{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WJBGVHBATP3SOBOINIWS4BC3NI","short_pith_number":"pith:WJBGVHBA","schema_version":"1.0","canonical_sha256":"b2426a9c209bf72705c86a2d2e045b6a25fe68269b3cf4b81cf2e748cb7b9299","source":{"kind":"arxiv","id":"2209.07148","version":3},"attestation_state":"computed","paper":{"title":"Semi-supervised Batch Learning From Logged Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Armin Behnamnia, Chengchun Shi, Gholamali Aminian, Hamid R. Rabiee, Laura Toni, Miguel R. D. Rodrigues, Omar Rivasplata, Roberto Vega","submitted_at":"2022-09-15T08:58:28Z","abstract_excerpt":"Off-policy learning methods are intended to learn a policy from logged data, which includes context, action, and feedback (cost or reward) for each sample point. In this work, we build on the counterfactual risk minimization framework, which also assumes access to propensity scores. We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data. We refer to this type of learning as semi-supervised batch learning from logged data, which arises in a wide range of application domains. We deriv"},"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":"2209.07148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T08:58:28Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"98e68fcaeded1d4bc79061e824b75b0861553b5168db03922a1e0dfd7d8f8270","abstract_canon_sha256":"9494329a93e784faba664a70ccda23a35d27beb2e39f9591d2b65b9673e6bc5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:13.890418Z","signature_b64":"HUlBfKCkaSw8buW/MHTPLuPd+riMMzI8LcCpToA8nmaPC4bYZTS3LAGy6pkVleK8h4le08FF3kkbtaNxGfDnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2426a9c209bf72705c86a2d2e045b6a25fe68269b3cf4b81cf2e748cb7b9299","last_reissued_at":"2026-07-05T07:46:13.889984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:13.889984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Batch Learning From Logged Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Armin Behnamnia, Chengchun Shi, Gholamali Aminian, Hamid R. Rabiee, Laura Toni, Miguel R. D. Rodrigues, Omar Rivasplata, Roberto Vega","submitted_at":"2022-09-15T08:58:28Z","abstract_excerpt":"Off-policy learning methods are intended to learn a policy from logged data, which includes context, action, and feedback (cost or reward) for each sample point. In this work, we build on the counterfactual risk minimization framework, which also assumes access to propensity scores. We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data. We refer to this type of learning as semi-supervised batch learning from logged data, which arises in a wide range of application domains. We deriv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07148","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.07148/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":"2209.07148","created_at":"2026-07-05T07:46:13.890043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07148v3","created_at":"2026-07-05T07:46:13.890043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07148","created_at":"2026-07-05T07:46:13.890043+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJBGVHBATP3S","created_at":"2026-07-05T07:46:13.890043+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJBGVHBATP3SOBOI","created_at":"2026-07-05T07:46:13.890043+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJBGVHBA","created_at":"2026-07-05T07:46:13.890043+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/WJBGVHBATP3SOBOINIWS4BC3NI","json":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI.json","graph_json":"https://pith.science/api/pith-number/WJBGVHBATP3SOBOINIWS4BC3NI/graph.json","events_json":"https://pith.science/api/pith-number/WJBGVHBATP3SOBOINIWS4BC3NI/events.json","paper":"https://pith.science/paper/WJBGVHBA"},"agent_actions":{"view_html":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI","download_json":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI.json","view_paper":"https://pith.science/paper/WJBGVHBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07148&json=true","fetch_graph":"https://pith.science/api/pith-number/WJBGVHBATP3SOBOINIWS4BC3NI/graph.json","fetch_events":"https://pith.science/api/pith-number/WJBGVHBATP3SOBOINIWS4BC3NI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI/action/storage_attestation","attest_author":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI/action/author_attestation","sign_citation":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI/action/citation_signature","submit_replication":"https://pith.science/pith/WJBGVHBATP3SOBOINIWS4BC3NI/action/replication_record"}},"created_at":"2026-07-05T07:46:13.890043+00:00","updated_at":"2026-07-05T07:46:13.890043+00:00"}