{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:D6RO276QCSD3WWXVZ6BXGJWFZT","short_pith_number":"pith:D6RO276Q","canonical_record":{"source":{"id":"1104.5601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-04-29T11:39:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5ed8343c879fdf656beb9e539b0c0e292f68d74a9072b5a1fb218b34b2fc65d","abstract_canon_sha256":"32096ccc662f412eea0473cc48ca5d2ee5050b4435cfb0224649364cbac00a47"},"schema_version":"1.0"},"canonical_sha256":"1fa2ed7fd01487bb5af5cf837326c5ccd8a960ea1b7adfec69eb5a2bc5fa8dc5","source":{"kind":"arxiv","id":"1104.5601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1104.5601","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"1104.5601v1","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1104.5601","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"D6RO276QCSD3","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"D6RO276QCSD3WWXV","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"D6RO276Q","created_at":"2026-05-18T12:26:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:D6RO276QCSD3WWXVZ6BXGJWFZT","target":"record","payload":{"canonical_record":{"source":{"id":"1104.5601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-04-29T11:39:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5ed8343c879fdf656beb9e539b0c0e292f68d74a9072b5a1fb218b34b2fc65d","abstract_canon_sha256":"32096ccc662f412eea0473cc48ca5d2ee5050b4435cfb0224649364cbac00a47"},"schema_version":"1.0"},"canonical_sha256":"1fa2ed7fd01487bb5af5cf837326c5ccd8a960ea1b7adfec69eb5a2bc5fa8dc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:23:20.698126Z","signature_b64":"BM3Z1Cb/hrEhH+Czm6AocQkE+ltPh6gaKfP+osVXVmtIuu+DD8jXIxXEElFPXprhzx5qMtLhS+tEVBvXOQKEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fa2ed7fd01487bb5af5cf837326c5ccd8a960ea1b7adfec69eb5a2bc5fa8dc5","last_reissued_at":"2026-05-18T04:23:20.697694Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:23:20.697694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1104.5601","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLkrh7j3B0NsSuIyUxyotZmmU6YK3BafgIGUcoELhudn7aOelKWSgCLqI0hDeMZMLZzcx65CrDUsTnwbPjb/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:10:05.404150Z"},"content_sha256":"ff73595dcb5f826411cde00bebee6a55f8053cb472c56659bf14d6d762d1c0f8","schema_version":"1.0","event_id":"sha256:ff73595dcb5f826411cde00bebee6a55f8053cb472c56659bf14d6d762d1c0f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:D6RO276QCSD3WWXVZ6BXGJWFZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mean-Variance Optimization in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John Tsitsiklis, Shie Mannor","submitted_at":"2011-04-29T11:39:40Z","abstract_excerpt":"We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1104.5601","kind":"arxiv","version":1},"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":"2026-05-18T04:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"642ENauqqroFs7ueNtMm039cl7ZBZNj9XFgZ9xUQHc6KWIkINekjpa9hhnyFWsCAAYzP3/Kly5FnVKomBqT5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:10:05.404771Z"},"content_sha256":"2386972677c621edfa7372c35e7403158e4ada5d85cbe4824d9a80bb2012e661","schema_version":"1.0","event_id":"sha256:2386972677c621edfa7372c35e7403158e4ada5d85cbe4824d9a80bb2012e661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/bundle.json","state_url":"https://pith.science/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/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":"2026-05-31T06:10:05Z","links":{"resolver":"https://pith.science/pith/D6RO276QCSD3WWXVZ6BXGJWFZT","bundle":"https://pith.science/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/bundle.json","state":"https://pith.science/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6RO276QCSD3WWXVZ6BXGJWFZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:D6RO276QCSD3WWXVZ6BXGJWFZT","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":"32096ccc662f412eea0473cc48ca5d2ee5050b4435cfb0224649364cbac00a47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-04-29T11:39:40Z","title_canon_sha256":"e5ed8343c879fdf656beb9e539b0c0e292f68d74a9072b5a1fb218b34b2fc65d"},"schema_version":"1.0","source":{"id":"1104.5601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1104.5601","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"1104.5601v1","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1104.5601","created_at":"2026-05-18T04:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"D6RO276QCSD3","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"D6RO276QCSD3WWXV","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"D6RO276Q","created_at":"2026-05-18T12:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:2386972677c621edfa7372c35e7403158e4ada5d85cbe4824d9a80bb2012e661","target":"graph","created_at":"2026-05-18T04:23:20Z","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"},"paper":{"abstract_excerpt":"We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms.","authors_text":"John Tsitsiklis, Shie Mannor","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-04-29T11:39:40Z","title":"Mean-Variance Optimization in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1104.5601","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:ff73595dcb5f826411cde00bebee6a55f8053cb472c56659bf14d6d762d1c0f8","target":"record","created_at":"2026-05-18T04:23:20Z","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":"32096ccc662f412eea0473cc48ca5d2ee5050b4435cfb0224649364cbac00a47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-04-29T11:39:40Z","title_canon_sha256":"e5ed8343c879fdf656beb9e539b0c0e292f68d74a9072b5a1fb218b34b2fc65d"},"schema_version":"1.0","source":{"id":"1104.5601","kind":"arxiv","version":1}},"canonical_sha256":"1fa2ed7fd01487bb5af5cf837326c5ccd8a960ea1b7adfec69eb5a2bc5fa8dc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fa2ed7fd01487bb5af5cf837326c5ccd8a960ea1b7adfec69eb5a2bc5fa8dc5","first_computed_at":"2026-05-18T04:23:20.697694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:23:20.697694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BM3Z1Cb/hrEhH+Czm6AocQkE+ltPh6gaKfP+osVXVmtIuu+DD8jXIxXEElFPXprhzx5qMtLhS+tEVBvXOQKEAg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:23:20.698126Z","signed_message":"canonical_sha256_bytes"},"source_id":"1104.5601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff73595dcb5f826411cde00bebee6a55f8053cb472c56659bf14d6d762d1c0f8","sha256:2386972677c621edfa7372c35e7403158e4ada5d85cbe4824d9a80bb2012e661"],"state_sha256":"fd45dd2e1252a242e551c3b41f3fc7f3fa599d8b562edaca2068f1dc2cebcd64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7zGnWxL5MSZmKiEuuPFb2dORLoccbeX4NMC39Gnql7tKYxHzDQnSkwbG7+bc8/Of3neDr0jzqwUMi0ujgb9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:10:05.408701Z","bundle_sha256":"70331cbb89aeb0e615e5d3f1b87fdd3ada6df78ce2e4a94ba84425678e9af28b"}}