{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XLKZVF36ACKCEFCPVCRDQR4O3Y","short_pith_number":"pith:XLKZVF36","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"},"canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","source":{"kind":"arxiv","id":"2107.01360","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XLKZVF36ACKCEFCPVCRDQR4O3Y","target":"record","payload":{"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"},"canonical_sha256":"bad59a977e009422144fa8a238478ede1ee723578be28fac9d3edbda800b36b4","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"},"source_kind":"arxiv","source_id":"2107.01360","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cau7km0XE+dRuNWrlRhu7MHNiVYP6ZI/N5tZGa8JZBMe4RF1S+dSgScUPdOIVAQ7sAvUda8LBAsQLcT2zPWrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:51:43.809719Z"},"content_sha256":"98d82803fa297576412a6014051114fa95f754a2db86a9dda2febc6c29a40caf","schema_version":"1.0","event_id":"sha256:98d82803fa297576412a6014051114fa95f754a2db86a9dda2febc6c29a40caf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XLKZVF36ACKCEFCPVCRDQR4O3Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7N6LGcd7yOGcvOAEhm7ySzxsQC7z4MNZp8fkErxgGr6DUVWtfnlLD9HtDxJLymbOwDSTpqCLZeEDveCqNUYkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:51:43.810097Z"},"content_sha256":"37552937d0a2d87f8421b2cf5fa6da78a2bb11bc26b25bcd72dd3052ff08d889","schema_version":"1.0","event_id":"sha256:37552937d0a2d87f8421b2cf5fa6da78a2bb11bc26b25bcd72dd3052ff08d889"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/bundle.json","state_url":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/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":"2026-07-26T00:51:43Z","links":{"resolver":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y","bundle":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/bundle.json","state":"https://pith.science/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLKZVF36ACKCEFCPVCRDQR4O3Y/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWermfu3F/7glHyZn6ni7aFX5aB26cWsF3IvpDuXSkRyrkJeKz3PNlPY6q+AfsH+PyU7lhw2hBwS4L/VppI1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T00:51:43.812303Z","bundle_sha256":"ddd0e97a150f26a16264984048253edf46aa1c3be480b0e46e48388c4739bd32"}}