{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PPTWKADNF5EKBODWIZREBKDHUD","short_pith_number":"pith:PPTWKADN","schema_version":"1.0","canonical_sha256":"7be765006d2f48a0b876466240a867a0c85dd169ca96ad65cd28ea9f6f317bf3","source":{"kind":"arxiv","id":"2006.09668","version":2},"attestation_state":"computed","paper":{"title":"Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Junya Honda, Masashi Sugiyama, Taira Tsuchiya","submitted_at":"2020-06-17T05:48:33Z","abstract_excerpt":"We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback. While Thompson sampling is one of the most promising algorithms on a variety of online decision-making problems, its properties for stochastic partial monitoring have not been theoretically investigated, and the existing algorithm relies on a heuristic approximation of the posterior distribution. To mitigate these problems, we present a novel Thompson-sampling-based algorithm, which enables us to exactly sample the target parameter from the posterior distribution. Beside"},"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":"2006.09668","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-17T05:48:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bac2a5ee627bb8bb1c4286d7eba258e9321eb0122b167f2dd6a49c8c1b69b8d","abstract_canon_sha256":"decfef6f17d796bda24eccd4e88095c7416a79f68a7ec5c28c0cc5c4e7d3c882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:56.552387Z","signature_b64":"gFfHvorZvOtKGfh3x05TZhsPGkeNGcX9uNtmv7z6pU9dGpHWc5LmmgoKVx5Mqw2DWWMD+qes3IhNDGXu6C7ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be765006d2f48a0b876466240a867a0c85dd169ca96ad65cd28ea9f6f317bf3","last_reissued_at":"2026-07-05T02:47:56.551902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:56.551902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Junya Honda, Masashi Sugiyama, Taira Tsuchiya","submitted_at":"2020-06-17T05:48:33Z","abstract_excerpt":"We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback. While Thompson sampling is one of the most promising algorithms on a variety of online decision-making problems, its properties for stochastic partial monitoring have not been theoretically investigated, and the existing algorithm relies on a heuristic approximation of the posterior distribution. To mitigate these problems, we present a novel Thompson-sampling-based algorithm, which enables us to exactly sample the target parameter from the posterior distribution. Beside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09668","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.09668/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":"2006.09668","created_at":"2026-07-05T02:47:56.551968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09668v2","created_at":"2026-07-05T02:47:56.551968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09668","created_at":"2026-07-05T02:47:56.551968+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPTWKADNF5EK","created_at":"2026-07-05T02:47:56.551968+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPTWKADNF5EKBODW","created_at":"2026-07-05T02:47:56.551968+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPTWKADN","created_at":"2026-07-05T02:47:56.551968+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/PPTWKADNF5EKBODWIZREBKDHUD","json":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD.json","graph_json":"https://pith.science/api/pith-number/PPTWKADNF5EKBODWIZREBKDHUD/graph.json","events_json":"https://pith.science/api/pith-number/PPTWKADNF5EKBODWIZREBKDHUD/events.json","paper":"https://pith.science/paper/PPTWKADN"},"agent_actions":{"view_html":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD","download_json":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD.json","view_paper":"https://pith.science/paper/PPTWKADN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09668&json=true","fetch_graph":"https://pith.science/api/pith-number/PPTWKADNF5EKBODWIZREBKDHUD/graph.json","fetch_events":"https://pith.science/api/pith-number/PPTWKADNF5EKBODWIZREBKDHUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD/action/storage_attestation","attest_author":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD/action/author_attestation","sign_citation":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD/action/citation_signature","submit_replication":"https://pith.science/pith/PPTWKADNF5EKBODWIZREBKDHUD/action/replication_record"}},"created_at":"2026-07-05T02:47:56.551968+00:00","updated_at":"2026-07-05T02:47:56.551968+00:00"}