{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BPDYIAW3ROO5ND4KG4DSLAGZER","short_pith_number":"pith:BPDYIAW3","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"},"canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","source":{"kind":"arxiv","id":"2607.25241","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BPDYIAW3ROO5ND4KG4DSLAGZER","target":"record","payload":{"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"},"canonical_sha256":"0bc78402db8b9dd68f8a37072580d9247aff05ee16979b933f898de70aaef1c1","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"},"source_kind":"arxiv","source_id":"2607.25241","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcFBMjA5mFWBcdUQ7vE4go2SKXhRd5OfB/XNRp4FsePp0n6KKrH43oSBmKlM3sFxmrB3IgZIhy6iaE9AHrykBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:25.703597Z"},"content_sha256":"f998c246124489dd655391ce6a97fcd137242a8442938552592efa6ae4a13c3d","schema_version":"1.0","event_id":"sha256:f998c246124489dd655391ce6a97fcd137242a8442938552592efa6ae4a13c3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BPDYIAW3ROO5ND4KG4DSLAGZER","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zwjbVU/yxX0gb63Y7jIRCS/SIrkGgB6GWLm6OosNgExohYW8SeVSu8g6OSqFbxxEBJ6oAXCngbPDfgHHO4tAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:25.704162Z"},"content_sha256":"023072aef7bc2a17a1b7b6c7fda637e587da148418b5b4a42134a42c43bfdcdc","schema_version":"1.0","event_id":"sha256:023072aef7bc2a17a1b7b6c7fda637e587da148418b5b4a42134a42c43bfdcdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/bundle.json","state_url":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:42:25Z","links":{"resolver":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER","bundle":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/bundle.json","state":"https://pith.science/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPDYIAW3ROO5ND4KG4DSLAGZER/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6J1ey6K2CHDh/8hKIp900k7wUKtZD2DjjZexTkPDkB6XAaKU2/or3PElnPHTaxTkvCKfC8uov9uswQWQR8IoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:42:25.707668Z","bundle_sha256":"1d55ba8b776a5f41b8f63a0bac8dff6e62a11ebbbbb897fd3444326457beee97"}}