{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZNIOUYAZJ3TSBMN4R67RYEQRV5","short_pith_number":"pith:ZNIOUYAZ","canonical_record":{"source":{"id":"2205.13589","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T19:13:55Z","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"cfc120b1e53ce8ed59a8147b87e21476100870eb34ac095c3cd8b9196bc3f342","abstract_canon_sha256":"380e714630780a871cc15b47e0a2f7ca42b9f1fe3d248f51a64e0531ec8825be"},"schema_version":"1.0"},"canonical_sha256":"cb50ea60194ee720b1bc8fbf1c1211af43efefcb2cf2f8c7da71d4957c101246","source":{"kind":"arxiv","id":"2205.13589","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13589","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13589v3","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13589","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZNIOUYAZJ3TS","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZNIOUYAZJ3TSBMN4","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZNIOUYAZ","created_at":"2026-07-05T08:02:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZNIOUYAZJ3TSBMN4R67RYEQRV5","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13589","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T19:13:55Z","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"cfc120b1e53ce8ed59a8147b87e21476100870eb34ac095c3cd8b9196bc3f342","abstract_canon_sha256":"380e714630780a871cc15b47e0a2f7ca42b9f1fe3d248f51a64e0531ec8825be"},"schema_version":"1.0"},"canonical_sha256":"cb50ea60194ee720b1bc8fbf1c1211af43efefcb2cf2f8c7da71d4957c101246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:41.153844Z","signature_b64":"1KjWpz6Uv827UqJqXoZFxtjCd7xKJ3MABmfwjmFsBC/V+7Sncm4KWTGJq0nv9kWMvutTc6Z5uZk83oWieZymCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb50ea60194ee720b1bc8fbf1c1211af43efefcb2cf2f8c7da71d4957c101246","last_reissued_at":"2026-07-05T08:02:41.153422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:41.153422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13589","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXf3ngOq81+tWPfqAvafCiZN/G6s96WxSczb/Y+cKDDhFTsj0/NXFBK13o1kwqHYy8W9Q98O82VPypaaQJ4LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:35.256100Z"},"content_sha256":"abb9d2015b4e1c9e5cbb5d5e28b0a04509df839c644b538c42c458c47810c455","schema_version":"1.0","event_id":"sha256:abb9d2015b4e1c9e5cbb5d5e28b0a04509df839c644b538c42c458c47810c455"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZNIOUYAZJ3TSBMN4R67RYEQRV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Miao Lu, Yifei Min, Zhaoran Wang, Zhuoran Yang","submitted_at":"2022-05-26T19:13:55Z","abstract_excerpt":"We study offline reinforcement learning (RL) in partially observable Markov decision processes. In particular, we aim to learn an optimal policy from a dataset collected by a behavior policy which possibly depends on the latent state. Such a dataset is confounded in the sense that the latent state simultaneously affects the action and the observation, which is prohibitive for existing offline RL algorithms. To this end, we propose the \\underline{P}roxy variable \\underline{P}essimistic \\underline{P}olicy \\underline{O}ptimization (\\texttt{P3O}) algorithm, which addresses the confounding bias and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13589","kind":"arxiv","version":3},"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/2205.13589/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":"2026-07-05T08:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMaABgSkWWZU96BzOk0irBHj333XxtyRHUC39N7FNPzsz6EPyzAHrvrv9V4bI+kqa62zQ3Rz30dHRC1F4gf/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:35.256599Z"},"content_sha256":"2e0e91b5f1dba44807e31c1417bca13821b80002cd9e68454eeba7b13704d47e","schema_version":"1.0","event_id":"sha256:2e0e91b5f1dba44807e31c1417bca13821b80002cd9e68454eeba7b13704d47e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/bundle.json","state_url":"https://pith.science/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/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":"2026-08-09T05:16:35Z","links":{"resolver":"https://pith.science/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5","bundle":"https://pith.science/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/bundle.json","state":"https://pith.science/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNIOUYAZJ3TSBMN4R67RYEQRV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZNIOUYAZJ3TSBMN4R67RYEQRV5","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":"380e714630780a871cc15b47e0a2f7ca42b9f1fe3d248f51a64e0531ec8825be","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T19:13:55Z","title_canon_sha256":"cfc120b1e53ce8ed59a8147b87e21476100870eb34ac095c3cd8b9196bc3f342"},"schema_version":"1.0","source":{"id":"2205.13589","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13589","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13589v3","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13589","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZNIOUYAZJ3TS","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZNIOUYAZJ3TSBMN4","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZNIOUYAZ","created_at":"2026-07-05T08:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:2e0e91b5f1dba44807e31c1417bca13821b80002cd9e68454eeba7b13704d47e","target":"graph","created_at":"2026-07-05T08:02:41Z","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/2205.13589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study offline reinforcement learning (RL) in partially observable Markov decision processes. In particular, we aim to learn an optimal policy from a dataset collected by a behavior policy which possibly depends on the latent state. Such a dataset is confounded in the sense that the latent state simultaneously affects the action and the observation, which is prohibitive for existing offline RL algorithms. To this end, we propose the \\underline{P}roxy variable \\underline{P}essimistic \\underline{P}olicy \\underline{O}ptimization (\\texttt{P3O}) algorithm, which addresses the confounding bias and","authors_text":"Miao Lu, Yifei Min, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T19:13:55Z","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13589","kind":"arxiv","version":3},"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:abb9d2015b4e1c9e5cbb5d5e28b0a04509df839c644b538c42c458c47810c455","target":"record","created_at":"2026-07-05T08:02:41Z","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":"380e714630780a871cc15b47e0a2f7ca42b9f1fe3d248f51a64e0531ec8825be","cross_cats_sorted":["cs.AI","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T19:13:55Z","title_canon_sha256":"cfc120b1e53ce8ed59a8147b87e21476100870eb34ac095c3cd8b9196bc3f342"},"schema_version":"1.0","source":{"id":"2205.13589","kind":"arxiv","version":3}},"canonical_sha256":"cb50ea60194ee720b1bc8fbf1c1211af43efefcb2cf2f8c7da71d4957c101246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb50ea60194ee720b1bc8fbf1c1211af43efefcb2cf2f8c7da71d4957c101246","first_computed_at":"2026-07-05T08:02:41.153422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:41.153422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1KjWpz6Uv827UqJqXoZFxtjCd7xKJ3MABmfwjmFsBC/V+7Sncm4KWTGJq0nv9kWMvutTc6Z5uZk83oWieZymCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:41.153844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13589","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abb9d2015b4e1c9e5cbb5d5e28b0a04509df839c644b538c42c458c47810c455","sha256:2e0e91b5f1dba44807e31c1417bca13821b80002cd9e68454eeba7b13704d47e"],"state_sha256":"e8163361fc1ab9d4a2ad1442bce9d145e4661aadf3b5468b86d350762760bb8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TBbuJuI0NoD1eE5b5qEu9GsWcjVnLkTRdRmSaOmpJdo9o2USqR+RNeT+kQKRgkLfaDgS34NszxZJ/OQXUP/IAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:16:35.260323Z","bundle_sha256":"5c32ecd0003f6985a5aa2da1774d458a82095997b29006f5d825c3171f04d5d0"}}