{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:JVDJDNU3SMYY6L3EMD54HS32WQ","short_pith_number":"pith:JVDJDNU3","canonical_record":{"source":{"id":"1402.0555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5cb3bbda6555e1ebd9c6b9af30470565ce07aec834c5f390e1c9443e9e13b3e9","abstract_canon_sha256":"1fba3f5b1a1a5276af99934322c542396f9e309ba7648f67df7305dc0e9e8dcf"},"schema_version":"1.0"},"canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","source":{"kind":"arxiv","id":"1402.0555","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0555","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0555v2","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0555","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"JVDJDNU3SMYY","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"JVDJDNU3SMYY6L3E","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"JVDJDNU3","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:JVDJDNU3SMYY6L3EMD54HS32WQ","target":"record","payload":{"canonical_record":{"source":{"id":"1402.0555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5cb3bbda6555e1ebd9c6b9af30470565ce07aec834c5f390e1c9443e9e13b3e9","abstract_canon_sha256":"1fba3f5b1a1a5276af99934322c542396f9e309ba7648f67df7305dc0e9e8dcf"},"schema_version":"1.0"},"canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:40:10.784089Z","signature_b64":"VV5mkFLojHY4KfWBSy0s1hbY848jny/ojFwL7oyOYTvdfPbHvdZejOIOqqZJrUhjz5ufp4MaH+0iWRRv+8zsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","last_reissued_at":"2026-05-18T02:40:10.783437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:40:10.783437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.0555","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":"2026-05-18T02:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+dGH6/XoanqcnYVeElssGHLeUSLWsey6neZZ8ZEwZPm+szsy9bVnpPrCeLtA30k6nG1P+wjvYeSRVfLw3JrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:35:17.601867Z"},"content_sha256":"7e017110fd11a6c0b4d712a5af33dc153096e5a2fd762e7f45a60c4397fb2ec0","schema_version":"1.0","event_id":"sha256:7e017110fd11a6c0b4d712a5af33dc153096e5a2fd762e7f45a60c4397fb2ec0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:JVDJDNU3SMYY6L3EMD54HS32WQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Daniel Hsu, John Langford, Lihong Li, Robert E. Schapire, Satyen Kale","submitted_at":"2014-02-04T00:48:29Z","abstract_excerpt":"We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problems and achieves the statistically optimal regret guarantee with only $\\tilde{O}(\\sqrt{KT/\\log N})$ oracle calls across all $T$ rounds, where $N$ is the number of policies in the policy class we compete against. By doing so, we obtain the most practical contextual bandit learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0555","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":"2026-05-18T02:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HHTgz+Tn3A8qhWQoKziPAatbYxl521mg9cnSZniuNXVaOpYdhpPRQTIQ70rzeDGqCzhqSw1UGVP9+m5DLaUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:35:17.602574Z"},"content_sha256":"5ffdbce0627ef421c7d84ff85da3789841f5e7300aa5205b4e01ce4b9f0930d9","schema_version":"1.0","event_id":"sha256:5ffdbce0627ef421c7d84ff85da3789841f5e7300aa5205b4e01ce4b9f0930d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/bundle.json","state_url":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/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":"2026-05-26T22:35:17Z","links":{"resolver":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ","bundle":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/bundle.json","state":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:JVDJDNU3SMYY6L3EMD54HS32WQ","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":"1fba3f5b1a1a5276af99934322c542396f9e309ba7648f67df7305dc0e9e8dcf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","title_canon_sha256":"5cb3bbda6555e1ebd9c6b9af30470565ce07aec834c5f390e1c9443e9e13b3e9"},"schema_version":"1.0","source":{"id":"1402.0555","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0555","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0555v2","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0555","created_at":"2026-05-18T02:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"JVDJDNU3SMYY","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"JVDJDNU3SMYY6L3E","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"JVDJDNU3","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:5ffdbce0627ef421c7d84ff85da3789841f5e7300aa5205b4e01ce4b9f0930d9","target":"graph","created_at":"2026-05-18T02:40:10Z","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 present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problems and achieves the statistically optimal regret guarantee with only $\\tilde{O}(\\sqrt{KT/\\log N})$ oracle calls across all $T$ rounds, where $N$ is the number of policies in the policy class we compete against. By doing so, we obtain the most practical contextual bandit learning a","authors_text":"Alekh Agarwal, Daniel Hsu, John Langford, Lihong Li, Robert E. Schapire, Satyen Kale","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0555","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":"sha256:7e017110fd11a6c0b4d712a5af33dc153096e5a2fd762e7f45a60c4397fb2ec0","target":"record","created_at":"2026-05-18T02:40:10Z","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":"1fba3f5b1a1a5276af99934322c542396f9e309ba7648f67df7305dc0e9e8dcf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","title_canon_sha256":"5cb3bbda6555e1ebd9c6b9af30470565ce07aec834c5f390e1c9443e9e13b3e9"},"schema_version":"1.0","source":{"id":"1402.0555","kind":"arxiv","version":2}},"canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","first_computed_at":"2026-05-18T02:40:10.783437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:40:10.783437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VV5mkFLojHY4KfWBSy0s1hbY848jny/ojFwL7oyOYTvdfPbHvdZejOIOqqZJrUhjz5ufp4MaH+0iWRRv+8zsCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:40:10.784089Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.0555","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e017110fd11a6c0b4d712a5af33dc153096e5a2fd762e7f45a60c4397fb2ec0","sha256:5ffdbce0627ef421c7d84ff85da3789841f5e7300aa5205b4e01ce4b9f0930d9"],"state_sha256":"492003ec334fe6ddfcf5353aa0413e09e349e06d0b8fa03b798adeea06ebb716"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eV9oJMhrffrG47k771PHUN9V6aLbnePzJ65LMrgeKiqLJ14NzLOJa/52KtKm3PTOjHmlj5thREKN80JXvVC5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T22:35:17.606083Z","bundle_sha256":"3ce4fd21fe9c0bb622e42521cfd36e4ec350ee53f400cb69ac065dc3857d1977"}}