{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MTETA5FT7IOP44QVV4CULBIYLU","short_pith_number":"pith:MTETA5FT","schema_version":"1.0","canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","source":{"kind":"arxiv","id":"2412.02251","version":3},"attestation_state":"computed","paper":{"title":"Selective Reviews of Bandit Problems in AI via a Statistical View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","econ.EM","math.PR"],"primary_cat":"stat.ML","authors_text":"Haoyu Wei, Huiming Zhang, Pengjie Zhou","submitted_at":"2024-12-03T08:28:47Z","abstract_excerpt":"Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes stochastic multi-armed bandit (MAB) and continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration-exploita"},"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":"2412.02251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.PR"],"title_canon_sha256":"217c3cc5c2fdd8763f7e9ac933a1bc14bff7d14da6fdb823c91bb2cdee0f39f2","abstract_canon_sha256":"0e76f72d7f2fd796a4e96a235bb457ce5f11ef019a2851f762c897ab2e17eb7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:59.409444Z","signature_b64":"RB76oOo7YY00zAuskHwDgRT+4OHVyyXbNM9E++W81GASej9KE34XdpncjFQiesQJQzXZuM2ZcVRz0xc57E5DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","last_reissued_at":"2026-07-05T10:16:59.408955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:59.408955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Reviews of Bandit Problems in AI via a Statistical View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","econ.EM","math.PR"],"primary_cat":"stat.ML","authors_text":"Haoyu Wei, Huiming Zhang, Pengjie Zhou","submitted_at":"2024-12-03T08:28:47Z","abstract_excerpt":"Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes stochastic multi-armed bandit (MAB) and continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration-exploita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02251","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.02251/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":"2412.02251","created_at":"2026-07-05T10:16:59.409017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02251v3","created_at":"2026-07-05T10:16:59.409017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02251","created_at":"2026-07-05T10:16:59.409017+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTETA5FT7IOP","created_at":"2026-07-05T10:16:59.409017+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTETA5FT7IOP44QV","created_at":"2026-07-05T10:16:59.409017+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTETA5FT","created_at":"2026-07-05T10:16:59.409017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU","json":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU.json","graph_json":"https://pith.science/api/pith-number/MTETA5FT7IOP44QVV4CULBIYLU/graph.json","events_json":"https://pith.science/api/pith-number/MTETA5FT7IOP44QVV4CULBIYLU/events.json","paper":"https://pith.science/paper/MTETA5FT"},"agent_actions":{"view_html":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU","download_json":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU.json","view_paper":"https://pith.science/paper/MTETA5FT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02251&json=true","fetch_graph":"https://pith.science/api/pith-number/MTETA5FT7IOP44QVV4CULBIYLU/graph.json","fetch_events":"https://pith.science/api/pith-number/MTETA5FT7IOP44QVV4CULBIYLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/action/storage_attestation","attest_author":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/action/author_attestation","sign_citation":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/action/citation_signature","submit_replication":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/action/replication_record"}},"created_at":"2026-07-05T10:16:59.409017+00:00","updated_at":"2026-07-05T10:16:59.409017+00:00"}