{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RW7LLCLWJ5P6LFHROOX53QQZ55","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":"ced6dd3a539aaa320bcd6990b7d52ae8a6d92d54dc8370a4c52c0fa332cea4e5","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2026-08-03T19:38:31Z","title_canon_sha256":"6b363f7e5a778790383b74b8665462347eb60420837ecfad35f89805fa160a62"},"schema_version":"1.0","source":{"id":"2608.02826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02826","created_at":"2026-08-05T00:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02826v1","created_at":"2026-08-05T00:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02826","created_at":"2026-08-05T00:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"RW7LLCLWJ5P6","created_at":"2026-08-05T00:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"RW7LLCLWJ5P6LFHR","created_at":"2026-08-05T00:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"RW7LLCLW","created_at":"2026-08-05T00:42:58Z"}],"graph_snapshots":[{"event_id":"sha256:69f399e92cf7a32348249b5476fccf4de16dcec41dda61499cfe930837d05cc9","target":"graph","created_at":"2026-08-05T00:42:58Z","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/2608.02826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is a subfield of machine learning that studies how an agent interacts with an environment in order to extract as large a reward as possible. A standard approach to study such interaction is through Markov Decision Processes (MDPs) and the task of choosing an optimal policy --- a function that tells the agent which action to take. In this work, we study two types of MDPs --- finite-horizon and infinite-horizon discounted --- and propose new quantum algorithms for computing approximate optimal policies. Our quantum algorithms are based on a new combination of standard valu","authors_text":"Joao F. Doriguello","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2026-08-03T19:38:31Z","title":"Improved Quantum Algorithms for Reinforcement Learning Under a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02826","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:f1ac39a7f79f8821bbaf6ccacc8ecb2878f06b3cd0778b05b2bdfd7423d6b6cd","target":"record","created_at":"2026-08-05T00:42:58Z","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":"ced6dd3a539aaa320bcd6990b7d52ae8a6d92d54dc8370a4c52c0fa332cea4e5","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2026-08-03T19:38:31Z","title_canon_sha256":"6b363f7e5a778790383b74b8665462347eb60420837ecfad35f89805fa160a62"},"schema_version":"1.0","source":{"id":"2608.02826","kind":"arxiv","version":1}},"canonical_sha256":"8dbeb589764f5fe594f173afddc219ef6b66a70da252cd9f5e59d6dc2d7f2e35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dbeb589764f5fe594f173afddc219ef6b66a70da252cd9f5e59d6dc2d7f2e35","first_computed_at":"2026-08-05T00:42:58.863858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:42:58.863858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JXCcSlxAy7wR/Q+Gc+SHSjbHrIW64ZJU0mdpusiZ/mD7F5so34i8XBvTuQMb9Oc+Qo7QU7jheNgLVIoo5B3mDQ==","signature_status":"signed_v1","signed_at":"2026-08-05T00:42:58.866465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1ac39a7f79f8821bbaf6ccacc8ecb2878f06b3cd0778b05b2bdfd7423d6b6cd","sha256:69f399e92cf7a32348249b5476fccf4de16dcec41dda61499cfe930837d05cc9"],"state_sha256":"5491613b8f0fa827dfe97bb8370915ba048d5680eab3e3cacc193fea1a9ac5d2"}