{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y52BOKYWSJ3MMA3B3ZFNJK6PTQ","short_pith_number":"pith:Y52BOKYW","canonical_record":{"source":{"id":"2307.02884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T09:39:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b0adbc795479b948d317834ef5404d6e1289903e0ba5b31ffed234e4ee14944a","abstract_canon_sha256":"9ca1ce30e8fd8ae2f37310f1f9a7056741129dd99a1d47754186478b03e579b2"},"schema_version":"1.0"},"canonical_sha256":"c774172b169276c60361de4ad4abcf9c21221dfc3217c52763b2dad7246349a4","source":{"kind":"arxiv","id":"2307.02884","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02884","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02884v1","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02884","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y52BOKYWSJ3M","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y52BOKYWSJ3MMA3B","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y52BOKYW","created_at":"2026-07-05T06:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y52BOKYWSJ3MMA3B3ZFNJK6PTQ","target":"record","payload":{"canonical_record":{"source":{"id":"2307.02884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T09:39:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b0adbc795479b948d317834ef5404d6e1289903e0ba5b31ffed234e4ee14944a","abstract_canon_sha256":"9ca1ce30e8fd8ae2f37310f1f9a7056741129dd99a1d47754186478b03e579b2"},"schema_version":"1.0"},"canonical_sha256":"c774172b169276c60361de4ad4abcf9c21221dfc3217c52763b2dad7246349a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:25.490764Z","signature_b64":"kt0hewXZglXMX6npdrH5FchaQo6jzxCWjcEu+YnOQAMBu92CKuI8/NI0/L9K4cpATL1co9Vd9ssbRxANZ6+vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c774172b169276c60361de4ad4abcf9c21221dfc3217c52763b2dad7246349a4","last_reissued_at":"2026-07-05T06:28:25.490364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:25.490364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.02884","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":"2026-07-05T06:28:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7r9cLf7Iy8RD5yzpwk+YRfz9B50uYZTfxrXA/nAHJZjJ2UhPFBg2phuatarDsLLD7iz954McVZTKOWVDQ4ruAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:41:49.619943Z"},"content_sha256":"efb4cae787504e1e587ccb7a3c07a878a88c4e8da55ab2020fd35288039d71f4","schema_version":"1.0","event_id":"sha256:efb4cae787504e1e587ccb7a3c07a878a88c4e8da55ab2020fd35288039d71f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y52BOKYWSJ3MMA3B3ZFNJK6PTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Huan Wang, Jiacheng Guo, Mengdi Wang, Minshuo Chen, Yu Bai","submitted_at":"2023-07-06T09:39:01Z","abstract_excerpt":"This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by real-world settings such as loading in game playing, we propose an enhanced feedback model called ``multiple observations in hindsight'', where after each episode of interaction with the POMDP, the learner may collect multiple additional observations emitted from the encountered latent states, but may not observe the latent states themselves. We show that sample-eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02884","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/2307.02884/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":"2026-07-05T06:28:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6WQJ59BkCFkTyfjZ4xSF0Y/Dnd2KuMtq3D6QIZh+m/5z5B5d+CwN81CFDA6TwecUhMdtURLbwlv6vUDhbXTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:41:49.620484Z"},"content_sha256":"7bacb89a8e1ace34963ca3114b42a673d132fee156e49ad7624557349560930a","schema_version":"1.0","event_id":"sha256:7bacb89a8e1ace34963ca3114b42a673d132fee156e49ad7624557349560930a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/bundle.json","state_url":"https://pith.science/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/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":"2026-08-07T12:41:49Z","links":{"resolver":"https://pith.science/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ","bundle":"https://pith.science/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/bundle.json","state":"https://pith.science/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y52BOKYWSJ3MMA3B3ZFNJK6PTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y52BOKYWSJ3MMA3B3ZFNJK6PTQ","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":"9ca1ce30e8fd8ae2f37310f1f9a7056741129dd99a1d47754186478b03e579b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T09:39:01Z","title_canon_sha256":"b0adbc795479b948d317834ef5404d6e1289903e0ba5b31ffed234e4ee14944a"},"schema_version":"1.0","source":{"id":"2307.02884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02884","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02884v1","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02884","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y52BOKYWSJ3M","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y52BOKYWSJ3MMA3B","created_at":"2026-07-05T06:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y52BOKYW","created_at":"2026-07-05T06:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:7bacb89a8e1ace34963ca3114b42a673d132fee156e49ad7624557349560930a","target":"graph","created_at":"2026-07-05T06:28:25Z","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/2307.02884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by real-world settings such as loading in game playing, we propose an enhanced feedback model called ``multiple observations in hindsight'', where after each episode of interaction with the POMDP, the learner may collect multiple additional observations emitted from the encountered latent states, but may not observe the latent states themselves. We show that sample-eff","authors_text":"Caiming Xiong, Huan Wang, Jiacheng Guo, Mengdi Wang, Minshuo Chen, Yu Bai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T09:39:01Z","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02884","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:efb4cae787504e1e587ccb7a3c07a878a88c4e8da55ab2020fd35288039d71f4","target":"record","created_at":"2026-07-05T06:28:25Z","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":"9ca1ce30e8fd8ae2f37310f1f9a7056741129dd99a1d47754186478b03e579b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T09:39:01Z","title_canon_sha256":"b0adbc795479b948d317834ef5404d6e1289903e0ba5b31ffed234e4ee14944a"},"schema_version":"1.0","source":{"id":"2307.02884","kind":"arxiv","version":1}},"canonical_sha256":"c774172b169276c60361de4ad4abcf9c21221dfc3217c52763b2dad7246349a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c774172b169276c60361de4ad4abcf9c21221dfc3217c52763b2dad7246349a4","first_computed_at":"2026-07-05T06:28:25.490364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:25.490364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kt0hewXZglXMX6npdrH5FchaQo6jzxCWjcEu+YnOQAMBu92CKuI8/NI0/L9K4cpATL1co9Vd9ssbRxANZ6+vDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:25.490764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efb4cae787504e1e587ccb7a3c07a878a88c4e8da55ab2020fd35288039d71f4","sha256:7bacb89a8e1ace34963ca3114b42a673d132fee156e49ad7624557349560930a"],"state_sha256":"267cca108d5d9927cf4f1eb5397232a222da84db3082c1372bd1967c76cd8246"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WWMSOMBdeIChAiTnuvQKs3cDH5UbFFhy0cRfVEevfRuDSe9AXmiTtspscjUou6QTtIXDlK/cYOGHfKwoFMgOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:41:49.626172Z","bundle_sha256":"1f19563a8808d2ccdf5baf1b4c8eb54b67f75d65b1c18ea39036d3a968fecbc3"}}