07:33:10Z","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/2301.11592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constrained Reinforcement Learning has been employed to enforce safety constraints on policy through the use of expected cost constraints. The key challenge is in handling expected cost accumulated using the policy and not just in a single step. Existing methods have developed innovative ways of converting this cost constraint over entire policy to constraints over local decisions (at each time step). While such approaches have provided good solutions with regards to objective, they can either be overly aggressive or conservative with respect to costs. This is owing to use of estimates for \"fu","authors_text":"Hao Jiang, Minh Huy Hoang, Pradeep Varakantham, Tien Mai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T08:33:08Z","title":"Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11592","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":"sha256:4e1777ec2a823d8349160671736b82214eef13036d8f5dcaddde934dfe3c512e","target":"record","created_at":"2026-07-05T07:33:10Z","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":"6089c838b478a5b40a554f5dfd94ed7ef7f93dce9380f97322994b55976f5889","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T08:33:08Z","title_canon_sha256":"d883e25790f951a786ec05d241d403ad27ba7dc0970be1b5099c2832adb8e20a"},"schema_version":"1.0","source":{"id":"2301.11592","kind":"arxiv","version":2}},"canonical_sha256":"669d41fbbf9e2caa2326e7360440aa47c20fd24db2a1aef0b525b4d953625de7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"669d41fbbf9e2caa2326e7360440aa47c20fd24db2a1aef0b525b4d953625de7","first_computed_at":"2026-07-05T07:33:10.636747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:10.636747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HtW7tKLObLEI7U5fesf6WE4mnlY7UT5YbtLeFzQv4Z8w3FEcv9dFWrF5B6dZxnJGcStUM0x7PJCa0yI4mfryAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:10.637288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e1777ec2a823d8349160671736b82214eef13036d8f5dcaddde934dfe3c512e","sha256:561ab7ab88be8235943c2804d74e08cb58097ad61e85d4d0927f1ed1563f30e4"],"state_sha256":"413d7c1d557475b2e236af8688a8bd8de6695ead7399a73e1552f99200491e21"}