{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2AGZQWR7DFPGM6QZ3T3J2HRDS2","short_pith_number":"pith:2AGZQWR7","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"},"canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","source":{"kind":"arxiv","id":"1805.01627","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01627","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01627v2","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01627","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"2AGZQWR7DFPG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2AGZQWR7DFPGM6QZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2AGZQWR7","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2AGZQWR7DFPGM6QZ3T3J2HRDS2","target":"record","payload":{"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"},"canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","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"},"source_kind":"arxiv","source_id":"1805.01627","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BaVTexuY9d1Ult3pXywNLsBkEe3/P9ukLQ5iyFP1a1lpQhzrZjWTWk6gY8KzYWadJ7Cnki/YmJTR4JZ0RtY+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:26:42.010809Z"},"content_sha256":"be10760d7f3e6288981cac87e2de8870fd852a280dbc0c4d9a7e90bcd7ca23bd","schema_version":"1.0","event_id":"sha256:be10760d7f3e6288981cac87e2de8870fd852a280dbc0c4d9a7e90bcd7ca23bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2AGZQWR7DFPGM6QZ3T3J2HRDS2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IC9JBhl+wUleHiq72zhjSQtRsBUkL63fAsQUQsyMAQqn9GXNYX2EXnml3I9Uz9U2bwjW1TTmjxDMmh1QkjPVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:26:42.013015Z"},"content_sha256":"880001e2021ba376ba45ed6f0bbf1f154e495eac63ca71903eee89fb52852b7b","schema_version":"1.0","event_id":"sha256:880001e2021ba376ba45ed6f0bbf1f154e495eac63ca71903eee89fb52852b7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/bundle.json","state_url":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T17:26:42Z","links":{"resolver":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2","bundle":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/bundle.json","state":"https://pith.science/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2AGZQWR7DFPGM6QZ3T3J2HRDS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2AGZQWR7DFPGM6QZ3T3J2HRDS2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f5c88544c5dba626c6e0b350e19ba6276ecd62b7c87b4a857ce9558add1182c2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-04T07:11:53Z","title_canon_sha256":"3da971b9f231e2f618273a787105bcb9cd77763b1c02c2c35261b1ee674420cf"},"schema_version":"1.0","source":{"id":"1805.01627","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01627","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01627v2","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01627","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"2AGZQWR7DFPG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2AGZQWR7DFPGM6QZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2AGZQWR7","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:880001e2021ba376ba45ed6f0bbf1f154e495eac63ca71903eee89fb52852b7b","target":"graph","created_at":"2026-05-17T23:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Debabrota Basu, Pierre Senellart, St\\'ephane Bressan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-04T07:11:53Z","title":"BelMan: Bayesian Bandits on the Belief--Reward Manifold"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01627","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be10760d7f3e6288981cac87e2de8870fd852a280dbc0c4d9a7e90bcd7ca23bd","target":"record","created_at":"2026-05-17T23:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f5c88544c5dba626c6e0b350e19ba6276ecd62b7c87b4a857ce9558add1182c2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-04T07:11:53Z","title_canon_sha256":"3da971b9f231e2f618273a787105bcb9cd77763b1c02c2c35261b1ee674420cf"},"schema_version":"1.0","source":{"id":"1805.01627","kind":"arxiv","version":2}},"canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d00d985a3f195e667a19dcf69d1e2396a21d658c882c77df926c89a5c3ffdaac","first_computed_at":"2026-05-17T23:42:43.288194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:43.288194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rqGpCOzQi5cxE6kjYRj6rzP/1rT6jHa5Rsyd2QUEzZHZ7Peh6P7SvBWOx2z9s2Fn8zZyNqYpsCBO0vAj2voQDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:43.288710Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.01627","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be10760d7f3e6288981cac87e2de8870fd852a280dbc0c4d9a7e90bcd7ca23bd","sha256:880001e2021ba376ba45ed6f0bbf1f154e495eac63ca71903eee89fb52852b7b"],"state_sha256":"7b03a179a60f918d6b4c2193792ce18afd503393269dc4dbc8cd4350abfdd8bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URbIeZ5GE3/39PmHFXcihWDeSl6NcLNsvYOvvka4xde4eovV0IzjnEoFY9WG6kEARiOm3cM22nnkMDU6Z5ufDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T17:26:42.017807Z","bundle_sha256":"a0ec91758d662c6fb6eb081b3bb13fcd547026ab09b961a4b885646e3dc17308"}}