{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3BD55P75BZPNKYNF6GJFMXZSOS","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":"d1bd065b0a4a0e3cd72519a503926dd83b07e696a6eb65894d5bc976f23927c6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-26T17:53:29Z","title_canon_sha256":"ffa962c70f7a036c25db66bede114a7a482c7326157052c74897df40d82ee703"},"schema_version":"1.0","source":{"id":"2207.13081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13081","created_at":"2026-07-05T07:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13081v2","created_at":"2026-07-05T07:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13081","created_at":"2026-07-05T07:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"3BD55P75BZPN","created_at":"2026-07-05T07:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"3BD55P75BZPNKYNF","created_at":"2026-07-05T07:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"3BD55P75","created_at":"2026-07-05T07:12:46Z"}],"graph_snapshots":[{"event_id":"sha256:273657170206aefbb0a83e763376383d891d85788bf2c840ca35360869dec4f9","target":"graph","created_at":"2026-07-05T07:12:46Z","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/2207.13081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the curse of horizon in POMDPs. To circumvent this problem, we develop a novel model-free OPE method by introducing future-dependent value functions that take future proxies as inputs. Future-dependent value functions play similar roles as classical value functions in fully-observable MDPs. We derive a new Bellman equation for future-dependent value functions as conditional moment ","authors_text":"Andrew Bennett, Chengchun Shi, Haruka Kiyohara, Masatoshi Uehara, Nan Jiang, Nathan Kallus, Victor Chernozhukov, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-26T17:53:29Z","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13081","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:dfe17a6abf2b6d4be900bc98c9746ebc535a279324e25eca5809d5f71e99b64c","target":"record","created_at":"2026-07-05T07:12:46Z","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":"d1bd065b0a4a0e3cd72519a503926dd83b07e696a6eb65894d5bc976f23927c6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-26T17:53:29Z","title_canon_sha256":"ffa962c70f7a036c25db66bede114a7a482c7326157052c74897df40d82ee703"},"schema_version":"1.0","source":{"id":"2207.13081","kind":"arxiv","version":2}},"canonical_sha256":"d847debffd0e5ed561a5f192565f3274bf4048f046c2933e3b8db7d5afbb122a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d847debffd0e5ed561a5f192565f3274bf4048f046c2933e3b8db7d5afbb122a","first_computed_at":"2026-07-05T07:12:46.713813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:46.713813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4OR9UP5LxbjbEez2gUo4Sq1Jancd3IVJpZaOYgoPCgYW5T9qLnTJyKWD1CqI8UIORHq4EmBoTxfMHgaw214CAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:46.714291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfe17a6abf2b6d4be900bc98c9746ebc535a279324e25eca5809d5f71e99b64c","sha256:273657170206aefbb0a83e763376383d891d85788bf2c840ca35360869dec4f9"],"state_sha256":"9403efbbc8a14c082364860dff57431e3fa285327696e2b977fcd62f0b02a601"}