{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M7SX6D75SOC5FW3H4IDCCUIJ23","short_pith_number":"pith:M7SX6D75","schema_version":"1.0","canonical_sha256":"67e57f0ffd9385d2db67e206215109d6da88fcee47f89b41bb3dbafcbb629ff8","source":{"kind":"arxiv","id":"2302.12202","version":2},"attestation_state":"computed","paper":{"title":"A Definition of Non-Stationary Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Xu Kuang, Yueyang Liu","submitted_at":"2023-02-23T17:55:11Z","abstract_excerpt":"Despite the subject of non-stationary bandit learning having attracted much recent attention, we have yet to identify a formal definition of non-stationarity that can consistently distinguish non-stationary bandits from stationary ones. Prior work has characterized non-stationary bandits as bandits for which the reward distribution changes over time. We demonstrate that this definition can ambiguously classify the same bandit as both stationary and non-stationary; this ambiguity arises in the existing definition's dependence on the latent sequence of reward distributions. Moreover, the definit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.12202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T17:55:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b6cd4c449568311346caa9fd0d51367fccb65d7423db15a2e8e64f5137f91327","abstract_canon_sha256":"e75431b8f6c426f4e49fae7d10dd1ca2e3cecc073795c5a8f807929f09510b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:26.357124Z","signature_b64":"N+FK0TovtPKd/mftR03tFIQOL+qG419wlP941d23bJBmmF6b+sKQ8NbnshjkDRGLuXhtFO3HbatphkpcADPxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67e57f0ffd9385d2db67e206215109d6da88fcee47f89b41bb3dbafcbb629ff8","last_reissued_at":"2026-07-05T06:35:26.356599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:26.356599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Definition of Non-Stationary Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Xu Kuang, Yueyang Liu","submitted_at":"2023-02-23T17:55:11Z","abstract_excerpt":"Despite the subject of non-stationary bandit learning having attracted much recent attention, we have yet to identify a formal definition of non-stationarity that can consistently distinguish non-stationary bandits from stationary ones. Prior work has characterized non-stationary bandits as bandits for which the reward distribution changes over time. We demonstrate that this definition can ambiguously classify the same bandit as both stationary and non-stationary; this ambiguity arises in the existing definition's dependence on the latent sequence of reward distributions. Moreover, the definit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12202","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.12202/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.12202","created_at":"2026-07-05T06:35:26.356685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12202v2","created_at":"2026-07-05T06:35:26.356685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12202","created_at":"2026-07-05T06:35:26.356685+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7SX6D75SOC5","created_at":"2026-07-05T06:35:26.356685+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7SX6D75SOC5FW3H","created_at":"2026-07-05T06:35:26.356685+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7SX6D75","created_at":"2026-07-05T06:35:26.356685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11797","citing_title":"Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20962","citing_title":"No-regret optimization of time-varying bilevel problems","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23","json":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23.json","graph_json":"https://pith.science/api/pith-number/M7SX6D75SOC5FW3H4IDCCUIJ23/graph.json","events_json":"https://pith.science/api/pith-number/M7SX6D75SOC5FW3H4IDCCUIJ23/events.json","paper":"https://pith.science/paper/M7SX6D75"},"agent_actions":{"view_html":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23","download_json":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23.json","view_paper":"https://pith.science/paper/M7SX6D75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12202&json=true","fetch_graph":"https://pith.science/api/pith-number/M7SX6D75SOC5FW3H4IDCCUIJ23/graph.json","fetch_events":"https://pith.science/api/pith-number/M7SX6D75SOC5FW3H4IDCCUIJ23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23/action/storage_attestation","attest_author":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23/action/author_attestation","sign_citation":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23/action/citation_signature","submit_replication":"https://pith.science/pith/M7SX6D75SOC5FW3H4IDCCUIJ23/action/replication_record"}},"created_at":"2026-07-05T06:35:26.356685+00:00","updated_at":"2026-07-05T06:35:26.356685+00:00"}