{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:S6SZMDUTPIBCJTVAJR6OVUK62P","short_pith_number":"pith:S6SZMDUT","canonical_record":{"source":{"id":"2203.01889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-03T18:08:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f4daf4d2cfb17405d2fea77619dfb3a73a4bf65140ce8efda5952c9bab6d607","abstract_canon_sha256":"b831c74818277b70388eee1f3bae9699d06a822dc4d39d31ef34df3038e7b157"},"schema_version":"1.0"},"canonical_sha256":"97a5960e937a0224cea04c7cead15ed3eda37ef8e3daf8c2a0e94ac498b3d88f","source":{"kind":"arxiv","id":"2203.01889","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01889","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01889v1","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01889","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"S6SZMDUTPIBC","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"S6SZMDUTPIBCJTVA","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"S6SZMDUT","created_at":"2026-07-05T07:16:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:S6SZMDUTPIBCJTVAJR6OVUK62P","target":"record","payload":{"canonical_record":{"source":{"id":"2203.01889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-03T18:08:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f4daf4d2cfb17405d2fea77619dfb3a73a4bf65140ce8efda5952c9bab6d607","abstract_canon_sha256":"b831c74818277b70388eee1f3bae9699d06a822dc4d39d31ef34df3038e7b157"},"schema_version":"1.0"},"canonical_sha256":"97a5960e937a0224cea04c7cead15ed3eda37ef8e3daf8c2a0e94ac498b3d88f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:31.384798Z","signature_b64":"K/gHJeXlKU5rMXrSYcqpq1ksPcjlCRK/NF73kCL+TBYkPRQtFxk52m/s2t+9zL1/ZlrEykiL6MX6f7SeKfNlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a5960e937a0224cea04c7cead15ed3eda37ef8e3daf8c2a0e94ac498b3d88f","last_reissued_at":"2026-07-05T07:16:31.384364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:31.384364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.01889","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":"2026-07-05T07:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"heXgCABkxjaHb4imMEOmz9hUB33P4QQEHfL4ke7e+JlbhZBc95BMpQgL8nDZAFELtAJ2+wcojiKhXgq5CA08Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:59:02.753192Z"},"content_sha256":"ec9dcbf3ad3d3ec973530462eeee08019b347f9a2d6fde382cf1dbed5c58e0a0","schema_version":"1.0","event_id":"sha256:ec9dcbf3ad3d3ec973530462eeee08019b347f9a2d6fde382cf1dbed5c58e0a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:S6SZMDUTPIBCJTVAJR6OVUK62P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum Reinforcement Learning via Policy Iteration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Anupam Prakash, El Amine Cherrat, Iordanis Kerenidis","submitted_at":"2022-03-03T18:08:17Z","abstract_excerpt":"Quantum computing has shown the potential to substantially speed up machine learning applications, in particular for supervised and unsupervised learning. Reinforcement learning, on the other hand, has become essential for solving many decision making problems and policy iteration methods remain the foundation of such approaches. In this paper, we provide a general framework for performing quantum reinforcement learning via policy iteration. We validate our framework by designing and analyzing: \\emph{quantum policy evaluation} methods for infinite horizon discounted problems by building quantu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01889","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/2203.01889/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":"2026-07-05T07:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4n6z9kCIC/T6eEVZkTf8uQvoVfN9v65UXguKfACC0+8FJ8QwAXJq7LohpujSltbxBskxhsf7DmXmn9ozDT8HCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:59:02.753835Z"},"content_sha256":"28066fc82dd5ea4db7d57c099541cdd544665d09caa0538cef5b1bb22bc5d6fa","schema_version":"1.0","event_id":"sha256:28066fc82dd5ea4db7d57c099541cdd544665d09caa0538cef5b1bb22bc5d6fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/bundle.json","state_url":"https://pith.science/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/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":"2026-07-05T15:59:02Z","links":{"resolver":"https://pith.science/pith/S6SZMDUTPIBCJTVAJR6OVUK62P","bundle":"https://pith.science/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/bundle.json","state":"https://pith.science/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6SZMDUTPIBCJTVAJR6OVUK62P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S6SZMDUTPIBCJTVAJR6OVUK62P","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":"b831c74818277b70388eee1f3bae9699d06a822dc4d39d31ef34df3038e7b157","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-03T18:08:17Z","title_canon_sha256":"6f4daf4d2cfb17405d2fea77619dfb3a73a4bf65140ce8efda5952c9bab6d607"},"schema_version":"1.0","source":{"id":"2203.01889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01889","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01889v1","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01889","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"S6SZMDUTPIBC","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"S6SZMDUTPIBCJTVA","created_at":"2026-07-05T07:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"S6SZMDUT","created_at":"2026-07-05T07:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:28066fc82dd5ea4db7d57c099541cdd544665d09caa0538cef5b1bb22bc5d6fa","target":"graph","created_at":"2026-07-05T07:16:31Z","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/2203.01889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantum computing has shown the potential to substantially speed up machine learning applications, in particular for supervised and unsupervised learning. Reinforcement learning, on the other hand, has become essential for solving many decision making problems and policy iteration methods remain the foundation of such approaches. In this paper, we provide a general framework for performing quantum reinforcement learning via policy iteration. We validate our framework by designing and analyzing: \\emph{quantum policy evaluation} methods for infinite horizon discounted problems by building quantu","authors_text":"Anupam Prakash, El Amine Cherrat, Iordanis Kerenidis","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-03T18:08:17Z","title":"Quantum Reinforcement Learning via Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01889","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:ec9dcbf3ad3d3ec973530462eeee08019b347f9a2d6fde382cf1dbed5c58e0a0","target":"record","created_at":"2026-07-05T07:16:31Z","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":"b831c74818277b70388eee1f3bae9699d06a822dc4d39d31ef34df3038e7b157","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-03T18:08:17Z","title_canon_sha256":"6f4daf4d2cfb17405d2fea77619dfb3a73a4bf65140ce8efda5952c9bab6d607"},"schema_version":"1.0","source":{"id":"2203.01889","kind":"arxiv","version":1}},"canonical_sha256":"97a5960e937a0224cea04c7cead15ed3eda37ef8e3daf8c2a0e94ac498b3d88f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a5960e937a0224cea04c7cead15ed3eda37ef8e3daf8c2a0e94ac498b3d88f","first_computed_at":"2026-07-05T07:16:31.384364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:31.384364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/gHJeXlKU5rMXrSYcqpq1ksPcjlCRK/NF73kCL+TBYkPRQtFxk52m/s2t+9zL1/ZlrEykiL6MX6f7SeKfNlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:31.384798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.01889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec9dcbf3ad3d3ec973530462eeee08019b347f9a2d6fde382cf1dbed5c58e0a0","sha256:28066fc82dd5ea4db7d57c099541cdd544665d09caa0538cef5b1bb22bc5d6fa"],"state_sha256":"8ebeba3a7f5f4ca5b290769b096990f3a96499f1c0196eb5a6d7e05d92df1193"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbAwcgGW33y0hvY1cTrHdi7MBzBUxs5R7HMBESsQwUtTTZcuIO0JRVEZ0chRurCGQejL9c2AAysHE9dHgB7LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:59:02.757458Z","bundle_sha256":"9fa0584d1887961772b2066b90510c9269dafe2302bbdd72433a89637a5f90e7"}}