{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YUO6FERR5QI2YQTIWLUGZVXJI5","short_pith_number":"pith:YUO6FERR","canonical_record":{"source":{"id":"1808.00232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a6a926fb7eceed2d638ca96b6b5ef66378e4b05c2e04ff04c0154cb528d70206","abstract_canon_sha256":"d649ff9c12654cd6dff0aeefdf0bc7645b9313b7b77c89c2ba1438e42a99791d"},"schema_version":"1.0"},"canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","source":{"kind":"arxiv","id":"1808.00232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00232","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00232v1","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00232","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"YUO6FERR5QI2","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YUO6FERR5QI2YQTI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YUO6FERR","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YUO6FERR5QI2YQTIWLUGZVXJI5","target":"record","payload":{"canonical_record":{"source":{"id":"1808.00232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a6a926fb7eceed2d638ca96b6b5ef66378e4b05c2e04ff04c0154cb528d70206","abstract_canon_sha256":"d649ff9c12654cd6dff0aeefdf0bc7645b9313b7b77c89c2ba1438e42a99791d"},"schema_version":"1.0"},"canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:08.344523Z","signature_b64":"5zXLHrBfSGO7UzKowEcaXhEhDT+zUllYaGeUkIWuveBW8XILHHYMUoM76RF/EyzB8CgARtmCTuXYHRRqLhujDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","last_reissued_at":"2026-05-18T00:09:08.344042Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:08.344042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.00232","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":"2026-05-18T00:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4B9NUO/EyaCAO2BK5ApBGYCUXf0ai0nZKYKmE1Fc2u7w4XqR+ZTt37m/bDSu6PxDCRC0HvFJ4mDpGx3sbGIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:42:51.106035Z"},"content_sha256":"e83834e71d2bc565ae0033d7a45ca46747df9d80e46811fa4e72dea4c192cf6f","schema_version":"1.0","event_id":"sha256:e83834e71d2bc565ae0033d7a45ca46747df9d80e46811fa4e72dea4c192cf6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YUO6FERR5QI2YQTIWLUGZVXJI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boyi Liu, Jian Peng, Qiang Liu, Yuan Xie, Yuan Zhou, Zhaoran Wang","submitted_at":"2018-08-01T08:56:32Z","abstract_excerpt":"When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00232","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":"2026-05-18T00:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pvw037yEJrjhlx3o2hZRnwN+O4ULaC+kwMN5kDxxk2iq7sH74L6R5PIgq2zgYikwLRBjhD7Ob4/kcYiL1UvJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:42:51.106406Z"},"content_sha256":"f57292e6be2f1be9076cdf60803e744d04798b72fbc7596ded5d5beb22ceecce","schema_version":"1.0","event_id":"sha256:f57292e6be2f1be9076cdf60803e744d04798b72fbc7596ded5d5beb22ceecce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/bundle.json","state_url":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/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":"2026-07-04T08:42:51Z","links":{"resolver":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5","bundle":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/bundle.json","state":"https://pith.science/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YUO6FERR5QI2YQTIWLUGZVXJI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YUO6FERR5QI2YQTIWLUGZVXJI5","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":"d649ff9c12654cd6dff0aeefdf0bc7645b9313b7b77c89c2ba1438e42a99791d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","title_canon_sha256":"a6a926fb7eceed2d638ca96b6b5ef66378e4b05c2e04ff04c0154cb528d70206"},"schema_version":"1.0","source":{"id":"1808.00232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00232","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00232v1","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00232","created_at":"2026-05-18T00:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"YUO6FERR5QI2","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YUO6FERR5QI2YQTI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YUO6FERR","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:f57292e6be2f1be9076cdf60803e744d04798b72fbc7596ded5d5beb22ceecce","target":"graph","created_at":"2026-05-18T00:09:08Z","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":"When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems","authors_text":"Boyi Liu, Jian Peng, Qiang Liu, Yuan Xie, Yuan Zhou, Zhaoran Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","title":"Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00232","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:e83834e71d2bc565ae0033d7a45ca46747df9d80e46811fa4e72dea4c192cf6f","target":"record","created_at":"2026-05-18T00:09:08Z","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":"d649ff9c12654cd6dff0aeefdf0bc7645b9313b7b77c89c2ba1438e42a99791d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-01T08:56:32Z","title_canon_sha256":"a6a926fb7eceed2d638ca96b6b5ef66378e4b05c2e04ff04c0154cb528d70206"},"schema_version":"1.0","source":{"id":"1808.00232","kind":"arxiv","version":1}},"canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c51de29231ec11ac4268b2e86cd6e9476a2c3483e1aec4147566f6f564a9e13e","first_computed_at":"2026-05-18T00:09:08.344042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:08.344042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5zXLHrBfSGO7UzKowEcaXhEhDT+zUllYaGeUkIWuveBW8XILHHYMUoM76RF/EyzB8CgARtmCTuXYHRRqLhujDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:08.344523Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.00232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e83834e71d2bc565ae0033d7a45ca46747df9d80e46811fa4e72dea4c192cf6f","sha256:f57292e6be2f1be9076cdf60803e744d04798b72fbc7596ded5d5beb22ceecce"],"state_sha256":"3517650076f7f4987ac329d3e306323fe831404b88d1d36e34363134d870a9d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73gFAnc/J44X61w23Ko9jKp/RKsI5NSUMKHcP5+gaKrOfESeOdHRqi9vLPaZ3uV2h50V4071YIH0JTVG+U86DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T08:42:51.108300Z","bundle_sha256":"f04c010a9153ea72600390ddd8ea64b4f7ee95581465d97a4e81773fce4fd1c9"}}