{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XLKZVF36ACKCEFCPVCRDQR4O3Y","short_pith_number":"pith:XLKZVF36","schema_version":"1.0","canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","source":{"kind":"arxiv","id":"2107.01360","version":2},"attestation_state":"computed","paper":{"title":"Supervised Off-Policy Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Houqiang Li, Jian Yuan, Tao Qin, Tie-Yan Liu, Xudong Zhang, Yue Jin, Yue Zhang","submitted_at":"2021-07-03T07:01:23Z","abstract_excerpt":"Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies and choose a good one, which is a much simpler task than precisely evaluating their true performance; and (2) there are usually multiple policies that have been deployed to serve users in real-world systems and thus the true performance of these policies can be known. Inspired by the two observations"},"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":"2107.01360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T07:01:23Z","cross_cats_sorted":[],"title_canon_sha256":"d10439e8118bec8d305fe66a6bc73b74325a3d2da9a74f93ed7c54eff1706241","abstract_canon_sha256":"4b6e6054432e18e0a2b011fc0232c7cab88e34a94935c3865996c28cdb8eeddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:50.419359Z","signature_b64":"SUkXtTiXt8RRohu1ezZw7uqaYJTAT7YKVBh7oFjJoMm93fuhoaFkUU28zi91picjoZ4GoyYBpFDLm87tWdXUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","last_reissued_at":"2026-07-05T04:32:50.418779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:50.418779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Off-Policy Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Houqiang Li, Jian Yuan, Tao Qin, Tie-Yan Liu, Xudong Zhang, Yue Jin, Yue Zhang","submitted_at":"2021-07-03T07:01:23Z","abstract_excerpt":"Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies and choose a good one, which is a much simpler task than precisely evaluating their true performance; and (2) there are usually multiple policies that have been deployed to serve users in real-world systems and thus the true performance of these policies can be known. Inspired by the two observations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01360","kind":"arxiv","version":2},"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/2107.01360/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":"2107.01360","created_at":"2026-07-05T04:32:50.418841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01360v2","created_at":"2026-07-05T04:32:50.418841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01360","created_at":"2026-07-05T04:32:50.418841+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLKZVF36ACKC","created_at":"2026-07-05T04:32:50.418841+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLKZVF36ACKCEFCP","created_at":"2026-07-05T04:32:50.418841+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLKZVF36","created_at":"2026-07-05T04:32:50.418841+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/XLKZVF36ACKCEFCPVCRDQR4O3Y","json":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y.json","graph_json":"https://pith.science/api/pith-number/XLKZVF36ACKCEFCPVCRDQR4O3Y/graph.json","events_json":"https://pith.science/api/pith-number/XLKZVF36ACKCEFCPVCRDQR4O3Y/events.json","paper":"https://pith.science/paper/XLKZVF36"},"agent_actions":{"view_html":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y","download_json":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y.json","view_paper":"https://pith.science/paper/XLKZVF36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01360&json=true","fetch_graph":"https://pith.science/api/pith-number/XLKZVF36ACKCEFCPVCRDQR4O3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/XLKZVF36ACKCEFCPVCRDQR4O3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/action/storage_attestation","attest_author":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/action/author_attestation","sign_citation":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/action/citation_signature","submit_replication":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/action/replication_record"}},"created_at":"2026-07-05T04:32:50.418841+00:00","updated_at":"2026-07-05T04:32:50.418841+00:00"}