{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2FPERGVIHDHH4ENK6IOOOMFZFO","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":"85b7f8b0fadc1fdf494e95e1854e9c5a498dd5352214c7b1bad1769afa8afa75","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T15:52:24Z","title_canon_sha256":"c7d4ec291080427e0e6e1dfbfd8fb2a9ab4490dfcc7ebc301d19981eee91b88c"},"schema_version":"1.0","source":{"id":"2111.06784","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.06784","created_at":"2026-07-05T04:32:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.06784v4","created_at":"2026-07-05T04:32:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06784","created_at":"2026-07-05T04:32:12Z"},{"alias_kind":"pith_short_12","alias_value":"2FPERGVIHDHH","created_at":"2026-07-05T04:32:12Z"},{"alias_kind":"pith_short_16","alias_value":"2FPERGVIHDHH4ENK","created_at":"2026-07-05T04:32:12Z"},{"alias_kind":"pith_short_8","alias_value":"2FPERGVI","created_at":"2026-07-05T04:32:12Z"}],"graph_snapshots":[{"event_id":"sha256:20965e9f55cdfdde4c97be62068f846ca17f14337e6694d180be303616d20843","target":"graph","created_at":"2026-07-05T04:32:12Z","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/2111.06784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent variables. Existing works either assume no unmeasured confounders, or focus on settings where both the observation and the state spaces are tabular. In this work, we first propose novel identification methods for OPE in POMDPs with latent confounders, by introducing bridge functions that link the target policy's value and the observed data distribution. We next propose minimax ","authors_text":"Chengchun Shi, Jiawei Huang, Masatoshi Uehara, Nan Jiang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T15:52:24Z","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06784","kind":"arxiv","version":4},"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":"sha256:7b86acfcbc4a40d81ad6ef76603f9a3d26ababf719416b916293d7b0a3150c9f","target":"record","created_at":"2026-07-05T04:32:12Z","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":"85b7f8b0fadc1fdf494e95e1854e9c5a498dd5352214c7b1bad1769afa8afa75","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T15:52:24Z","title_canon_sha256":"c7d4ec291080427e0e6e1dfbfd8fb2a9ab4490dfcc7ebc301d19981eee91b88c"},"schema_version":"1.0","source":{"id":"2111.06784","kind":"arxiv","version":4}},"canonical_sha256":"d15e489aa838ce7e11aaf21ce730b92ba2f74ceaa8bd959d8d480b20c8965578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d15e489aa838ce7e11aaf21ce730b92ba2f74ceaa8bd959d8d480b20c8965578","first_computed_at":"2026-07-05T04:32:12.723170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:12.723170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8U3kbyM2n4Dsb+gIy92Hxc9epJwOkJWjDVFeM3zEO9vjKRkvSlJ0iJFNI5jtDmai1IJbcKO5pJ+ZMS/x4/FOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:12.723657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.06784","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b86acfcbc4a40d81ad6ef76603f9a3d26ababf719416b916293d7b0a3150c9f","sha256:20965e9f55cdfdde4c97be62068f846ca17f14337e6694d180be303616d20843"],"state_sha256":"b7116b9d5155a2424bdcb4a5d54866d42809e1c9fec5bd923b52992019d9ec4d"}