{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BPDYIAW3ROO5ND4KG4DSLAGZER","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":"4c724a7609a686853ea96235a0844844e8c3840ca62fcb034fc46be2c53fd8b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-28T03:32:31Z","title_canon_sha256":"473fecaaec2d909fc864057a6a08843acb45bb89c38eed53e2d39ba0c251c28a"},"schema_version":"1.0","source":{"id":"2607.25241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25241","created_at":"2026-07-29T00:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25241v1","created_at":"2026-07-29T00:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25241","created_at":"2026-07-29T00:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"BPDYIAW3ROO5","created_at":"2026-07-29T00:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"BPDYIAW3ROO5ND4K","created_at":"2026-07-29T00:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"BPDYIAW3","created_at":"2026-07-29T00:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:023072aef7bc2a17a1b7b6c7fda637e587da148418b5b4a42134a42c43bfdcdc","target":"graph","created_at":"2026-07-29T00:25:10Z","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/2607.25241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard offline reinforcement learning (RL) algorithms typically assume that the actions in the dataset are observed without error. However, in many real-world applications, the true actions are unobserved and only noisy proxies are available, causing existing RL methods to yield biased and potentially misleading conclusions. We study off-policy evaluation in infinite-horizon discounted Markov decision processes with hidden actions. By leveraging the next-state variable as a natural proxy for the unobserved action, we establish identification of the policy value and propose an influence-funct","authors_text":"Yifan Cui, Ying Zhou, Zeyu Bian","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-28T03:32:31Z","title":"Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25241","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:f998c246124489dd655391ce6a97fcd137242a8442938552592efa6ae4a13c3d","target":"record","created_at":"2026-07-29T00:25:10Z","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":"4c724a7609a686853ea96235a0844844e8c3840ca62fcb034fc46be2c53fd8b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-28T03:32:31Z","title_canon_sha256":"473fecaaec2d909fc864057a6a08843acb45bb89c38eed53e2d39ba0c251c28a"},"schema_version":"1.0","source":{"id":"2607.25241","kind":"arxiv","version":1}},"canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","first_computed_at":"2026-07-29T00:25:10.336506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:10.336506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+HeCImQIwEg17PmHxZ4avnfgKh7xoZaI37LO0vd453KqaPerpqc9ZWURyAvAt60rKVbZIVOs6RVh988S7K09DQ==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:10.337416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f998c246124489dd655391ce6a97fcd137242a8442938552592efa6ae4a13c3d","sha256:023072aef7bc2a17a1b7b6c7fda637e587da148418b5b4a42134a42c43bfdcdc"],"state_sha256":"377a0d426cf613389226aea7ba3db20fa5b416751766481bdc577846778d8a19"}