{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UYEXOIMMKDTSP55WSP6CAA76W6","short_pith_number":"pith:UYEXOIMM","canonical_record":{"source":{"id":"1901.04723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T09:20:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f441b094e46018879b84429bccd1987ef58f4d105bfa126acfba9a1ecd428f0","abstract_canon_sha256":"57e8a8de660601f2f7eea8641a22946610f107ad727b89cb839e7f9ce635a047"},"schema_version":"1.0"},"canonical_sha256":"a60977218c50e727f7b693fc2003feb791dfd7623d983fece58918f2152749a5","source":{"kind":"arxiv","id":"1901.04723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.04723","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"1901.04723v1","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.04723","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"UYEXOIMMKDTS","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UYEXOIMMKDTSP55W","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UYEXOIMM","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UYEXOIMMKDTSP55WSP6CAA76W6","target":"record","payload":{"canonical_record":{"source":{"id":"1901.04723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T09:20:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f441b094e46018879b84429bccd1987ef58f4d105bfa126acfba9a1ecd428f0","abstract_canon_sha256":"57e8a8de660601f2f7eea8641a22946610f107ad727b89cb839e7f9ce635a047"},"schema_version":"1.0"},"canonical_sha256":"a60977218c50e727f7b693fc2003feb791dfd7623d983fece58918f2152749a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:21.937726Z","signature_b64":"cnyhURJl8EgNN4t2CTVekz6XhDonC3y41N6BIlrdY5bmWUBnUp5ZCQzM8YHYVFL55cxh/ogVRzowk1cbv7XVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a60977218c50e727f7b693fc2003feb791dfd7623d983fece58918f2152749a5","last_reissued_at":"2026-05-17T23:56:21.937250Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:21.937250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.04723","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8U0lD18SwX6gm1LxmH/gDl/ocXnhZvl5bDY9yv73XPDIHDMLEAcisch+RrMJ97vlwo7URlgQ/3ILCGDD6oRvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:27:01.685044Z"},"content_sha256":"0e95bed353382ab4d306ac08d2aac96e1139ee66f81f27aa9cd4379828024cfb","schema_version":"1.0","event_id":"sha256:0e95bed353382ab4d306ac08d2aac96e1139ee66f81f27aa9cd4379828024cfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UYEXOIMMKDTSP55WSP6CAA76W6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitation-Regularized Offline Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balakrishnan (Murali) Narayanaswamy, Yifei Ma, Yu-Xiang Wang","submitted_at":"2019-01-15T09:20:53Z","abstract_excerpt":"We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to evaluate what would happen if different actions were taken in the same contexts, so as to optimize the action policies accordingly. The typical approach to this problem, inverse probability weighted estimation (IPWE) [Bottou et al., 2013], requires logged action probabilities, which may be missing in practice due to engineering complications. Even when available"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.04723","kind":"arxiv","version":1},"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":"2026-05-17T23:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwQwySbJTfBj1YfEOZPu2k2X7swexI/TAMbvryUdIyRqDpLXfY70u9pbI0H6C9J9G/vZVpnM78LYya5NTdXnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:27:01.685405Z"},"content_sha256":"56042a3cb167ef1d3206c7d2b75832e727718f84e3b61b7a4af1bb218c4be847","schema_version":"1.0","event_id":"sha256:56042a3cb167ef1d3206c7d2b75832e727718f84e3b61b7a4af1bb218c4be847"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYEXOIMMKDTSP55WSP6CAA76W6/bundle.json","state_url":"https://pith.science/pith/UYEXOIMMKDTSP55WSP6CAA76W6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYEXOIMMKDTSP55WSP6CAA76W6/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":"2026-06-05T08:27:01Z","links":{"resolver":"https://pith.science/pith/UYEXOIMMKDTSP55WSP6CAA76W6","bundle":"https://pith.science/pith/UYEXOIMMKDTSP55WSP6CAA76W6/bundle.json","state":"https://pith.science/pith/UYEXOIMMKDTSP55WSP6CAA76W6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYEXOIMMKDTSP55WSP6CAA76W6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UYEXOIMMKDTSP55WSP6CAA76W6","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":"57e8a8de660601f2f7eea8641a22946610f107ad727b89cb839e7f9ce635a047","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T09:20:53Z","title_canon_sha256":"7f441b094e46018879b84429bccd1987ef58f4d105bfa126acfba9a1ecd428f0"},"schema_version":"1.0","source":{"id":"1901.04723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.04723","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"1901.04723v1","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.04723","created_at":"2026-05-17T23:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"UYEXOIMMKDTS","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UYEXOIMMKDTSP55W","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UYEXOIMM","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:56042a3cb167ef1d3206c7d2b75832e727718f84e3b61b7a4af1bb218c4be847","target":"graph","created_at":"2026-05-17T23:56:21Z","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 study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to evaluate what would happen if different actions were taken in the same contexts, so as to optimize the action policies accordingly. The typical approach to this problem, inverse probability weighted estimation (IPWE) [Bottou et al., 2013], requires logged action probabilities, which may be missing in practice due to engineering complications. Even when available","authors_text":"Balakrishnan (Murali) Narayanaswamy, Yifei Ma, Yu-Xiang Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T09:20:53Z","title":"Imitation-Regularized Offline Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.04723","kind":"arxiv","version":1},"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":"sha256:0e95bed353382ab4d306ac08d2aac96e1139ee66f81f27aa9cd4379828024cfb","target":"record","created_at":"2026-05-17T23:56:21Z","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":"57e8a8de660601f2f7eea8641a22946610f107ad727b89cb839e7f9ce635a047","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T09:20:53Z","title_canon_sha256":"7f441b094e46018879b84429bccd1987ef58f4d105bfa126acfba9a1ecd428f0"},"schema_version":"1.0","source":{"id":"1901.04723","kind":"arxiv","version":1}},"canonical_sha256":"a60977218c50e727f7b693fc2003feb791dfd7623d983fece58918f2152749a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a60977218c50e727f7b693fc2003feb791dfd7623d983fece58918f2152749a5","first_computed_at":"2026-05-17T23:56:21.937250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:21.937250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cnyhURJl8EgNN4t2CTVekz6XhDonC3y41N6BIlrdY5bmWUBnUp5ZCQzM8YHYVFL55cxh/ogVRzowk1cbv7XVDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:21.937726Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.04723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e95bed353382ab4d306ac08d2aac96e1139ee66f81f27aa9cd4379828024cfb","sha256:56042a3cb167ef1d3206c7d2b75832e727718f84e3b61b7a4af1bb218c4be847"],"state_sha256":"6c25f740f7333103e96a76225dcb7f80ffba9200108a84e7cd54d50c8fc4e9e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Luyb0RAlx3Znw5dUtEenLWqEAcPvqapu0kMlWKDdkh3zNnXLnO7gjWSzzLr6YVjzEW1M1Wh6zLZGXvsd19QTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T08:27:01.687502Z","bundle_sha256":"318b5c11701002fbd2b10df73973c37e71ae3f7cc9bc55bd3686665a0e4b5f38"}}