{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5ICT36MXQ5MBXQXG22QAGLIMY2","short_pith_number":"pith:5ICT36MX","canonical_record":{"source":{"id":"1604.05257","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"8971ea8489b4460e6226be6a1ee3f02479f867261789d4decb5021082268e061","abstract_canon_sha256":"30af60d665872aafe836b523f1c09ddf18ae09a7a16c710c763bd36314b6c3df"},"schema_version":"1.0"},"canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","source":{"kind":"arxiv","id":"1604.05257","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.05257","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"1604.05257v3","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.05257","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"5ICT36MXQ5MB","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5ICT36MXQ5MBXQXG","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5ICT36MX","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5ICT36MXQ5MBXQXG22QAGLIMY2","target":"record","payload":{"canonical_record":{"source":{"id":"1604.05257","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"8971ea8489b4460e6226be6a1ee3f02479f867261789d4decb5021082268e061","abstract_canon_sha256":"30af60d665872aafe836b523f1c09ddf18ae09a7a16c710c763bd36314b6c3df"},"schema_version":"1.0"},"canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:04.466978Z","signature_b64":"Vb6u5JB8PigfCsJKnuyKS5YqKPtnzZncddBHZi2eMUUkctvMIU5wIOTkkJvGCEkRrbdbi/Ig2E5p/9F+iT8vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","last_reissued_at":"2026-05-18T00:38:04.466289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:04.466289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.05257","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZwNPUNE05Mnl3UU5HaS0iFGJmvc1XDKcNnS1GNEmtQeLpovhdk3QyyWFxH3lF8JhANs1a9K+ZKMnpsbUqxEnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:32:11.617376Z"},"content_sha256":"becd11f48a79cc72e575a86d4a0659a67859464274212652b537f150bdb9adae","schema_version":"1.0","event_id":"sha256:becd11f48a79cc72e575a86d4a0659a67859464274212652b537f150bdb9adae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5ICT36MXQ5MBXQXG22QAGLIMY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qing Zhao, Sattar Vakili","submitted_at":"2016-04-18T17:28:41Z","abstract_excerpt":"The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel results under the measure of mean-variance, a commonly adopted risk measure in economics and mathematical finance. We show that the model-specific regret and the model-independent regret in terms of the mean-variance of the reward process are lower bounded by $\\Omega(\\log T)$ and $\\Omega(T^{2/3})$, respectively. We then show that variations of the UCB policy and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.05257","kind":"arxiv","version":3},"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":"2026-05-18T00:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0L4mJbyTob09XxQqCQw31Dxeqj1J9GqmPLHEXK+HnxVnD0qv5onOGylG4jvbhzY383qyV8ruOiJt1PNUSIdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:32:11.618067Z"},"content_sha256":"8a6da3d3c7ab9eaecef132778313523967d1200eed4550b12693a4eab6426130","schema_version":"1.0","event_id":"sha256:8a6da3d3c7ab9eaecef132778313523967d1200eed4550b12693a4eab6426130"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/bundle.json","state_url":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/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":"2026-05-30T07:32:11Z","links":{"resolver":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2","bundle":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/bundle.json","state":"https://pith.science/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ICT36MXQ5MBXQXG22QAGLIMY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5ICT36MXQ5MBXQXG22QAGLIMY2","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":"30af60d665872aafe836b523f1c09ddf18ae09a7a16c710c763bd36314b6c3df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","title_canon_sha256":"8971ea8489b4460e6226be6a1ee3f02479f867261789d4decb5021082268e061"},"schema_version":"1.0","source":{"id":"1604.05257","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.05257","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"1604.05257v3","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.05257","created_at":"2026-05-18T00:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"5ICT36MXQ5MB","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5ICT36MXQ5MBXQXG","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5ICT36MX","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:8a6da3d3c7ab9eaecef132778313523967d1200eed4550b12693a4eab6426130","target":"graph","created_at":"2026-05-18T00:38:04Z","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":"The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel results under the measure of mean-variance, a commonly adopted risk measure in economics and mathematical finance. We show that the model-specific regret and the model-independent regret in terms of the mean-variance of the reward process are lower bounded by $\\Omega(\\log T)$ and $\\Omega(T^{2/3})$, respectively. We then show that variations of the UCB policy and t","authors_text":"Qing Zhao, Sattar Vakili","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","title":"Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.05257","kind":"arxiv","version":3},"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:becd11f48a79cc72e575a86d4a0659a67859464274212652b537f150bdb9adae","target":"record","created_at":"2026-05-18T00:38:04Z","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":"30af60d665872aafe836b523f1c09ddf18ae09a7a16c710c763bd36314b6c3df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-18T17:28:41Z","title_canon_sha256":"8971ea8489b4460e6226be6a1ee3f02479f867261789d4decb5021082268e061"},"schema_version":"1.0","source":{"id":"1604.05257","kind":"arxiv","version":3}},"canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea053df99787581bc2e6d6a0032d0cc6a624d843df075ccbaa9686a66bd8a51f","first_computed_at":"2026-05-18T00:38:04.466289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:04.466289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vb6u5JB8PigfCsJKnuyKS5YqKPtnzZncddBHZi2eMUUkctvMIU5wIOTkkJvGCEkRrbdbi/Ig2E5p/9F+iT8vCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:04.466978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.05257","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:becd11f48a79cc72e575a86d4a0659a67859464274212652b537f150bdb9adae","sha256:8a6da3d3c7ab9eaecef132778313523967d1200eed4550b12693a4eab6426130"],"state_sha256":"ca96661b6f40ccd9ceabdf4a91a5ffdadfbd39575a3cacd5ab6c776c7ce77c1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAlxeBzOc1FEMcttR/7KscMRXuScrK1mtuFd8XeEz1ZBu/XIeQDpa8cC1ls7Xo3IKksn6KdYmQuRJBxSk3pNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:32:11.621613Z","bundle_sha256":"6d692d3d82dbb28d36f4ac61d6578f02e84635d244ea2855272fdc5db34fa9cd"}}