{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:NXSLIL7Y3XNITXUARMNY274ZLD","short_pith_number":"pith:NXSLIL7Y","canonical_record":{"source":{"id":"1301.0104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-01T16:25:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d87769ad4c8998f81b5fa4f4898c51b6f4544d51b8bf8aa4a274dc1b4a0fd77","abstract_canon_sha256":"6dba2db9470f695f56ac6da5c48f9950f4d8cf7eaf134a81dcc98caf53e2d385"},"schema_version":"1.0"},"canonical_sha256":"6de4b42ff8ddda89de808b1b8d7f9958d227df110fc857758df46981eabafe08","source":{"kind":"arxiv","id":"1301.0104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0104","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0104v1","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0104","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"NXSLIL7Y3XNI","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NXSLIL7Y3XNITXUA","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NXSLIL7Y","created_at":"2026-05-18T12:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:NXSLIL7Y3XNITXUARMNY274ZLD","target":"record","payload":{"canonical_record":{"source":{"id":"1301.0104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-01T16:25:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d87769ad4c8998f81b5fa4f4898c51b6f4544d51b8bf8aa4a274dc1b4a0fd77","abstract_canon_sha256":"6dba2db9470f695f56ac6da5c48f9950f4d8cf7eaf134a81dcc98caf53e2d385"},"schema_version":"1.0"},"canonical_sha256":"6de4b42ff8ddda89de808b1b8d7f9958d227df110fc857758df46981eabafe08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:37.145206Z","signature_b64":"SsS2jzmKv69NezkBtPu5VX1v0BhuzV2h39/w/x2j4nsDIUvlF6lwJOOQFb7vlBKUiIhXQDMA/yOaTmfc7jJ/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6de4b42ff8ddda89de808b1b8d7f9958d227df110fc857758df46981eabafe08","last_reissued_at":"2026-05-18T03:10:37.144556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:37.144556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.0104","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":"2026-05-18T03:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gigKTF8V5EuEma0m5XNHGNSUCIBj47l2DgXDmrgQvt1bkUnkpF/JG1w63gLwl//T+wbuD6A0slyKYIE4X6ZxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:52:48.928571Z"},"content_sha256":"445f96f89c1065d1ea13d12294c3bc53744ab68cb49b2067def318ae89e75efc","schema_version":"1.0","event_id":"sha256:445f96f89c1065d1ea13d12294c3bc53744ab68cb49b2067def318ae89e75efc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:NXSLIL7Y3XNITXUARMNY274ZLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Evaluation with Variance Related Risk Criteria in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Dotan Di Castro, Shie Mannor","submitted_at":"2013-01-01T16:25:17Z","abstract_excerpt":"In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose both TD(0) and LSTD(lambda) variants with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0104","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":"2026-05-18T03:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zShpRYYdvtT5zs7RH9YsKSN19M2YE3nBSiB6q5vg1BM8VqngOtHDAcGgis3Cegogacz9LUrFKvRpxJa6zjoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:52:48.929350Z"},"content_sha256":"15c6d30b56a457d82fc25a5e0b3d05538d6c8a352b55dca1dbac98011788cfe8","schema_version":"1.0","event_id":"sha256:15c6d30b56a457d82fc25a5e0b3d05538d6c8a352b55dca1dbac98011788cfe8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXSLIL7Y3XNITXUARMNY274ZLD/bundle.json","state_url":"https://pith.science/pith/NXSLIL7Y3XNITXUARMNY274ZLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXSLIL7Y3XNITXUARMNY274ZLD/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":"2026-05-31T03:52:48Z","links":{"resolver":"https://pith.science/pith/NXSLIL7Y3XNITXUARMNY274ZLD","bundle":"https://pith.science/pith/NXSLIL7Y3XNITXUARMNY274ZLD/bundle.json","state":"https://pith.science/pith/NXSLIL7Y3XNITXUARMNY274ZLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXSLIL7Y3XNITXUARMNY274ZLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:NXSLIL7Y3XNITXUARMNY274ZLD","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":"6dba2db9470f695f56ac6da5c48f9950f4d8cf7eaf134a81dcc98caf53e2d385","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-01T16:25:17Z","title_canon_sha256":"1d87769ad4c8998f81b5fa4f4898c51b6f4544d51b8bf8aa4a274dc1b4a0fd77"},"schema_version":"1.0","source":{"id":"1301.0104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0104","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0104v1","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0104","created_at":"2026-05-18T03:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"NXSLIL7Y3XNI","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NXSLIL7Y3XNITXUA","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NXSLIL7Y","created_at":"2026-05-18T12:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:15c6d30b56a457d82fc25a5e0b3d05538d6c8a352b55dca1dbac98011788cfe8","target":"graph","created_at":"2026-05-18T03:10:37Z","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 this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose both TD(0) and LSTD(lambda) variants with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.","authors_text":"Aviv Tamar, Dotan Di Castro, Shie Mannor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-01T16:25:17Z","title":"Policy Evaluation with Variance Related Risk Criteria in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0104","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":"sha256:445f96f89c1065d1ea13d12294c3bc53744ab68cb49b2067def318ae89e75efc","target":"record","created_at":"2026-05-18T03:10:37Z","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":"6dba2db9470f695f56ac6da5c48f9950f4d8cf7eaf134a81dcc98caf53e2d385","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-01T16:25:17Z","title_canon_sha256":"1d87769ad4c8998f81b5fa4f4898c51b6f4544d51b8bf8aa4a274dc1b4a0fd77"},"schema_version":"1.0","source":{"id":"1301.0104","kind":"arxiv","version":1}},"canonical_sha256":"6de4b42ff8ddda89de808b1b8d7f9958d227df110fc857758df46981eabafe08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6de4b42ff8ddda89de808b1b8d7f9958d227df110fc857758df46981eabafe08","first_computed_at":"2026-05-18T03:10:37.144556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:37.144556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsS2jzmKv69NezkBtPu5VX1v0BhuzV2h39/w/x2j4nsDIUvlF6lwJOOQFb7vlBKUiIhXQDMA/yOaTmfc7jJ/Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:37.145206Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.0104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:445f96f89c1065d1ea13d12294c3bc53744ab68cb49b2067def318ae89e75efc","sha256:15c6d30b56a457d82fc25a5e0b3d05538d6c8a352b55dca1dbac98011788cfe8"],"state_sha256":"c6f198d53c03bc9fa63e386da189aabeb7cc8db82b71749b847963cd6e84970f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HdHj9aETeo7QOY9qfPQW+eUXVUx0XWh6q6ljYp4Ar0pZm47fmKe94NqwrOiF5oq9Qa0ZQd+ICAzR9k6oiS8SBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:52:48.932927Z","bundle_sha256":"d3a040eb465ca4a4151d557480d767166d48ae293cb916f44c3b381d3fc540db"}}