{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:R5W2MD3SJFTWUJ6OJD76UCNP47","short_pith_number":"pith:R5W2MD3S","canonical_record":{"source":{"id":"1202.1334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"389d8945457550323f886e1bd287df8838bbd1b518f374117cc8ed8c4ca01599","abstract_canon_sha256":"868bbf5bf530cfbe5b2ed1b4526edd7f612bd26a91aa4a98caab67d94e665757"},"schema_version":"1.0"},"canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","source":{"kind":"arxiv","id":"1202.1334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.1334","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1202.1334v2","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1334","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"R5W2MD3SJFTW","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"R5W2MD3SJFTWUJ6O","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"R5W2MD3S","created_at":"2026-05-18T12:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:R5W2MD3SJFTWUJ6OJD76UCNP47","target":"record","payload":{"canonical_record":{"source":{"id":"1202.1334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"389d8945457550323f886e1bd287df8838bbd1b518f374117cc8ed8c4ca01599","abstract_canon_sha256":"868bbf5bf530cfbe5b2ed1b4526edd7f612bd26a91aa4a98caab67d94e665757"},"schema_version":"1.0"},"canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:01:01.394268Z","signature_b64":"dI5baVb5mH3K/RTBoVs0dK1FgXGPH0yRiGTYLTZ3O/4KFl6X7fKzbyP86kkd2IrbvlBbIyvcIqhuoci58RhnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","last_reissued_at":"2026-05-18T04:01:01.393591Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:01:01.393591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.1334","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":"2026-05-18T04:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WauBZlrOto0ub7T9ZYexaRyw4qiTtKuSU2oZyERYFZzs3HdjsDp3iPIm86YPwDQKMqZTrLj5/LrnjrJ/ZN7cBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:08:49.780480Z"},"content_sha256":"c1be383c2c59471211a2b54bf4b561aac91fa658189479100d05afa3e8457ab5","schema_version":"1.0","event_id":"sha256:c1be383c2c59471211a2b54bf4b561aac91fa658189479100d05afa3e8457ab5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:R5W2MD3SJFTWUJ6OJD76UCNP47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Bandit Learning with Predictable Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, John Langford, Miroslav Dud\\'ik, Robert E. Schapire, Satyen Kale","submitted_at":"2012-02-07T02:27:55Z","abstract_excerpt":"Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a realizability assumption: there exists a function in a (known) function class, always capable of predicting the expected reward, given the action and context. Under this assumption, we show three things. We present a new algorithm---Regressor Elimination--- with a regret similar to the agnostic setting (i.e. in the absence of realizability assumption). We prove a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1334","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":"2026-05-18T04:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLUaXUCNE6CG/TUjv/JYtSw3EmvLjH7PhuvNJuMJfsdnwH/hbPcfjnrLOcQRp6t8z6aEgZtkaGEWDbooNmlUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:08:49.781011Z"},"content_sha256":"c4c7b5ff43e608b116393c61f4c7675f80cb2b6f50d04b6410ca90f5a7daa117","schema_version":"1.0","event_id":"sha256:c4c7b5ff43e608b116393c61f4c7675f80cb2b6f50d04b6410ca90f5a7daa117"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/bundle.json","state_url":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/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":"2026-05-27T05:08:49Z","links":{"resolver":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47","bundle":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/bundle.json","state":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:R5W2MD3SJFTWUJ6OJD76UCNP47","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":"868bbf5bf530cfbe5b2ed1b4526edd7f612bd26a91aa4a98caab67d94e665757","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","title_canon_sha256":"389d8945457550323f886e1bd287df8838bbd1b518f374117cc8ed8c4ca01599"},"schema_version":"1.0","source":{"id":"1202.1334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.1334","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1202.1334v2","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1334","created_at":"2026-05-18T04:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"R5W2MD3SJFTW","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"R5W2MD3SJFTWUJ6O","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"R5W2MD3S","created_at":"2026-05-18T12:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:c4c7b5ff43e608b116393c61f4c7675f80cb2b6f50d04b6410ca90f5a7daa117","target":"graph","created_at":"2026-05-18T04:01:01Z","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":"Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a realizability assumption: there exists a function in a (known) function class, always capable of predicting the expected reward, given the action and context. Under this assumption, we show three things. We present a new algorithm---Regressor Elimination--- with a regret similar to the agnostic setting (i.e. in the absence of realizability assumption). We prove a ","authors_text":"Alekh Agarwal, John Langford, Miroslav Dud\\'ik, Robert E. Schapire, Satyen Kale","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","title":"Contextual Bandit Learning with Predictable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1334","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:c1be383c2c59471211a2b54bf4b561aac91fa658189479100d05afa3e8457ab5","target":"record","created_at":"2026-05-18T04:01:01Z","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":"868bbf5bf530cfbe5b2ed1b4526edd7f612bd26a91aa4a98caab67d94e665757","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","title_canon_sha256":"389d8945457550323f886e1bd287df8838bbd1b518f374117cc8ed8c4ca01599"},"schema_version":"1.0","source":{"id":"1202.1334","kind":"arxiv","version":2}},"canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","first_computed_at":"2026-05-18T04:01:01.393591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:01:01.393591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dI5baVb5mH3K/RTBoVs0dK1FgXGPH0yRiGTYLTZ3O/4KFl6X7fKzbyP86kkd2IrbvlBbIyvcIqhuoci58RhnDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:01:01.394268Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.1334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1be383c2c59471211a2b54bf4b561aac91fa658189479100d05afa3e8457ab5","sha256:c4c7b5ff43e608b116393c61f4c7675f80cb2b6f50d04b6410ca90f5a7daa117"],"state_sha256":"dbee840c3fbb2d28174404e9bc026d4982ad6b65e9ed7e5b2f71dc37c72895a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOS7Ctxbx0onwRsWt/nXHvainWhJMRuIZ+UogRkHufL0ErxsP/sAAE7jbiB5HPWSUePWq0Y+5O0Sttx22TmZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:08:49.784460Z","bundle_sha256":"07564e99d07d7d739cc5c762451d4fc5e08ad27745e1645b393b0cce3a6f1aa1"}}