{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DGMJCF2CNLWG3F6AWUKAPWG6PG","short_pith_number":"pith:DGMJCF2C","canonical_record":{"source":{"id":"1802.03692","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee265ffc29a25f6808e78e173aa6da2f38636c0b74357694a2977c82aa4da665","abstract_canon_sha256":"1afc29bf5b2faa83a024a055cedf8008d2679911f3714c617dab128da62650d3"},"schema_version":"1.0"},"canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","source":{"kind":"arxiv","id":"1802.03692","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03692","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03692v4","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03692","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"DGMJCF2CNLWG","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DGMJCF2CNLWG3F6A","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DGMJCF2C","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DGMJCF2CNLWG3F6AWUKAPWG6PG","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03692","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee265ffc29a25f6808e78e173aa6da2f38636c0b74357694a2977c82aa4da665","abstract_canon_sha256":"1afc29bf5b2faa83a024a055cedf8008d2679911f3714c617dab128da62650d3"},"schema_version":"1.0"},"canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:38.824874Z","signature_b64":"gotTzu5i+FBlIGUWEPdt1jOywsh/ec5tLxPv4Gv2Rj5G20m8kbbsgyWEAvpI2K/gsxJ78gKt7MLDtNL7OtJAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","last_reissued_at":"2026-05-17T23:55:38.824200Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:38.824200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03692","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijhC2xanHypIvxi8MfuJ0/ldJmg1k8ygc+qgX4f4cfDXdQAKI9ksRzH6r95xfStcmGzN3tPpTYy43I2/zPmzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:36:03.142349Z"},"content_sha256":"a7875a121a0996f061cecd8930218a6e4445952ab3866774e5d6403ed445a888","schema_version":"1.0","event_id":"sha256:a7875a121a0996f061cecd8930218a6e4445952ab3866774e5d6403ed445a888"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DGMJCF2CNLWG3F6AWUKAPWG6PG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Branislav Kveton, Yang Cao, Yao Xie, Zheng Wen","submitted_at":"2018-02-11T04:57:28Z","abstract_excerpt":"Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown time steps. We show that by incorporating a simple change-detection component with classic UCB algorithms to detect and adapt to changes, our so-called M-UCB algorithm can achieve nearly optimal regret bound on the order of $O(\\sqrt{MKT\\log T})$, where $T$ is the number of time s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03692","kind":"arxiv","version":4},"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":"2026-05-17T23:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQ/k1o4dVTe5abspwmold4eSXF7p1CNeVu9iSaNCy0JRcXGPFj9A3ZfRxmHbUP0+X/jN27wwLuBs1LBfWVoGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:36:03.143030Z"},"content_sha256":"4ef2e57fb19aaff207699a3133244c453f335b9378395ca8ea6b64a897cab15d","schema_version":"1.0","event_id":"sha256:4ef2e57fb19aaff207699a3133244c453f335b9378395ca8ea6b64a897cab15d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/bundle.json","state_url":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/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":"2026-06-05T00:36:03Z","links":{"resolver":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG","bundle":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/bundle.json","state":"https://pith.science/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGMJCF2CNLWG3F6AWUKAPWG6PG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DGMJCF2CNLWG3F6AWUKAPWG6PG","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":"1afc29bf5b2faa83a024a055cedf8008d2679911f3714c617dab128da62650d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","title_canon_sha256":"ee265ffc29a25f6808e78e173aa6da2f38636c0b74357694a2977c82aa4da665"},"schema_version":"1.0","source":{"id":"1802.03692","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03692","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03692v4","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03692","created_at":"2026-05-17T23:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"DGMJCF2CNLWG","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DGMJCF2CNLWG3F6A","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DGMJCF2C","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:4ef2e57fb19aaff207699a3133244c453f335b9378395ca8ea6b64a897cab15d","target":"graph","created_at":"2026-05-17T23:55:38Z","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":"Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown time steps. We show that by incorporating a simple change-detection component with classic UCB algorithms to detect and adapt to changes, our so-called M-UCB algorithm can achieve nearly optimal regret bound on the order of $O(\\sqrt{MKT\\log T})$, where $T$ is the number of time s","authors_text":"Branislav Kveton, Yang Cao, Yao Xie, Zheng Wen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03692","kind":"arxiv","version":4},"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:a7875a121a0996f061cecd8930218a6e4445952ab3866774e5d6403ed445a888","target":"record","created_at":"2026-05-17T23:55:38Z","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":"1afc29bf5b2faa83a024a055cedf8008d2679911f3714c617dab128da62650d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-11T04:57:28Z","title_canon_sha256":"ee265ffc29a25f6808e78e173aa6da2f38636c0b74357694a2977c82aa4da665"},"schema_version":"1.0","source":{"id":"1802.03692","kind":"arxiv","version":4}},"canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19989117426aec6d97c0b51407d8de799a0106a0abfc8ba26b27f5fb888f0fe4","first_computed_at":"2026-05-17T23:55:38.824200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:38.824200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gotTzu5i+FBlIGUWEPdt1jOywsh/ec5tLxPv4Gv2Rj5G20m8kbbsgyWEAvpI2K/gsxJ78gKt7MLDtNL7OtJAAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:38.824874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03692","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7875a121a0996f061cecd8930218a6e4445952ab3866774e5d6403ed445a888","sha256:4ef2e57fb19aaff207699a3133244c453f335b9378395ca8ea6b64a897cab15d"],"state_sha256":"f10b76be50331c763e7bac1e4cc2ddd5d424e436719dd48aac79ccb69cc21cc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ygjqS1E+g4wmJtBQkkMbQIF76Xd7vkeYbYTUPs1s2fNNd/6wLonIRNYZ9pET8yG7tp1tKHlFf5J2jCBoHZbLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:36:03.146423Z","bundle_sha256":"f3ba9f16f7d04b4a82b192cfa5d56677143670f0de8906d11c919948eb277ad0"}}