{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:XGTZEEKVNTQNKRJF5PSPDA33X3","short_pith_number":"pith:XGTZEEKV","canonical_record":{"source":{"id":"1403.6530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6570276323de258861d8b17ec064662225a2656ee88a2ba6739aa59a8a384385","abstract_canon_sha256":"fd09e054e0cc83fd12e2483701ea6d877bf8263cb9e637c91b7f1525a990e939"},"schema_version":"1.0"},"canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","source":{"kind":"arxiv","id":"1403.6530","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.6530","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"1403.6530v2","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6530","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"XGTZEEKVNTQN","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"XGTZEEKVNTQNKRJF","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"XGTZEEKV","created_at":"2026-05-18T12:28:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:XGTZEEKVNTQNKRJF5PSPDA33X3","target":"record","payload":{"canonical_record":{"source":{"id":"1403.6530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6570276323de258861d8b17ec064662225a2656ee88a2ba6739aa59a8a384385","abstract_canon_sha256":"fd09e054e0cc83fd12e2483701ea6d877bf8263cb9e637c91b7f1525a990e939"},"schema_version":"1.0"},"canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:51.907974Z","signature_b64":"KXc/Bot7CfPvNKJUfJWM1c+RLflyLs8GKUpxn7XzdsZrIpbF+oytPyv2saAvs1ALW5Ca4lazylCaHNdMdgfUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","last_reissued_at":"2026-05-18T02:21:51.907418Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:51.907418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1403.6530","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CGr5q+2dBILiAk8RtuUPb1kFTN6Rad0UCpYkDInXKiPUKDCWV7EUqnaflGc0OT8RimYdoK9ou5SvT5b5hSNfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:47:41.697793Z"},"content_sha256":"8c739d95688473c4f4cd8fea95dd9ba50800ff8d292eb594619c85ded552f515","schema_version":"1.0","event_id":"sha256:8c739d95688473c4f4cd8fea95dd9ba50800ff8d292eb594619c85ded552f515"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:XGTZEEKVNTQNKRJF5PSPDA33X3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mohammad Ghavamzadeh, Prashanth L.A.","submitted_at":"2014-03-25T23:00:50Z","abstract_excerpt":"In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6530","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1Qc+M0Ek34ae24s+zeXjFMEerPmWvUq5xumwkXjby2JanBEALzgTVuee7ytRSmOJyafrSi6gmNWvgVOfobFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:47:41.698146Z"},"content_sha256":"b1fc266d18c59cbb36e14a2db96e68f6dcc24943d243339b403d2f833d7e5930","schema_version":"1.0","event_id":"sha256:b1fc266d18c59cbb36e14a2db96e68f6dcc24943d243339b403d2f833d7e5930"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/bundle.json","state_url":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T18:47:41Z","links":{"resolver":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3","bundle":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/bundle.json","state":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:XGTZEEKVNTQNKRJF5PSPDA33X3","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":"fd09e054e0cc83fd12e2483701ea6d877bf8263cb9e637c91b7f1525a990e939","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","title_canon_sha256":"6570276323de258861d8b17ec064662225a2656ee88a2ba6739aa59a8a384385"},"schema_version":"1.0","source":{"id":"1403.6530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.6530","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"1403.6530v2","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6530","created_at":"2026-05-18T02:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"XGTZEEKVNTQN","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"XGTZEEKVNTQNKRJF","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"XGTZEEKV","created_at":"2026-05-18T12:28:57Z"}],"graph_snapshots":[{"event_id":"sha256:b1fc266d18c59cbb36e14a2db96e68f6dcc24943d243339b403d2f833d7e5930","target":"graph","created_at":"2026-05-18T02:21:51Z","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"},"paper":{"abstract_excerpt":"In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For ea","authors_text":"Mohammad Ghavamzadeh, Prashanth L.A.","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","title":"Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6530","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":"sha256:8c739d95688473c4f4cd8fea95dd9ba50800ff8d292eb594619c85ded552f515","target":"record","created_at":"2026-05-18T02:21:51Z","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":"fd09e054e0cc83fd12e2483701ea6d877bf8263cb9e637c91b7f1525a990e939","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","title_canon_sha256":"6570276323de258861d8b17ec064662225a2656ee88a2ba6739aa59a8a384385"},"schema_version":"1.0","source":{"id":"1403.6530","kind":"arxiv","version":2}},"canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","first_computed_at":"2026-05-18T02:21:51.907418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:21:51.907418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXc/Bot7CfPvNKJUfJWM1c+RLflyLs8GKUpxn7XzdsZrIpbF+oytPyv2saAvs1ALW5Ca4lazylCaHNdMdgfUDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:21:51.907974Z","signed_message":"canonical_sha256_bytes"},"source_id":"1403.6530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c739d95688473c4f4cd8fea95dd9ba50800ff8d292eb594619c85ded552f515","sha256:b1fc266d18c59cbb36e14a2db96e68f6dcc24943d243339b403d2f833d7e5930"],"state_sha256":"5ce02dd5e3f5eef7be2e081416daa817285510a432c7aadf62d0f4a68fe0891c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NtK2XfZ/sL76cg1xhB+iBaN02X1d/M0vpRt6sEOwFxa0Aalp9+WZGDP20hr4SY83fL9goQgC0uk6FKE28gFqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:47:41.700501Z","bundle_sha256":"e9e116e1e05eaaf06836116087a0155afba49dc8117ce63b774f1d220071f7ed"}}