{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ARXYVTWWSWHI42E3B2K4T3VJ2W","short_pith_number":"pith:ARXYVTWW","schema_version":"1.0","canonical_sha256":"046f8aced6958e8e689b0e95c9eea9d58375231a7ddd77e7b6a669ede29fbde0","source":{"kind":"arxiv","id":"1706.02986","version":2},"attestation_state":"computed","paper":{"title":"Monte-Carlo Tree Search by Best Arm Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"CRIStAL, Emilie Kaufmann (CNRS, SEQUEL), Wouter Koolen (CWI)","submitted_at":"2017-06-09T14:58:10Z","abstract_excerpt":"Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sampling its stochastic payoffs. We develop new algorithms for trees of arbitrary depth, that operate by summarizing all deeper levels of the tree into confidence intervals at depth one, and applying a best arm identification procedure at the root. We prove new sample complexity gu"},"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":"1706.02986","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-09T14:58:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64025507fb4fcfa2895df3412b6e5f16525292eb74de1ec47783dbe8a5f76381","abstract_canon_sha256":"3e9d9834e9e9624348f70afd6510f72bb0d013710af5a087041ed4d185410cae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.272865Z","signature_b64":"VO/EyFt9nVhkW6HROHCb0GAu/7Yj5X/NMdE5T3/JnuPpZdZyfYbz6II3cv6VlcDGlUgp+Rz0czp5nQx738KOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046f8aced6958e8e689b0e95c9eea9d58375231a7ddd77e7b6a669ede29fbde0","last_reissued_at":"2026-05-18T00:31:19.272185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.272185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte-Carlo Tree Search by Best Arm Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"CRIStAL, Emilie Kaufmann (CNRS, SEQUEL), Wouter Koolen (CWI)","submitted_at":"2017-06-09T14:58:10Z","abstract_excerpt":"Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sampling its stochastic payoffs. We develop new algorithms for trees of arbitrary depth, that operate by summarizing all deeper levels of the tree into confidence intervals at depth one, and applying a best arm identification procedure at the root. We prove new sample complexity gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02986","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":"1706.02986","created_at":"2026-05-18T00:31:19.272299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02986v2","created_at":"2026-05-18T00:31:19.272299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02986","created_at":"2026-05-18T00:31:19.272299+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARXYVTWWSWHI","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARXYVTWWSWHI42E3","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARXYVTWW","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18312","citing_title":"Scale-free adaptive planning for deterministic dynamics & discounted rewards","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19695","citing_title":"Planning in entropy-regularized Markov decision processes and games","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W","json":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W.json","graph_json":"https://pith.science/api/pith-number/ARXYVTWWSWHI42E3B2K4T3VJ2W/graph.json","events_json":"https://pith.science/api/pith-number/ARXYVTWWSWHI42E3B2K4T3VJ2W/events.json","paper":"https://pith.science/paper/ARXYVTWW"},"agent_actions":{"view_html":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W","download_json":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W.json","view_paper":"https://pith.science/paper/ARXYVTWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02986&json=true","fetch_graph":"https://pith.science/api/pith-number/ARXYVTWWSWHI42E3B2K4T3VJ2W/graph.json","fetch_events":"https://pith.science/api/pith-number/ARXYVTWWSWHI42E3B2K4T3VJ2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W/action/storage_attestation","attest_author":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W/action/author_attestation","sign_citation":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W/action/citation_signature","submit_replication":"https://pith.science/pith/ARXYVTWWSWHI42E3B2K4T3VJ2W/action/replication_record"}},"created_at":"2026-05-18T00:31:19.272299+00:00","updated_at":"2026-05-18T00:31:19.272299+00:00"}