{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YEBUHZPTC5ACCF7GFNBSBVBLFR","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":"b3e87b7bd3b0e7d7bdb28398817b0fefd3f7f49faebd1db6238663b91b51fb2b","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T06:03:20Z","title_canon_sha256":"f2576a892bee5e7c7809253e909a17564825a2dd8dd39e853f7a4d970b7976b5"},"schema_version":"1.0","source":{"id":"2301.12366","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12366","created_at":"2026-07-05T09:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12366v3","created_at":"2026-07-05T09:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12366","created_at":"2026-07-05T09:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"YEBUHZPTC5AC","created_at":"2026-07-05T09:36:07Z"},{"alias_kind":"pith_short_16","alias_value":"YEBUHZPTC5ACCF7G","created_at":"2026-07-05T09:36:07Z"},{"alias_kind":"pith_short_8","alias_value":"YEBUHZPT","created_at":"2026-07-05T09:36:07Z"}],"graph_snapshots":[{"event_id":"sha256:53db49658ebb2bc3038e7c309a51f366f56e238af1daa312d0e2358ad2ef0b80","target":"graph","created_at":"2026-07-05T09:36:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.12366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many applications of online decision making, the environment is non-stationary and it is therefore crucial to use bandit algorithms that handle changes. Most existing approaches are designed to protect against non-smooth changes, constrained only by total variation or Lipschitzness over time. However, in practice, environments often change {\\em smoothly}, so such algorithms may incur higher-than-necessary regret. We study a non-stationary bandits problem where each arm's mean reward sequence can be embedded into a $\\beta$-H\\\"older function, i.e., a function that is $(\\beta-1)$-times Lipschi","authors_text":"Nathan Kallus, Peter I. Frazier, Qian Xie, Su Jia","cross_cats":["cs.AI","math.OC","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T06:03:20Z","title":"Smooth Non-Stationary Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12366","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":"sha256:1148f7110aed8b91d37d7d732eca3f39e3107807e8ac62d9fcd164073f9982eb","target":"record","created_at":"2026-07-05T09:36:07Z","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":"b3e87b7bd3b0e7d7bdb28398817b0fefd3f7f49faebd1db6238663b91b51fb2b","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T06:03:20Z","title_canon_sha256":"f2576a892bee5e7c7809253e909a17564825a2dd8dd39e853f7a4d970b7976b5"},"schema_version":"1.0","source":{"id":"2301.12366","kind":"arxiv","version":3}},"canonical_sha256":"c10343e5f317402117e62b4320d42b2c61a6a7075031740525a50d99ebcaf919","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c10343e5f317402117e62b4320d42b2c61a6a7075031740525a50d99ebcaf919","first_computed_at":"2026-07-05T09:36:07.031669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:07.031669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+8/TbV4a3E2BB8LgTK+5dzeOBKZVRpFsd4IePRei7NItkPV+ozhVBY3vNNSzA15vPB1geWMwe+fwTp9dCfHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:07.032194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12366","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1148f7110aed8b91d37d7d732eca3f39e3107807e8ac62d9fcd164073f9982eb","sha256:53db49658ebb2bc3038e7c309a51f366f56e238af1daa312d0e2358ad2ef0b80"],"state_sha256":"d2a972ee8b0def93dc3367b60c9e0b0d7da74081ee7e3f0cc34c3e369cb92fa0"}