{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BA4A44UPJGT5XPEESJ6W37ZMZP","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":"5a9de1d987b63e67422357b070412596750873b9c2717b3d4ec735f1c2a1dd41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T09:48:54Z","title_canon_sha256":"e7334fcc45409b426e62ef1607594c969a8635ccde3f585374d3c4b30585289a"},"schema_version":"1.0","source":{"id":"2112.06517","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06517","created_at":"2026-07-05T04:13:47Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06517v4","created_at":"2026-07-05T04:13:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06517","created_at":"2026-07-05T04:13:47Z"},{"alias_kind":"pith_short_12","alias_value":"BA4A44UPJGT5","created_at":"2026-07-05T04:13:47Z"},{"alias_kind":"pith_short_16","alias_value":"BA4A44UPJGT5XPEE","created_at":"2026-07-05T04:13:47Z"},{"alias_kind":"pith_short_8","alias_value":"BA4A44UP","created_at":"2026-07-05T04:13:47Z"}],"graph_snapshots":[{"event_id":"sha256:68506f37ca4a79559eb953f43123f806704eb35565a5be0b31e3b44716f220fb","target":"graph","created_at":"2026-07-05T04:13:47Z","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/2112.06517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a multi-armed bandit setting where, at the beginning of each round, the learner receives noisy independent, and possibly biased, \\emph{evaluations} of the true reward of each arm and it selects $K$ arms with the objective of accumulating as much reward as possible over $T$ rounds. Under the assumption that at each round the true reward of each arm is drawn from a fixed distribution, we derive different algorithmic approaches and theoretical guarantees depending on how the evaluations are generated. First, we show a $\\widetilde{O}(T^{2/3})$ regret in the general case when the observ","authors_text":"Alessandro Lazaric, Evrard Garcelon, Matteo Pirotta, Vashist Avadhanula","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T09:48:54Z","title":"Top $K$ Ranking for Multi-Armed Bandit with Noisy Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06517","kind":"arxiv","version":4},"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:b554006ff4357ad6967b8bab4f692f81877829ec845b1e83fdea47dd5142138b","target":"record","created_at":"2026-07-05T04:13:47Z","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":"5a9de1d987b63e67422357b070412596750873b9c2717b3d4ec735f1c2a1dd41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T09:48:54Z","title_canon_sha256":"e7334fcc45409b426e62ef1607594c969a8635ccde3f585374d3c4b30585289a"},"schema_version":"1.0","source":{"id":"2112.06517","kind":"arxiv","version":4}},"canonical_sha256":"08380e728f49a7dbbc84927d6dff2ccbf78a5b98cfb2337d2519f06674d6bb96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08380e728f49a7dbbc84927d6dff2ccbf78a5b98cfb2337d2519f06674d6bb96","first_computed_at":"2026-07-05T04:13:47.646075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:47.646075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6EbLPUFKn0O/4/95SjfCwgG9ZbKsG5m598CnUEcc1su6UgOeWoaqD1Eb7vSZUfB15EFOYslQn+tWapn5yx4xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:47.646670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06517","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b554006ff4357ad6967b8bab4f692f81877829ec845b1e83fdea47dd5142138b","sha256:68506f37ca4a79559eb953f43123f806704eb35565a5be0b31e3b44716f220fb"],"state_sha256":"eef0e887a70575b66288b221527a1de0b1ad359ee989a64ae9eb9843db458f51"}