{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2AGZQWR7DFPGM6QZ3T3J2HRDS2","short_pith_number":"pith:2AGZQWR7","schema_version":"1.0","canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","source":{"kind":"arxiv","id":"1805.01627","version":2},"attestation_state":"computed","paper":{"title":"BelMan: Bayesian Bandits on the Belief--Reward Manifold","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debabrota Basu, Pierre Senellart, St\\'ephane Bressan","submitted_at":"2018-05-04T07:11:53Z","abstract_excerpt":"We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is summarised by the barycentre of the joint distributions of beliefs and rewards of the arms, the \\emph{pseudobelief-reward}, within the beliefs-rewards manifold. BelMan alternates \\emph{information projection} and \\emph{reverse information projection}, i.e., projection of the pseudo"},"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":"1805.01627","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-04T07:11:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3da971b9f231e2f618273a787105bcb9cd77763b1c02c2c35261b1ee674420cf","abstract_canon_sha256":"f5c88544c5dba626c6e0b350e19ba6276ecd62b7c87b4a857ce9558add1182c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:43.288710Z","signature_b64":"rqGpCOzQi5cxE6kjYRj6rzP/1rT6jHa5Rsyd2QUEzZHZ7Peh6P7SvBWOx2z9s2Fn8zZyNqYpsCBO0vAj2voQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","last_reissued_at":"2026-05-17T23:42:43.288194Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:43.288194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BelMan: Bayesian Bandits on the Belief--Reward Manifold","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debabrota Basu, Pierre Senellart, St\\'ephane Bressan","submitted_at":"2018-05-04T07:11:53Z","abstract_excerpt":"We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is summarised by the barycentre of the joint distributions of beliefs and rewards of the arms, the \\emph{pseudobelief-reward}, within the beliefs-rewards manifold. BelMan alternates \\emph{information projection} and \\emph{reverse information projection}, i.e., projection of the pseudo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01627","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":"1805.01627","created_at":"2026-05-17T23:42:43.288267+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.01627v2","created_at":"2026-05-17T23:42:43.288267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01627","created_at":"2026-05-17T23:42:43.288267+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AGZQWR7DFPG","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AGZQWR7DFPGM6QZ","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AGZQWR7","created_at":"2026-05-18T12:31:59.375834+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/2AGZQWR7DFPGM6QZ3T3J2HRDS2","json":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2.json","graph_json":"https://pith.science/api/pith-number/2AGZQWR7DFPGM6QZ3T3J2HRDS2/graph.json","events_json":"https://pith.science/api/pith-number/2AGZQWR7DFPGM6QZ3T3J2HRDS2/events.json","paper":"https://pith.science/paper/2AGZQWR7"},"agent_actions":{"view_html":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2","download_json":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2.json","view_paper":"https://pith.science/paper/2AGZQWR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.01627&json=true","fetch_graph":"https://pith.science/api/pith-number/2AGZQWR7DFPGM6QZ3T3J2HRDS2/graph.json","fetch_events":"https://pith.science/api/pith-number/2AGZQWR7DFPGM6QZ3T3J2HRDS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/action/storage_attestation","attest_author":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/action/author_attestation","sign_citation":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/action/citation_signature","submit_replication":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/action/replication_record"}},"created_at":"2026-05-17T23:42:43.288267+00:00","updated_at":"2026-05-17T23:42:43.288267+00:00"}