{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VVLV4ENBNPE3W5RY25GOCY2MEC","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":"bb0aa343563e8ffea77ba04f27264716214dae350de7812f1e13b1cd2d9d53ce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T12:39:11Z","title_canon_sha256":"4de991690190c2e41dc40b2464d4a6d7f6e4305c8c50c73240309657515d4b86"},"schema_version":"1.0","source":{"id":"2010.11652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11652","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11652v1","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11652","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"VVLV4ENBNPE3","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"VVLV4ENBNPE3W5RY","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"VVLV4ENB","created_at":"2026-07-05T01:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:e705bd5092416b4b8ed05ec90acf3416f952dbb726462dd19cf0ffe4d0b98c53","target":"graph","created_at":"2026-07-05T01:45:12Z","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/2010.11652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given only access to a static experience dataset collected by unknown behavior policies. Starting from a function space embedding of the linear program formulation of the $Q$-function, we obtain an optimization problem with generalized estimating equation constraints. By applying the generalized empirical likelihood method to the resulting Lagrangian, we propose CoinDICE, a novel and efficient algorithm for computing confide","authors_text":"Bo Dai, Csaba Szepesv\\'ari, Dale Schuurmans, Lihong Li, Ofir Nachum, Yinlam Chow","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T12:39:11Z","title":"CoinDICE: Off-Policy Confidence Interval Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11652","kind":"arxiv","version":1},"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:d9593817e6e8e22bc77bdb11bca622e57b367ad918e4bdc93a488b089b365897","target":"record","created_at":"2026-07-05T01:45:12Z","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":"bb0aa343563e8ffea77ba04f27264716214dae350de7812f1e13b1cd2d9d53ce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T12:39:11Z","title_canon_sha256":"4de991690190c2e41dc40b2464d4a6d7f6e4305c8c50c73240309657515d4b86"},"schema_version":"1.0","source":{"id":"2010.11652","kind":"arxiv","version":1}},"canonical_sha256":"ad575e11a16bc9bb7638d74ce1634c20ad367e798c8a1ef6332a7cea2a29967c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad575e11a16bc9bb7638d74ce1634c20ad367e798c8a1ef6332a7cea2a29967c","first_computed_at":"2026-07-05T01:45:12.219949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:12.219949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FfyCTNG/h7PZVBdDqoQUgmXCy+NK+I/wiJgDeCz62uU5UOaW4xPgvo1nxTwaBz6V2/J4pHB/jUzurmWtkXvvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:12.220280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9593817e6e8e22bc77bdb11bca622e57b367ad918e4bdc93a488b089b365897","sha256:e705bd5092416b4b8ed05ec90acf3416f952dbb726462dd19cf0ffe4d0b98c53"],"state_sha256":"25e7adac9bd830dc16f842e3d663d5b790f38d097c99e2643d522f72e0814733"}