{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JCJRPVLJYIJZI3JVGLMIZ6KDSY","short_pith_number":"pith:JCJRPVLJ","schema_version":"1.0","canonical_sha256":"489317d569c213946d3532d88cf943961872b047a940c8e28b60af644ceaa88b","source":{"kind":"arxiv","id":"1509.09011","version":1},"attestation_state":"computed","paper":{"title":"Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroshi Nakagawa, Junpei Komiyama, Junya Honda","submitted_at":"2015-09-30T04:36:40Z","abstract_excerpt":"Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to minimize the total loss. In this paper, we study partial monitoring with finite actions and stochastic outcomes. We derive a logarithmic distribution-dependent regret lower bound that defines the hardness of the problem. Inspired by the DMED algorithm (Honda and Takemura, 2010) for"},"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":"1509.09011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-09-30T04:36:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"560b904245b1ca21515806df3cc28a6067bf1fdad80ef03084baeb3b9c65bd20","abstract_canon_sha256":"a43f42a52f18a9ea77915d2a748d15de03bf917db1d4c75c22c4cef29c74e12b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:31:29.325810Z","signature_b64":"PrseM18+s1dzivpXPrnoeQkm57MuW5Vp45gxaOvkGYwpfalYGHXe7ipHA+pRakiI8OxjTQ9gEVpogNvOJlVcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"489317d569c213946d3532d88cf943961872b047a940c8e28b60af644ceaa88b","last_reissued_at":"2026-05-18T01:31:29.325383Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:31:29.325383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroshi Nakagawa, Junpei Komiyama, Junya Honda","submitted_at":"2015-09-30T04:36:40Z","abstract_excerpt":"Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to minimize the total loss. In this paper, we study partial monitoring with finite actions and stochastic outcomes. We derive a logarithmic distribution-dependent regret lower bound that defines the hardness of the problem. Inspired by the DMED algorithm (Honda and Takemura, 2010) for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.09011","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":"1509.09011","created_at":"2026-05-18T01:31:29.325451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.09011v1","created_at":"2026-05-18T01:31:29.325451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.09011","created_at":"2026-05-18T01:31:29.325451+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCJRPVLJYIJZ","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCJRPVLJYIJZI3JV","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCJRPVLJ","created_at":"2026-05-18T12:29:27.538025+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/JCJRPVLJYIJZI3JVGLMIZ6KDSY","json":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY.json","graph_json":"https://pith.science/api/pith-number/JCJRPVLJYIJZI3JVGLMIZ6KDSY/graph.json","events_json":"https://pith.science/api/pith-number/JCJRPVLJYIJZI3JVGLMIZ6KDSY/events.json","paper":"https://pith.science/paper/JCJRPVLJ"},"agent_actions":{"view_html":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY","download_json":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY.json","view_paper":"https://pith.science/paper/JCJRPVLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.09011&json=true","fetch_graph":"https://pith.science/api/pith-number/JCJRPVLJYIJZI3JVGLMIZ6KDSY/graph.json","fetch_events":"https://pith.science/api/pith-number/JCJRPVLJYIJZI3JVGLMIZ6KDSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY/action/storage_attestation","attest_author":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY/action/author_attestation","sign_citation":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY/action/citation_signature","submit_replication":"https://pith.science/pith/JCJRPVLJYIJZI3JVGLMIZ6KDSY/action/replication_record"}},"created_at":"2026-05-18T01:31:29.325451+00:00","updated_at":"2026-05-18T01:31:29.325451+00:00"}