{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XLKZVF36ACKCEFCPVCRDQR4O3Y","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":"4b6e6054432e18e0a2b011fc0232c7cab88e34a94935c3865996c28cdb8eeddf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T07:01:23Z","title_canon_sha256":"d10439e8118bec8d305fe66a6bc73b74325a3d2da9a74f93ed7c54eff1706241"},"schema_version":"1.0","source":{"id":"2107.01360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01360","created_at":"2026-07-05T04:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01360v2","created_at":"2026-07-05T04:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01360","created_at":"2026-07-05T04:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"XLKZVF36ACKC","created_at":"2026-07-05T04:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"XLKZVF36ACKCEFCP","created_at":"2026-07-05T04:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"XLKZVF36","created_at":"2026-07-05T04:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:37552937d0a2d87f8421b2cf5fa6da78a2bb11bc26b25bcd72dd3052ff08d889","target":"graph","created_at":"2026-07-05T04:32:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.01360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Houqiang Li, Jian Yuan, Tao Qin, Tie-Yan Liu, Xudong Zhang, Yue Jin, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T07:01:23Z","title":"Supervised Off-Policy Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01360","kind":"arxiv","version":2},"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":"sha256:98d82803fa297576412a6014051114fa95f754a2db86a9dda2febc6c29a40caf","target":"record","created_at":"2026-07-05T04:32:50Z","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":"4b6e6054432e18e0a2b011fc0232c7cab88e34a94935c3865996c28cdb8eeddf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T07:01:23Z","title_canon_sha256":"d10439e8118bec8d305fe66a6bc73b74325a3d2da9a74f93ed7c54eff1706241"},"schema_version":"1.0","source":{"id":"2107.01360","kind":"arxiv","version":2}},"canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","first_computed_at":"2026-07-05T04:32:50.418779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:50.418779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SUkXtTiXt8RRohu1ezZw7uqaYJTAT7YKVBh7oFjJoMm93fuhoaFkUU28zi91picjoZ4GoyYBpFDLm87tWdXUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:50.419359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98d82803fa297576412a6014051114fa95f754a2db86a9dda2febc6c29a40caf","sha256:37552937d0a2d87f8421b2cf5fa6da78a2bb11bc26b25bcd72dd3052ff08d889"],"state_sha256":"a6c7d7b36b4b77469a797ad025b13427938989801170d4f89bf7b52c49211872"}