{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LETTD332BFGW3WXFOG4FBSMZSO","short_pith_number":"pith:LETTD332","schema_version":"1.0","canonical_sha256":"592731ef7a094d6ddae571b850c999939c2a82292b4ab1748776ca5751553754","source":{"kind":"arxiv","id":"2210.05660","version":1},"attestation_state":"computed","paper":{"title":"The Typical Behavior of Bandit Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lin Fan, Peter W. Glynn","submitted_at":"2022-10-11T17:56:01Z","abstract_excerpt":"We establish strong laws of large numbers and central limit theorems for the regret of two of the most popular bandit algorithms: Thompson sampling and UCB. Here, our characterizations of the regret distribution complement the characterizations of the tail of the regret distribution recently developed by Fan and Glynn (2021) (arXiv:2109.13595). The tail characterizations there are associated with atypical bandit behavior on trajectories where the optimal arm mean is under-estimated, leading to mis-identification of the optimal arm and large regret. In contrast, our SLLN's and CLT's here descri"},"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":"2210.05660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T17:56:01Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"a1027262ee4b6602509f030b3d24049074f2327f2ad2ba974d8ff0bb4c6ca26d","abstract_canon_sha256":"33710cb7eda9c2f8c84a5c2a082da08501301266c46d44c92868b1e8c625692b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:18.928273Z","signature_b64":"krr8omNCpvOfQ0REy0TqeeQ6mw47U6v4drzrf+g2R/fev3/pM34iZtOLhESFBj+rOVAr2Z9oUMJJARyHAq+EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"592731ef7a094d6ddae571b850c999939c2a82292b4ab1748776ca5751553754","last_reissued_at":"2026-07-05T05:05:18.927814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:18.927814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Typical Behavior of Bandit Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lin Fan, Peter W. Glynn","submitted_at":"2022-10-11T17:56:01Z","abstract_excerpt":"We establish strong laws of large numbers and central limit theorems for the regret of two of the most popular bandit algorithms: Thompson sampling and UCB. Here, our characterizations of the regret distribution complement the characterizations of the tail of the regret distribution recently developed by Fan and Glynn (2021) (arXiv:2109.13595). The tail characterizations there are associated with atypical bandit behavior on trajectories where the optimal arm mean is under-estimated, leading to mis-identification of the optimal arm and large regret. In contrast, our SLLN's and CLT's here descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05660","kind":"arxiv","version":1},"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/2210.05660/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":"2210.05660","created_at":"2026-07-05T05:05:18.927873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05660v1","created_at":"2026-07-05T05:05:18.927873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05660","created_at":"2026-07-05T05:05:18.927873+00:00"},{"alias_kind":"pith_short_12","alias_value":"LETTD332BFGW","created_at":"2026-07-05T05:05:18.927873+00:00"},{"alias_kind":"pith_short_16","alias_value":"LETTD332BFGW3WXF","created_at":"2026-07-05T05:05:18.927873+00:00"},{"alias_kind":"pith_short_8","alias_value":"LETTD332","created_at":"2026-07-05T05:05:18.927873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01655","citing_title":"MINTS: Minimalist Thompson Sampling","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14876","citing_title":"Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO","json":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO.json","graph_json":"https://pith.science/api/pith-number/LETTD332BFGW3WXFOG4FBSMZSO/graph.json","events_json":"https://pith.science/api/pith-number/LETTD332BFGW3WXFOG4FBSMZSO/events.json","paper":"https://pith.science/paper/LETTD332"},"agent_actions":{"view_html":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO","download_json":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO.json","view_paper":"https://pith.science/paper/LETTD332","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05660&json=true","fetch_graph":"https://pith.science/api/pith-number/LETTD332BFGW3WXFOG4FBSMZSO/graph.json","fetch_events":"https://pith.science/api/pith-number/LETTD332BFGW3WXFOG4FBSMZSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO/action/storage_attestation","attest_author":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO/action/author_attestation","sign_citation":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO/action/citation_signature","submit_replication":"https://pith.science/pith/LETTD332BFGW3WXFOG4FBSMZSO/action/replication_record"}},"created_at":"2026-07-05T05:05:18.927873+00:00","updated_at":"2026-07-05T05:05:18.927873+00:00"}