{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QVZ75EUFZIKUY7PCS3MLQ2GR2J","short_pith_number":"pith:QVZ75EUF","schema_version":"1.0","canonical_sha256":"8573fe9285ca154c7de296d8b868d1d264fbb3cba5e17223f447879968620306","source":{"kind":"arxiv","id":"1602.04676","version":1},"attestation_state":"computed","paper":{"title":"Maximin Action Identification: A New Bandit Framework for Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier (IMT), Emilie Kaufmann (CRIStAL, SEQUEL), Wouter Koolen (CWI)","submitted_at":"2016-02-15T13:55:45Z","abstract_excerpt":"We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs of actions. We propose two strategies for the fixed-confidence setting: Maximin-LUCB, based on lower-and upper-confidence bounds; and Maximin-Racing, which operates by successively eliminating the sub-optimal actions. We discuss the sample complexity of both methods and compare their performance empirically. We sketch a lower bound analysis, and possible co"},"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":"1602.04676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-02-15T13:55:45Z","cross_cats_sorted":["cs.GT","stat.ML","stat.TH"],"title_canon_sha256":"14a794c210eeb28b72837d8c38d75367d72a2d19063c2efc8b94fbd1be232a41","abstract_canon_sha256":"d75924bcf72a2b8de4cdbbb8071ce53a17c69ca87c577f6326f82ca54aa134ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:49.428105Z","signature_b64":"iwgTbJxMSV4YbGGI9mVQGW52VgSUgudoP3ght20+ilSlrD+P4cr5jDp93kD2cgLwOWXan2hQorLZxVOj06+2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8573fe9285ca154c7de296d8b868d1d264fbb3cba5e17223f447879968620306","last_reissued_at":"2026-05-18T01:20:49.427757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:49.427757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximin Action Identification: A New Bandit Framework for Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier (IMT), Emilie Kaufmann (CRIStAL, SEQUEL), Wouter Koolen (CWI)","submitted_at":"2016-02-15T13:55:45Z","abstract_excerpt":"We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs of actions. We propose two strategies for the fixed-confidence setting: Maximin-LUCB, based on lower-and upper-confidence bounds; and Maximin-Racing, which operates by successively eliminating the sub-optimal actions. We discuss the sample complexity of both methods and compare their performance empirically. We sketch a lower bound analysis, and possible co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04676","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":""},"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":"1602.04676","created_at":"2026-05-18T01:20:49.427811+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.04676v1","created_at":"2026-05-18T01:20:49.427811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04676","created_at":"2026-05-18T01:20:49.427811+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVZ75EUFZIKU","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVZ75EUFZIKUY7PC","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVZ75EUF","created_at":"2026-05-18T12:30:41.710351+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/QVZ75EUFZIKUY7PCS3MLQ2GR2J","json":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J.json","graph_json":"https://pith.science/api/pith-number/QVZ75EUFZIKUY7PCS3MLQ2GR2J/graph.json","events_json":"https://pith.science/api/pith-number/QVZ75EUFZIKUY7PCS3MLQ2GR2J/events.json","paper":"https://pith.science/paper/QVZ75EUF"},"agent_actions":{"view_html":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J","download_json":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J.json","view_paper":"https://pith.science/paper/QVZ75EUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.04676&json=true","fetch_graph":"https://pith.science/api/pith-number/QVZ75EUFZIKUY7PCS3MLQ2GR2J/graph.json","fetch_events":"https://pith.science/api/pith-number/QVZ75EUFZIKUY7PCS3MLQ2GR2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J/action/storage_attestation","attest_author":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J/action/author_attestation","sign_citation":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J/action/citation_signature","submit_replication":"https://pith.science/pith/QVZ75EUFZIKUY7PCS3MLQ2GR2J/action/replication_record"}},"created_at":"2026-05-18T01:20:49.427811+00:00","updated_at":"2026-05-18T01:20:49.427811+00:00"}