{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:R437CDWGXIULEYFKUVZM4LHMF5","short_pith_number":"pith:R437CDWG","canonical_record":{"source":{"id":"1405.3316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-13T22:15:06Z","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"title_canon_sha256":"8bdd579dad52f09c46f0add9ddec0c5a1c58a937386c4756993384f5eff6b66d","abstract_canon_sha256":"4ef868d33e84b32b2cb32f3b59bc405ce02c1a2244412db3af5b05eb58421b91"},"schema_version":"1.0"},"canonical_sha256":"8f37f10ec6ba28b260aaa572ce2cec2f501e7e59c27ade5991f18ceba833c685","source":{"kind":"arxiv","id":"1405.3316","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.3316","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1405.3316v2","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.3316","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"R437CDWGXIUL","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"R437CDWGXIULEYFK","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"R437CDWG","created_at":"2026-05-18T12:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:R437CDWGXIULEYFKUVZM4LHMF5","target":"record","payload":{"canonical_record":{"source":{"id":"1405.3316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-13T22:15:06Z","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"title_canon_sha256":"8bdd579dad52f09c46f0add9ddec0c5a1c58a937386c4756993384f5eff6b66d","abstract_canon_sha256":"4ef868d33e84b32b2cb32f3b59bc405ce02c1a2244412db3af5b05eb58421b91"},"schema_version":"1.0"},"canonical_sha256":"8f37f10ec6ba28b260aaa572ce2cec2f501e7e59c27ade5991f18ceba833c685","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:54.496560Z","signature_b64":"Q7R5noKs2QeK5Vm4GrJieakFQkQuukuhymTzHOpWvBsMONluDwkscP7euKbIENCG3Gk5NVxXUw3Ng3XmVRcJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f37f10ec6ba28b260aaa572ce2cec2f501e7e59c27ade5991f18ceba833c685","last_reissued_at":"2026-05-17T23:43:54.496028Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:54.496028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.3316","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":"2026-05-17T23:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DT+jabW+o/zIXaNTY2nHXMNTmdt2YnxPT/dhEbkqGPbYGDHflo84eNQMytfmGisR7srCLflML2FOsu/3cze0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:33:07.907817Z"},"content_sha256":"d764dcf000a79018f064a703a734509ad014a7eee82b8f58121bbe371a1c3e17","schema_version":"1.0","event_id":"sha256:d764dcf000a79018f064a703a734509ad014a7eee82b8f58121bbe371a1c3e17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:R437CDWGXIULEYFKUVZM4LHMF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Assaf Zeevi, Omar Besbes, Yonatan Gur","submitted_at":"2014-05-13T22:15:06Z","abstract_excerpt":"In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play one of K arms, each characterized by an unknown reward distribution. Reward realizations are only observed when an arm is selected, and the gambler's objective is to maximize his cumulative expected earnings over some given horizon of play T. To do this, the gambler needs to acquire information about arms (exploration) while simultaneously optimizing immediate rewards (exploitation); the price paid due to this trade off is often referred to as the regret, and the main question is how small can this price be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.3316","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":"2026-05-17T23:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5iAukcwpOI/kgrrBMj+SLe9w7QEOontrPTXegxY6TlaFi3rtLHGqStk+LbJ/YP/JcPIpFOZFf4wQD7B0z16CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:33:07.908166Z"},"content_sha256":"6ccfa118a99c77f71cc073db40f1e2b6a16fcdb57d886b0834f795da822844fd","schema_version":"1.0","event_id":"sha256:6ccfa118a99c77f71cc073db40f1e2b6a16fcdb57d886b0834f795da822844fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R437CDWGXIULEYFKUVZM4LHMF5/bundle.json","state_url":"https://pith.science/pith/R437CDWGXIULEYFKUVZM4LHMF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R437CDWGXIULEYFKUVZM4LHMF5/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":"2026-05-28T12:33:07Z","links":{"resolver":"https://pith.science/pith/R437CDWGXIULEYFKUVZM4LHMF5","bundle":"https://pith.science/pith/R437CDWGXIULEYFKUVZM4LHMF5/bundle.json","state":"https://pith.science/pith/R437CDWGXIULEYFKUVZM4LHMF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R437CDWGXIULEYFKUVZM4LHMF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:R437CDWGXIULEYFKUVZM4LHMF5","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":"4ef868d33e84b32b2cb32f3b59bc405ce02c1a2244412db3af5b05eb58421b91","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-13T22:15:06Z","title_canon_sha256":"8bdd579dad52f09c46f0add9ddec0c5a1c58a937386c4756993384f5eff6b66d"},"schema_version":"1.0","source":{"id":"1405.3316","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.3316","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1405.3316v2","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.3316","created_at":"2026-05-17T23:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"R437CDWGXIUL","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"R437CDWGXIULEYFK","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"R437CDWG","created_at":"2026-05-18T12:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:6ccfa118a99c77f71cc073db40f1e2b6a16fcdb57d886b0834f795da822844fd","target":"graph","created_at":"2026-05-17T23:43:54Z","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":"In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play one of K arms, each characterized by an unknown reward distribution. Reward realizations are only observed when an arm is selected, and the gambler's objective is to maximize his cumulative expected earnings over some given horizon of play T. To do this, the gambler needs to acquire information about arms (exploration) while simultaneously optimizing immediate rewards (exploitation); the price paid due to this trade off is often referred to as the regret, and the main question is how small can this price be a","authors_text":"Assaf Zeevi, Omar Besbes, Yonatan Gur","cross_cats":["math.OC","math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-13T22:15:06Z","title":"Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.3316","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:d764dcf000a79018f064a703a734509ad014a7eee82b8f58121bbe371a1c3e17","target":"record","created_at":"2026-05-17T23:43:54Z","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":"4ef868d33e84b32b2cb32f3b59bc405ce02c1a2244412db3af5b05eb58421b91","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-13T22:15:06Z","title_canon_sha256":"8bdd579dad52f09c46f0add9ddec0c5a1c58a937386c4756993384f5eff6b66d"},"schema_version":"1.0","source":{"id":"1405.3316","kind":"arxiv","version":2}},"canonical_sha256":"8f37f10ec6ba28b260aaa572ce2cec2f501e7e59c27ade5991f18ceba833c685","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f37f10ec6ba28b260aaa572ce2cec2f501e7e59c27ade5991f18ceba833c685","first_computed_at":"2026-05-17T23:43:54.496028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:54.496028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q7R5noKs2QeK5Vm4GrJieakFQkQuukuhymTzHOpWvBsMONluDwkscP7euKbIENCG3Gk5NVxXUw3Ng3XmVRcJBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:54.496560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.3316","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d764dcf000a79018f064a703a734509ad014a7eee82b8f58121bbe371a1c3e17","sha256:6ccfa118a99c77f71cc073db40f1e2b6a16fcdb57d886b0834f795da822844fd"],"state_sha256":"6bf4418f2a2c8929fcae34cbc8ca7fcdc70b88eadbe51c22e30f1c0812cbffad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvcXBfRRg+Y+07qxJc+7rOuv+FdjlxgVBl0r3Spx6KP6sA+G+QvLqXNUTj32OCdAqWt4+FvZBN57VORDLXX8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:33:07.910169Z","bundle_sha256":"8dbcced0b071d952fae991b05fe6cddcfe275ef099179f5b7c9db6361904cf62"}}