{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BPDYIAW3ROO5ND4KG4DSLAGZER","short_pith_number":"pith:BPDYIAW3","schema_version":"1.0","canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","source":{"kind":"arxiv","id":"2607.25241","version":1},"attestation_state":"computed","paper":{"title":"Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Yifan Cui, Ying Zhou, Zeyu Bian","submitted_at":"2026-07-28T03:32:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.25241","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-28T03:32:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"473fecaaec2d909fc864057a6a08843acb45bb89c38eed53e2d39ba0c251c28a","abstract_canon_sha256":"4c724a7609a686853ea96235a0844844e8c3840ca62fcb034fc46be2c53fd8b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:10.337416Z","signature_b64":"+HeCImQIwEg17PmHxZ4avnfgKh7xoZaI37LO0vd453KqaPerpqc9ZWURyAvAt60rKVbZIVOs6RVh988S7K09DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","last_reissued_at":"2026-07-29T00:25:10.336506Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:10.336506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Yifan Cui, Ying Zhou, Zeyu Bian","submitted_at":"2026-07-28T03:32:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25241","kind":"arxiv","version":1},"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/2607.25241/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.25241","created_at":"2026-07-29T00:25:10.336975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25241v1","created_at":"2026-07-29T00:25:10.336975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25241","created_at":"2026-07-29T00:25:10.336975+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPDYIAW3ROO5","created_at":"2026-07-29T00:25:10.336975+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPDYIAW3ROO5ND4K","created_at":"2026-07-29T00:25:10.336975+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPDYIAW3","created_at":"2026-07-29T00:25:10.336975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER","json":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER.json","graph_json":"https://pith.science/api/pith-number/BPDYIAW3ROO5ND4KG4DSLAGZER/graph.json","events_json":"https://pith.science/api/pith-number/BPDYIAW3ROO5ND4KG4DSLAGZER/events.json","paper":"https://pith.science/paper/BPDYIAW3"},"agent_actions":{"view_html":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER","download_json":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER.json","view_paper":"https://pith.science/paper/BPDYIAW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25241&json=true","fetch_graph":"https://pith.science/api/pith-number/BPDYIAW3ROO5ND4KG4DSLAGZER/graph.json","fetch_events":"https://pith.science/api/pith-number/BPDYIAW3ROO5ND4KG4DSLAGZER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/action/storage_attestation","attest_author":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/action/author_attestation","sign_citation":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/action/citation_signature","submit_replication":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/action/replication_record"}},"created_at":"2026-07-29T00:25:10.336975+00:00","updated_at":"2026-07-29T00:25:10.336975+00:00"}