{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:V4BYEKXISU4MJHQWVDERQDYCRF","short_pith_number":"pith:V4BYEKXI","canonical_record":{"source":{"id":"1702.00001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-31T07:45:32Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8af078c5a0394560f06f8a2dab511500398b702b040877196a9c1d76dc76beb0","abstract_canon_sha256":"79e6d2e9440c4aca21abb850109689ab1060a2395e420f5dc9c617757846b49f"},"schema_version":"1.0"},"canonical_sha256":"af03822ae89538c49e16a8c9180f02896d6e4a9cabcfc116ddc0b797aac93d26","source":{"kind":"arxiv","id":"1702.00001","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00001","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00001v3","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00001","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"pith_short_12","alias_value":"V4BYEKXISU4M","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4BYEKXISU4MJHQW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4BYEKXI","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:V4BYEKXISU4MJHQWVDERQDYCRF","target":"record","payload":{"canonical_record":{"source":{"id":"1702.00001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-31T07:45:32Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8af078c5a0394560f06f8a2dab511500398b702b040877196a9c1d76dc76beb0","abstract_canon_sha256":"79e6d2e9440c4aca21abb850109689ab1060a2395e420f5dc9c617757846b49f"},"schema_version":"1.0"},"canonical_sha256":"af03822ae89538c49e16a8c9180f02896d6e4a9cabcfc116ddc0b797aac93d26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:13.422209Z","signature_b64":"MPu+lL9mqburfasa/bGFFM++o3ZDgOfFtyKYA1mkoHdz7qtJatJ87BnxSAWOwk9biDoXE1/sgcIMe9AL2xLGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af03822ae89538c49e16a8c9180f02896d6e4a9cabcfc116ddc0b797aac93d26","last_reissued_at":"2026-05-18T00:31:13.421510Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:13.421510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.00001","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":"2026-05-18T00:31:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVKA5XV6Npi5EPzFM3CMYbF0Py9zGjFipNGberCcM1Sgab9tMXWl+T1VN5ukfeD7MADou/xDTjUoWFKI/urxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:39:25.879498Z"},"content_sha256":"8ec5985e60142616d8d3fe1ef27c049cff5c2a31804a34955b7d2c884ddfc3af","schema_version":"1.0","event_id":"sha256:8ec5985e60142616d8d3fe1ef27c049cff5c2a31804a34955b7d2c884ddfc3af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:V4BYEKXISU4MJHQWVDERQDYCRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning the distribution with largest mean: two bandit frameworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Garivier (IMT), CNRS), CRIStAL, Emilie Kaufmann (SEQUEL","submitted_at":"2017-01-31T07:45:32Z","abstract_excerpt":"Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00001","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":"2026-05-18T00:31:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZJZMvy2HGAGP4liKNH9Ha/uVh64lL5JN5cpBr1vRdY8SxkK/0Cm9qOvY5ntodWjoYU6oKCwUVHxxFGOG7+YDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:39:25.880192Z"},"content_sha256":"f2084a538875823539b3c41d621ccb8800762090ede98a686d6b770bb455a9c3","schema_version":"1.0","event_id":"sha256:f2084a538875823539b3c41d621ccb8800762090ede98a686d6b770bb455a9c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4BYEKXISU4MJHQWVDERQDYCRF/bundle.json","state_url":"https://pith.science/pith/V4BYEKXISU4MJHQWVDERQDYCRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4BYEKXISU4MJHQWVDERQDYCRF/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":"2026-05-31T07:39:25Z","links":{"resolver":"https://pith.science/pith/V4BYEKXISU4MJHQWVDERQDYCRF","bundle":"https://pith.science/pith/V4BYEKXISU4MJHQWVDERQDYCRF/bundle.json","state":"https://pith.science/pith/V4BYEKXISU4MJHQWVDERQDYCRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4BYEKXISU4MJHQWVDERQDYCRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:V4BYEKXISU4MJHQWVDERQDYCRF","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":"79e6d2e9440c4aca21abb850109689ab1060a2395e420f5dc9c617757846b49f","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-31T07:45:32Z","title_canon_sha256":"8af078c5a0394560f06f8a2dab511500398b702b040877196a9c1d76dc76beb0"},"schema_version":"1.0","source":{"id":"1702.00001","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00001","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00001v3","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00001","created_at":"2026-05-18T00:31:13Z"},{"alias_kind":"pith_short_12","alias_value":"V4BYEKXISU4M","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4BYEKXISU4MJHQW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4BYEKXI","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:f2084a538875823539b3c41d621ccb8800762090ede98a686d6b770bb455a9c3","target":"graph","created_at":"2026-05-18T00:31:13Z","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":"Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compar","authors_text":"Aur\\'elien Garivier (IMT), CNRS), CRIStAL, Emilie Kaufmann (SEQUEL","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-31T07:45:32Z","title":"Learning the distribution with largest mean: two bandit frameworks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00001","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":"sha256:8ec5985e60142616d8d3fe1ef27c049cff5c2a31804a34955b7d2c884ddfc3af","target":"record","created_at":"2026-05-18T00:31:13Z","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":"79e6d2e9440c4aca21abb850109689ab1060a2395e420f5dc9c617757846b49f","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-31T07:45:32Z","title_canon_sha256":"8af078c5a0394560f06f8a2dab511500398b702b040877196a9c1d76dc76beb0"},"schema_version":"1.0","source":{"id":"1702.00001","kind":"arxiv","version":3}},"canonical_sha256":"af03822ae89538c49e16a8c9180f02896d6e4a9cabcfc116ddc0b797aac93d26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af03822ae89538c49e16a8c9180f02896d6e4a9cabcfc116ddc0b797aac93d26","first_computed_at":"2026-05-18T00:31:13.421510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:13.421510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MPu+lL9mqburfasa/bGFFM++o3ZDgOfFtyKYA1mkoHdz7qtJatJ87BnxSAWOwk9biDoXE1/sgcIMe9AL2xLGAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:13.422209Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.00001","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ec5985e60142616d8d3fe1ef27c049cff5c2a31804a34955b7d2c884ddfc3af","sha256:f2084a538875823539b3c41d621ccb8800762090ede98a686d6b770bb455a9c3"],"state_sha256":"900f838553a878ae8aaf09e6e5cb4a3f3b6308150c4c49805f883ba8c661eb6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVpMX7y7bGRqGI5MWTRlbzX3QdH6+GQ8vX0IUb2QGHdv8xVxlkOdBf+0IfP41IjLLapr50rjRiQmKTQO/Np4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:39:25.883271Z","bundle_sha256":"b869a11aa10634135d69f789893dea9d1cee9efe1552d46b1fa5a666a1712cfb"}}