{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:I2QWTEVLJWNYEGJZWWPKPVC4V3","short_pith_number":"pith:I2QWTEVL","schema_version":"1.0","canonical_sha256":"46a16992ab4d9b821939b59ea7d45caef2f99b7a87888ee5a467bbf1d8a9b0a7","source":{"kind":"arxiv","id":"1505.02865","version":2},"attestation_state":"computed","paper":{"title":"Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael N. Katehakis, Wesley Cowan","submitted_at":"2015-05-12T03:35:47Z","abstract_excerpt":"The purpose of this paper is to provide further understanding into the structure of the sequential allocation (\"stochastic multi-armed bandit\", or MAB) problem by establishing probability one finite horizon bounds and convergence rates for the sample (or \"pseudo\") regret associated with two simple classes of allocation policies $\\pi$.\n  For any slowly increasing function $g$, subject to mild regularity constraints, we construct two policies (the $g$-Forcing, and the $g$-Inflated Sample Mean) that achieve a measure of regret of order $ O(g(n))$ almost surely as $n \\to \\infty$, bound from above "},"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":"1505.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-12T03:35:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"56a7a0f224f48a3f9fb273bad8e2d3defce084aae6fb19728a5c7a36153b0f22","abstract_canon_sha256":"8e56fba531fa95e594bb0182438082eeeb7d0a9ba501f8ed8660e5724c18b34d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:10.829413Z","signature_b64":"ildYfkfAnexkkog0mewPgBtwxHwsff4SRjHsS+dVxjadc5x1CM+w3LC4Wa6E95+TXs/WwASQdV+kbAI0ELFsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46a16992ab4d9b821939b59ea7d45caef2f99b7a87888ee5a467bbf1d8a9b0a7","last_reissued_at":"2026-05-18T01:24:10.828951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:10.828951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael N. Katehakis, Wesley Cowan","submitted_at":"2015-05-12T03:35:47Z","abstract_excerpt":"The purpose of this paper is to provide further understanding into the structure of the sequential allocation (\"stochastic multi-armed bandit\", or MAB) problem by establishing probability one finite horizon bounds and convergence rates for the sample (or \"pseudo\") regret associated with two simple classes of allocation policies $\\pi$.\n  For any slowly increasing function $g$, subject to mild regularity constraints, we construct two policies (the $g$-Forcing, and the $g$-Inflated Sample Mean) that achieve a measure of regret of order $ O(g(n))$ almost surely as $n \\to \\infty$, bound from above "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.02865","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":""},"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":"1505.02865","created_at":"2026-05-18T01:24:10.829031+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.02865v2","created_at":"2026-05-18T01:24:10.829031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.02865","created_at":"2026-05-18T01:24:10.829031+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2QWTEVLJWNY","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2QWTEVLJWNYEGJZ","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2QWTEVL","created_at":"2026-05-18T12:29:25.134429+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/I2QWTEVLJWNYEGJZWWPKPVC4V3","json":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3.json","graph_json":"https://pith.science/api/pith-number/I2QWTEVLJWNYEGJZWWPKPVC4V3/graph.json","events_json":"https://pith.science/api/pith-number/I2QWTEVLJWNYEGJZWWPKPVC4V3/events.json","paper":"https://pith.science/paper/I2QWTEVL"},"agent_actions":{"view_html":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3","download_json":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3.json","view_paper":"https://pith.science/paper/I2QWTEVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.02865&json=true","fetch_graph":"https://pith.science/api/pith-number/I2QWTEVLJWNYEGJZWWPKPVC4V3/graph.json","fetch_events":"https://pith.science/api/pith-number/I2QWTEVLJWNYEGJZWWPKPVC4V3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3/action/storage_attestation","attest_author":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3/action/author_attestation","sign_citation":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3/action/citation_signature","submit_replication":"https://pith.science/pith/I2QWTEVLJWNYEGJZWWPKPVC4V3/action/replication_record"}},"created_at":"2026-05-18T01:24:10.829031+00:00","updated_at":"2026-05-18T01:24:10.829031+00:00"}