{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7EOA7FH52HPBQYLP56BANBVV6I","short_pith_number":"pith:7EOA7FH5","canonical_record":{"source":{"id":"2206.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-06-09T19:23:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"370af5602732ab887a2db74ba9785083bac479e65fecc7a09468e06ab0719f05","abstract_canon_sha256":"a619bae31c6e844a340e41cd48d359209949ba9e768915c9806adc76b0e6e35f"},"schema_version":"1.0"},"canonical_sha256":"f91c0f94fdd1de18616fef820686b5f235685c3d8d1ddb0c2ae7effba965e6bc","source":{"kind":"arxiv","id":"2206.04741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04741","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04741v2","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04741","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"7EOA7FH52HPB","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"7EOA7FH52HPBQYLP","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"7EOA7FH5","created_at":"2026-07-05T07:11:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7EOA7FH52HPBQYLP56BANBVV6I","target":"record","payload":{"canonical_record":{"source":{"id":"2206.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-06-09T19:23:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"370af5602732ab887a2db74ba9785083bac479e65fecc7a09468e06ab0719f05","abstract_canon_sha256":"a619bae31c6e844a340e41cd48d359209949ba9e768915c9806adc76b0e6e35f"},"schema_version":"1.0"},"canonical_sha256":"f91c0f94fdd1de18616fef820686b5f235685c3d8d1ddb0c2ae7effba965e6bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:04.262746Z","signature_b64":"unAmhInIfIfx3QT3V6GBrvYl12AhXXZ6muhWikEF8eMGcrVYVKzGZ3oAM3CjN5P8wcUJnu/BWWeAcUxvLpF9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f91c0f94fdd1de18616fef820686b5f235685c3d8d1ddb0c2ae7effba965e6bc","last_reissued_at":"2026-07-05T07:11:04.262004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:04.262004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.04741","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":"2026-07-05T07:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMmtt13HpNlts/o5lyu4/YqczuCVmXDYy8Nm+GJFTmaXbnvy8bRBtPBXW6tchDTSqbKbm+snCYQ6dxqPjs7NBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T16:35:56.473696Z"},"content_sha256":"f26e676332d661d839b3df86c72951417f58ce93615c400ce7ebc12d72ef13f7","schema_version":"1.0","event_id":"sha256:f26e676332d661d839b3df86c72951417f58ce93615c400ce7ebc12d72ef13f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7EOA7FH52HPBQYLP56BANBVV6I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Christian Mendl, Daniel Hein, Simon Wiedemann, Steffen Udluft","submitted_at":"2022-06-09T19:23:10Z","abstract_excerpt":"We present a full implementation and simulation of a novel quantum reinforcement learning method. Our work is a detailed and formal proof of concept for how quantum algorithms can be used to solve reinforcement learning problems and shows that, given access to error-free, efficient quantum realizations of the agent and environment, quantum methods can yield provable improvements over classical Monte-Carlo based methods in terms of sample complexity. Our approach shows in detail how to combine amplitude estimation and Grover search into a policy evaluation and improvement scheme. We first devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04741","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/2206.04741/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":"2026-07-05T07:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1NFQGgsh8mMKq026yaP6rUt8vGbg4JUxQHwTm2eeQn3y7neYIXVs9klf1UoX2CwtwkhoZtdSsYNEuBia1ApCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T16:35:56.474271Z"},"content_sha256":"1975947f722ddf4cc2a30176815004486b3d82da17c6e7ad3095dc9a7b16fd28","schema_version":"1.0","event_id":"sha256:1975947f722ddf4cc2a30176815004486b3d82da17c6e7ad3095dc9a7b16fd28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7EOA7FH52HPBQYLP56BANBVV6I/bundle.json","state_url":"https://pith.science/pith/7EOA7FH52HPBQYLP56BANBVV6I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7EOA7FH52HPBQYLP56BANBVV6I/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":"2026-08-01T16:35:56Z","links":{"resolver":"https://pith.science/pith/7EOA7FH52HPBQYLP56BANBVV6I","bundle":"https://pith.science/pith/7EOA7FH52HPBQYLP56BANBVV6I/bundle.json","state":"https://pith.science/pith/7EOA7FH52HPBQYLP56BANBVV6I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7EOA7FH52HPBQYLP56BANBVV6I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7EOA7FH52HPBQYLP56BANBVV6I","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":"a619bae31c6e844a340e41cd48d359209949ba9e768915c9806adc76b0e6e35f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-06-09T19:23:10Z","title_canon_sha256":"370af5602732ab887a2db74ba9785083bac479e65fecc7a09468e06ab0719f05"},"schema_version":"1.0","source":{"id":"2206.04741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04741","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04741v2","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04741","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"7EOA7FH52HPB","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"7EOA7FH52HPBQYLP","created_at":"2026-07-05T07:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"7EOA7FH5","created_at":"2026-07-05T07:11:04Z"}],"graph_snapshots":[{"event_id":"sha256:1975947f722ddf4cc2a30176815004486b3d82da17c6e7ad3095dc9a7b16fd28","target":"graph","created_at":"2026-07-05T07:11:04Z","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/2206.04741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a full implementation and simulation of a novel quantum reinforcement learning method. Our work is a detailed and formal proof of concept for how quantum algorithms can be used to solve reinforcement learning problems and shows that, given access to error-free, efficient quantum realizations of the agent and environment, quantum methods can yield provable improvements over classical Monte-Carlo based methods in terms of sample complexity. Our approach shows in detail how to combine amplitude estimation and Grover search into a policy evaluation and improvement scheme. We first devel","authors_text":"Christian Mendl, Daniel Hein, Simon Wiedemann, Steffen Udluft","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-06-09T19:23:10Z","title":"Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04741","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:f26e676332d661d839b3df86c72951417f58ce93615c400ce7ebc12d72ef13f7","target":"record","created_at":"2026-07-05T07:11:04Z","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":"a619bae31c6e844a340e41cd48d359209949ba9e768915c9806adc76b0e6e35f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-06-09T19:23:10Z","title_canon_sha256":"370af5602732ab887a2db74ba9785083bac479e65fecc7a09468e06ab0719f05"},"schema_version":"1.0","source":{"id":"2206.04741","kind":"arxiv","version":2}},"canonical_sha256":"f91c0f94fdd1de18616fef820686b5f235685c3d8d1ddb0c2ae7effba965e6bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f91c0f94fdd1de18616fef820686b5f235685c3d8d1ddb0c2ae7effba965e6bc","first_computed_at":"2026-07-05T07:11:04.262004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:04.262004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"unAmhInIfIfx3QT3V6GBrvYl12AhXXZ6muhWikEF8eMGcrVYVKzGZ3oAM3CjN5P8wcUJnu/BWWeAcUxvLpF9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:04.262746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f26e676332d661d839b3df86c72951417f58ce93615c400ce7ebc12d72ef13f7","sha256:1975947f722ddf4cc2a30176815004486b3d82da17c6e7ad3095dc9a7b16fd28"],"state_sha256":"0622e9e3bef2130056dcef14a69f81c83c4b697615b218d7c028dd42adadd67c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9YL1U8Yy31NsnRqBMI1oQ/t7PLs9BJhNNXivdBk9YnwzOra7pPwyThrPYpfjy2VSbxcCQPKeIrOZ8y+BbU+LDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T16:35:56.479277Z","bundle_sha256":"7385624f2f3ee7e183cd19c0be25ab506bd28cf428e770651d74ebacd6001851"}}