{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T5523W4JVEQBV2NNWHSD3RMUNR","short_pith_number":"pith:T5523W4J","schema_version":"1.0","canonical_sha256":"9f7baddb89a9201ae9adb1e43dc5946c52626114d0567ac50563f2652eb13255","source":{"kind":"arxiv","id":"2212.01925","version":1},"attestation_state":"computed","paper":{"title":"Counterfactual Learning with General Data-generating Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Shimizu, Kohei Yata, Kyohei Okumura, Yusuke Narita","submitted_at":"2022-12-04T21:07:46Z","abstract_excerpt":"Off-policy evaluation (OPE) attempts to predict the performance of counterfactual policies using log data from a different policy. We extend its applicability by developing an OPE method for a class of both full support and deficient support logging policies in contextual-bandit settings. This class includes deterministic bandit (such as Upper Confidence Bound) as well as deterministic decision-making based on supervised and unsupervised learning. We prove that our method's prediction converges in probability to the true performance of a counterfactual policy as the sample size increases. We v"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.01925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-04T21:07:46Z","cross_cats_sorted":["cs.AI","econ.EM","stat.AP","stat.ML"],"title_canon_sha256":"7b39e46d8b73f34836e52b113ee5a330373a48fd5a908de031476da577d463c0","abstract_canon_sha256":"cf10e2810cefbb01f28e0baba7376dbf445bd92013080afb9cf63d9b9993e575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:18.710699Z","signature_b64":"laCkQsFKyu9UjaRiIs6utl3I+2TeMb/J6i+nvDar96uVaSs4k6bBzF0aCFJtj6f73UDvppBPGH45tEiodhS7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7baddb89a9201ae9adb1e43dc5946c52626114d0567ac50563f2652eb13255","last_reissued_at":"2026-07-05T05:22:18.710294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:18.710294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Learning with General Data-generating Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Shimizu, Kohei Yata, Kyohei Okumura, Yusuke Narita","submitted_at":"2022-12-04T21:07:46Z","abstract_excerpt":"Off-policy evaluation (OPE) attempts to predict the performance of counterfactual policies using log data from a different policy. We extend its applicability by developing an OPE method for a class of both full support and deficient support logging policies in contextual-bandit settings. This class includes deterministic bandit (such as Upper Confidence Bound) as well as deterministic decision-making based on supervised and unsupervised learning. We prove that our method's prediction converges in probability to the true performance of a counterfactual policy as the sample size increases. We v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01925","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.01925/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.01925","created_at":"2026-07-05T05:22:18.710355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01925v1","created_at":"2026-07-05T05:22:18.710355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01925","created_at":"2026-07-05T05:22:18.710355+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5523W4JVEQB","created_at":"2026-07-05T05:22:18.710355+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5523W4JVEQBV2NN","created_at":"2026-07-05T05:22:18.710355+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5523W4J","created_at":"2026-07-05T05:22:18.710355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR","json":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR.json","graph_json":"https://pith.science/api/pith-number/T5523W4JVEQBV2NNWHSD3RMUNR/graph.json","events_json":"https://pith.science/api/pith-number/T5523W4JVEQBV2NNWHSD3RMUNR/events.json","paper":"https://pith.science/paper/T5523W4J"},"agent_actions":{"view_html":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR","download_json":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR.json","view_paper":"https://pith.science/paper/T5523W4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01925&json=true","fetch_graph":"https://pith.science/api/pith-number/T5523W4JVEQBV2NNWHSD3RMUNR/graph.json","fetch_events":"https://pith.science/api/pith-number/T5523W4JVEQBV2NNWHSD3RMUNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR/action/storage_attestation","attest_author":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR/action/author_attestation","sign_citation":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR/action/citation_signature","submit_replication":"https://pith.science/pith/T5523W4JVEQBV2NNWHSD3RMUNR/action/replication_record"}},"created_at":"2026-07-05T05:22:18.710355+00:00","updated_at":"2026-07-05T05:22:18.710355+00:00"}