{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PRMHRQDJGFLWNLMFIOMNBMTLVC","short_pith_number":"pith:PRMHRQDJ","canonical_record":{"source":{"id":"1809.03084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ME","stat.ML"],"title_canon_sha256":"0c4a6b9675fc6918b02cfd037ed966196569c0003b0163bf772e314f2d008529","abstract_canon_sha256":"2fe7af45a6cdefba26d3752803ab34ae98b26d6913b3042bace2b0380a603fa8"},"schema_version":"1.0"},"canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","source":{"kind":"arxiv","id":"1809.03084","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03084","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03084v3","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03084","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"PRMHRQDJGFLW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PRMHRQDJGFLWNLMF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PRMHRQDJ","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PRMHRQDJGFLWNLMFIOMNBMTLVC","target":"record","payload":{"canonical_record":{"source":{"id":"1809.03084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ME","stat.ML"],"title_canon_sha256":"0c4a6b9675fc6918b02cfd037ed966196569c0003b0163bf772e314f2d008529","abstract_canon_sha256":"2fe7af45a6cdefba26d3752803ab34ae98b26d6913b3042bace2b0380a603fa8"},"schema_version":"1.0"},"canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:57.111297Z","signature_b64":"ZYh0Hoqs+nwQbpAOVBkUqV2SH5JkDm2qioRsaHmDWZvg6XTa95l8oeu/Hc1YdfY1w5GLXlGRskX8Pf+q6nI5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","last_reissued_at":"2026-05-17T23:58:57.110864Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:57.110864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.03084","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFbsJg8tf1ZAHC1U/qrfgfkY+essoAohsuKaO4f3pTdIE/SnlrZN/9vRrqW0Mb8/RxhJb4sabgPdpVUUnWknDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:24:43.848761Z"},"content_sha256":"35f9998208170ee971651e4c78ec34b76ffb5a6d05c9f4625d221e54ee59bf8c","schema_version":"1.0","event_id":"sha256:35f9998208170ee971651e4c78ec34b76ffb5a6d05c9f4625d221e54ee59bf8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PRMHRQDJGFLWNLMFIOMNBMTLVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Counterfactual Learning from Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kohei Yata, Shota Yasui, Yusuke Narita","submitted_at":"2018-09-10T02:08:14Z","abstract_excerpt":"What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in a wide class of estimators, achieving variance reduction relative to standard estimators. We then apply our estimators to improve advertisement design by a major advertisement company. Consistent with the theoretical result, our estimators allow us to improve on the existing ban"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03084","kind":"arxiv","version":3},"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":"2026-05-17T23:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nA1vmcrZlhlCPxoBXtMAMAqx6bYofkQueOVbaE/sE+A4WES9vXij2BQ2AMkB7Jcu/n4OM8R39TAKHvDaKvlcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:24:43.849574Z"},"content_sha256":"953f3034089a44743ef546b53b1cbeb006977939e28c148de5c5869fca946ea6","schema_version":"1.0","event_id":"sha256:953f3034089a44743ef546b53b1cbeb006977939e28c148de5c5869fca946ea6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/bundle.json","state_url":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/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":"2026-05-31T15:24:43Z","links":{"resolver":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC","bundle":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/bundle.json","state":"https://pith.science/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRMHRQDJGFLWNLMFIOMNBMTLVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PRMHRQDJGFLWNLMFIOMNBMTLVC","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":"2fe7af45a6cdefba26d3752803ab34ae98b26d6913b3042bace2b0380a603fa8","cross_cats_sorted":["cs.AI","cs.IR","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","title_canon_sha256":"0c4a6b9675fc6918b02cfd037ed966196569c0003b0163bf772e314f2d008529"},"schema_version":"1.0","source":{"id":"1809.03084","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03084","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03084v3","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03084","created_at":"2026-05-17T23:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"PRMHRQDJGFLW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PRMHRQDJGFLWNLMF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PRMHRQDJ","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:953f3034089a44743ef546b53b1cbeb006977939e28c148de5c5869fca946ea6","target":"graph","created_at":"2026-05-17T23:58:57Z","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":"What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in a wide class of estimators, achieving variance reduction relative to standard estimators. We then apply our estimators to improve advertisement design by a major advertisement company. Consistent with the theoretical result, our estimators allow us to improve on the existing ban","authors_text":"Kohei Yata, Shota Yasui, Yusuke Narita","cross_cats":["cs.AI","cs.IR","stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","title":"Efficient Counterfactual Learning from Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03084","kind":"arxiv","version":3},"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":"sha256:35f9998208170ee971651e4c78ec34b76ffb5a6d05c9f4625d221e54ee59bf8c","target":"record","created_at":"2026-05-17T23:58:57Z","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":"2fe7af45a6cdefba26d3752803ab34ae98b26d6913b3042bace2b0380a603fa8","cross_cats_sorted":["cs.AI","cs.IR","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T02:08:14Z","title_canon_sha256":"0c4a6b9675fc6918b02cfd037ed966196569c0003b0163bf772e314f2d008529"},"schema_version":"1.0","source":{"id":"1809.03084","kind":"arxiv","version":3}},"canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c5878c069315766ad854398d0b26ba89a65f60624ae8df235e6535ce77441e4","first_computed_at":"2026-05-17T23:58:57.110864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:57.110864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYh0Hoqs+nwQbpAOVBkUqV2SH5JkDm2qioRsaHmDWZvg6XTa95l8oeu/Hc1YdfY1w5GLXlGRskX8Pf+q6nI5AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:57.111297Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03084","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35f9998208170ee971651e4c78ec34b76ffb5a6d05c9f4625d221e54ee59bf8c","sha256:953f3034089a44743ef546b53b1cbeb006977939e28c148de5c5869fca946ea6"],"state_sha256":"61c03deeea563b14155b2f609fc9f26c14e238f77febd7d03b2519cd955ad5ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SeaGyhMARfEoYb5cyGlRWd/IOSttDuxba9XqX5J+E4MErZ3IsqUV3Wkuu/ew3ET3UKDS+6G1TmfaX4A7gD/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T15:24:43.853969Z","bundle_sha256":"54f36059bc45f9d388e811f977fd8eb2b3cfd529d54db8ebec3e263a35dbc9a0"}}