{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KPUXKEOQYKHHWH5NMF5ITT76XA","short_pith_number":"pith:KPUXKEOQ","schema_version":"1.0","canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","source":{"kind":"arxiv","id":"2008.03959","version":4},"attestation_state":"computed","paper":{"title":"Lenient Regret for Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Merlis, Shie Mannor","submitted_at":"2020-08-10T08:30:52Z","abstract_excerpt":"We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus o"},"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":"2008.03959","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-10T08:30:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b4ef5eeaf69968f7998ba412cf214dab90f3ebb8b39c72318063a7ab2e9aa39","abstract_canon_sha256":"5adcd8f3ab99ee5c2e0ffb02ba501fb420a2edd8415c41dcf00e6fe95ecd3447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:22.739726Z","signature_b64":"DH4wkkA0ldrA8TWdDVt36DufZ7nVt1dV8axZMr3ZANcrTDe0yNhsHPLHq/gkOixgDbVAvtAF/rpHhBFMDrobDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e97511d0c28e7b1fad617a89cffeb8073b060d770294b7ec062b7cff91a2cd","last_reissued_at":"2026-07-05T03:13:22.739282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:22.739282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lenient Regret for Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Merlis, Shie Mannor","submitted_at":"2020-08-10T08:30:52Z","abstract_excerpt":"We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03959","kind":"arxiv","version":4},"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/2008.03959/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":"2008.03959","created_at":"2026-07-05T03:13:22.739342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03959v4","created_at":"2026-07-05T03:13:22.739342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03959","created_at":"2026-07-05T03:13:22.739342+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPUXKEOQYKHH","created_at":"2026-07-05T03:13:22.739342+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPUXKEOQYKHHWH5N","created_at":"2026-07-05T03:13:22.739342+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPUXKEOQ","created_at":"2026-07-05T03:13:22.739342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03999","citing_title":"Adaptive Experiments Under Data Sparse Settings: Applications for Educational Platforms","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA","json":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA.json","graph_json":"https://pith.science/api/pith-number/KPUXKEOQYKHHWH5NMF5ITT76XA/graph.json","events_json":"https://pith.science/api/pith-number/KPUXKEOQYKHHWH5NMF5ITT76XA/events.json","paper":"https://pith.science/paper/KPUXKEOQ"},"agent_actions":{"view_html":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA","download_json":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA.json","view_paper":"https://pith.science/paper/KPUXKEOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03959&json=true","fetch_graph":"https://pith.science/api/pith-number/KPUXKEOQYKHHWH5NMF5ITT76XA/graph.json","fetch_events":"https://pith.science/api/pith-number/KPUXKEOQYKHHWH5NMF5ITT76XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/action/storage_attestation","attest_author":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/action/author_attestation","sign_citation":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/action/citation_signature","submit_replication":"https://pith.science/pith/KPUXKEOQYKHHWH5NMF5ITT76XA/action/replication_record"}},"created_at":"2026-07-05T03:13:22.739342+00:00","updated_at":"2026-07-05T03:13:22.739342+00:00"}