{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LR5NN2W2SU7O57LJT5HJLIMXV3","short_pith_number":"pith:LR5NN2W2","canonical_record":{"source":{"id":"2305.17083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T16:48:05Z","cross_cats_sorted":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"title_canon_sha256":"92866e1bfd42b2f93406467122a09b40da7b9fad33a4dda4b0f7eb5ac5a617ae","abstract_canon_sha256":"d84a06ae0777deb7c93beeea3cf542aebbf55b4d72d2a5f83d90ddc359cbd238"},"schema_version":"1.0"},"canonical_sha256":"5c7ad6eada953eeefd699f4e95a197aed9563fdd41901618d0611db28c795d41","source":{"kind":"arxiv","id":"2305.17083","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17083","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17083v2","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17083","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"LR5NN2W2SU7O","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"LR5NN2W2SU7O57LJ","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"LR5NN2W2","created_at":"2026-07-05T07:18:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LR5NN2W2SU7O57LJT5HJLIMXV3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T16:48:05Z","cross_cats_sorted":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"title_canon_sha256":"92866e1bfd42b2f93406467122a09b40da7b9fad33a4dda4b0f7eb5ac5a617ae","abstract_canon_sha256":"d84a06ae0777deb7c93beeea3cf542aebbf55b4d72d2a5f83d90ddc359cbd238"},"schema_version":"1.0"},"canonical_sha256":"5c7ad6eada953eeefd699f4e95a197aed9563fdd41901618d0611db28c795d41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:58.050699Z","signature_b64":"rUns8wAXa6NbUSi1olqsVqYq8fqz1AoCleC3OqvhGRK4qC64aC4DHljY1DlbgD8/fr7HxyEhJ8sPS4rUI7bCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7ad6eada953eeefd699f4e95a197aed9563fdd41901618d0611db28c795d41","last_reissued_at":"2026-07-05T07:18:58.050176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:58.050176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17083","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7403ItWTB85NZDPMX0hA07D3fCdp73IFk0YzFczm0UWKfcbvqCJ5ubmvj464v9aV86YMzcRpjoNt7vYB8VeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:10:49.778575Z"},"content_sha256":"d9cbb80d1409ed5edd1af05271dac4505796fe5b7afbf49350196ed7b5f01457","schema_version":"1.0","event_id":"sha256:d9cbb80d1409ed5edd1af05271dac4505796fe5b7afbf49350196ed7b5f01457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LR5NN2W2SU7O57LJT5HJLIMXV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Policy Gradient Method for Confounded POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Mao Hong, Yanxun Xu, Zhengling Qi","submitted_at":"2023-05-26T16:48:05Z","abstract_excerpt":"In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result to non-parametrically estimate any history-dependent policy gradient under POMDPs using the offline data. The identification enables us to solve a sequence of conditional moment restrictions and adopt the min-max learning procedure with general function approximation for estimating the policy gradient. We then provide a finite-sample non-asymptotic bound for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17083","kind":"arxiv","version":2},"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/2305.17083/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":"2026-07-05T07:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vm4nrcnBBGr+tgPhmPY1gcK3a0u6lfciMwEKq5tYsg2PRho9mcZ5urPEK2CjIDpB7TPSXNZ/h2WQC1Zeu4IHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:10:49.783270Z"},"content_sha256":"23f45d8c3f79d94e0d206ca11521fe86422f7b327c7122f732a106fc67564410","schema_version":"1.0","event_id":"sha256:23f45d8c3f79d94e0d206ca11521fe86422f7b327c7122f732a106fc67564410"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/bundle.json","state_url":"https://pith.science/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/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":"2026-08-13T07:10:49Z","links":{"resolver":"https://pith.science/pith/LR5NN2W2SU7O57LJT5HJLIMXV3","bundle":"https://pith.science/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/bundle.json","state":"https://pith.science/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LR5NN2W2SU7O57LJT5HJLIMXV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LR5NN2W2SU7O57LJT5HJLIMXV3","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":"d84a06ae0777deb7c93beeea3cf542aebbf55b4d72d2a5f83d90ddc359cbd238","cross_cats_sorted":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T16:48:05Z","title_canon_sha256":"92866e1bfd42b2f93406467122a09b40da7b9fad33a4dda4b0f7eb5ac5a617ae"},"schema_version":"1.0","source":{"id":"2305.17083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17083","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17083v2","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17083","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"LR5NN2W2SU7O","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"LR5NN2W2SU7O57LJ","created_at":"2026-07-05T07:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"LR5NN2W2","created_at":"2026-07-05T07:18:58Z"}],"graph_snapshots":[{"event_id":"sha256:23f45d8c3f79d94e0d206ca11521fe86422f7b327c7122f732a106fc67564410","target":"graph","created_at":"2026-07-05T07:18:58Z","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/2305.17083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result to non-parametrically estimate any history-dependent policy gradient under POMDPs using the offline data. The identification enables us to solve a sequence of conditional moment restrictions and adopt the min-max learning procedure with general function approximation for estimating the policy gradient. We then provide a finite-sample non-asymptotic bound for","authors_text":"Mao Hong, Yanxun Xu, Zhengling Qi","cross_cats":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T16:48:05Z","title":"A Policy Gradient Method for Confounded POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17083","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:d9cbb80d1409ed5edd1af05271dac4505796fe5b7afbf49350196ed7b5f01457","target":"record","created_at":"2026-07-05T07:18:58Z","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":"d84a06ae0777deb7c93beeea3cf542aebbf55b4d72d2a5f83d90ddc359cbd238","cross_cats_sorted":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-26T16:48:05Z","title_canon_sha256":"92866e1bfd42b2f93406467122a09b40da7b9fad33a4dda4b0f7eb5ac5a617ae"},"schema_version":"1.0","source":{"id":"2305.17083","kind":"arxiv","version":2}},"canonical_sha256":"5c7ad6eada953eeefd699f4e95a197aed9563fdd41901618d0611db28c795d41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7ad6eada953eeefd699f4e95a197aed9563fdd41901618d0611db28c795d41","first_computed_at":"2026-07-05T07:18:58.050176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:58.050176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rUns8wAXa6NbUSi1olqsVqYq8fqz1AoCleC3OqvhGRK4qC64aC4DHljY1DlbgD8/fr7HxyEhJ8sPS4rUI7bCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:58.050699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9cbb80d1409ed5edd1af05271dac4505796fe5b7afbf49350196ed7b5f01457","sha256:23f45d8c3f79d94e0d206ca11521fe86422f7b327c7122f732a106fc67564410"],"state_sha256":"ae53f3cdea3705cbe04c7c7b709f318ea68fe7ab4a0732e480d01c3fcc779b23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRWNQE5+JGmsWSti5uj0GzsYjlflwuw1RZuaZxyqAply3vl8/Vy6uLkUK0eOMguvF5AqMe2msM8gXkBh1HhoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:10:49.806044Z","bundle_sha256":"c38e2570dfea5d898497e619d490e7cf24cd395279856ff0c97bc3d59d8cbd15"}}