{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R32EFPIZB2HNU7EZQLS6UUPKRJ","short_pith_number":"pith:R32EFPIZ","schema_version":"1.0","canonical_sha256":"8ef442bd190e8eda7c9982e5ea51ea8a5f1002dcbae83f0fce72d7612007f627","source":{"kind":"arxiv","id":"2402.05002","version":2},"attestation_state":"computed","paper":{"title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Audrey Durand, Maxime Heuillet, Ola Ahmad","submitted_at":"2024-02-07T16:18:59Z","abstract_excerpt":"The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action while the environment simultaneously chooses an outcome. The agent then observes a feedback signal that is only partially informative about the (unobserved) outcome. The agent leverages the received feedback signals to select actions that minimize the (unobserved) cumulative loss. In contextual PM, the outcomes depend on some side information that is observable by the agent before selecting the action on each round. I"},"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":"2402.05002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:18:59Z","cross_cats_sorted":[],"title_canon_sha256":"087cb2171bf19007b5b56f1b27b4c4d85fbcf159b978e35660c0c7d65b718853","abstract_canon_sha256":"95adf8f744e9129c73032386f9601612f3b961d9ac963d632062325737d9e731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:42.090838Z","signature_b64":"FWFC2gfz/V7yyaPpFQGjPBR6+tnm8aHNAjVauvDefOYXJhNg/tVf0yXoL8TNSEtImsVwz17ffowDtsDwyfxcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef442bd190e8eda7c9982e5ea51ea8a5f1002dcbae83f0fce72d7612007f627","last_reissued_at":"2026-07-05T08:19:42.090300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:42.090300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Audrey Durand, Maxime Heuillet, Ola Ahmad","submitted_at":"2024-02-07T16:18:59Z","abstract_excerpt":"The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action while the environment simultaneously chooses an outcome. The agent then observes a feedback signal that is only partially informative about the (unobserved) outcome. The agent leverages the received feedback signals to select actions that minimize the (unobserved) cumulative loss. In contextual PM, the outcomes depend on some side information that is observable by the agent before selecting the action on each round. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05002","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/2402.05002/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":"2402.05002","created_at":"2026-07-05T08:19:42.090393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05002v2","created_at":"2026-07-05T08:19:42.090393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05002","created_at":"2026-07-05T08:19:42.090393+00:00"},{"alias_kind":"pith_short_12","alias_value":"R32EFPIZB2HN","created_at":"2026-07-05T08:19:42.090393+00:00"},{"alias_kind":"pith_short_16","alias_value":"R32EFPIZB2HNU7EZ","created_at":"2026-07-05T08:19:42.090393+00:00"},{"alias_kind":"pith_short_8","alias_value":"R32EFPIZ","created_at":"2026-07-05T08:19:42.090393+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/R32EFPIZB2HNU7EZQLS6UUPKRJ","json":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ.json","graph_json":"https://pith.science/api/pith-number/R32EFPIZB2HNU7EZQLS6UUPKRJ/graph.json","events_json":"https://pith.science/api/pith-number/R32EFPIZB2HNU7EZQLS6UUPKRJ/events.json","paper":"https://pith.science/paper/R32EFPIZ"},"agent_actions":{"view_html":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ","download_json":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ.json","view_paper":"https://pith.science/paper/R32EFPIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05002&json=true","fetch_graph":"https://pith.science/api/pith-number/R32EFPIZB2HNU7EZQLS6UUPKRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/R32EFPIZB2HNU7EZQLS6UUPKRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ/action/storage_attestation","attest_author":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ/action/author_attestation","sign_citation":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ/action/citation_signature","submit_replication":"https://pith.science/pith/R32EFPIZB2HNU7EZQLS6UUPKRJ/action/replication_record"}},"created_at":"2026-07-05T08:19:42.090393+00:00","updated_at":"2026-07-05T08:19:42.090393+00:00"}