{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PPLRSA3E6RO3JXJ52EITK4IAJY","short_pith_number":"pith:PPLRSA3E","canonical_record":{"source":{"id":"1802.04063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","cross_cats_sorted":["quant-ph"],"title_canon_sha256":"c47af10100698f98d235d5228938be57c887efbf6ffc206da016f7c88790d6bf","abstract_canon_sha256":"8d79e542c1431d26e4739ec72a1942ce7f8a39182cf1864de71de8b48eaaa4ff"},"schema_version":"1.0"},"canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","source":{"kind":"arxiv","id":"1802.04063","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04063","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04063v2","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04063","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"PPLRSA3E6RO3","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPLRSA3E6RO3JXJ5","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPLRSA3E","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PPLRSA3E6RO3JXJ52EITK4IAJY","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","cross_cats_sorted":["quant-ph"],"title_canon_sha256":"c47af10100698f98d235d5228938be57c887efbf6ffc206da016f7c88790d6bf","abstract_canon_sha256":"8d79e542c1431d26e4739ec72a1942ce7f8a39182cf1864de71de8b48eaaa4ff"},"schema_version":"1.0"},"canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:35.613306Z","signature_b64":"8h9oD9X9KHbPeNA3rTyrNUZ5dPUMpl5UVmCehgoywHHxprzd/Yy3rRCELBPo/iYlUl1pUoLDn1ocWEC6RS+pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","last_reissued_at":"2026-05-18T00:18:35.612567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:35.612567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04063","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":"2026-05-18T00:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1VWCQmPYU0DgLVAD/vMINqwWSWyYVKBy36z5ZjVJU7qKRAdGS7nEfgAVU7ZIqHTAHSr4d/uwkd9DfD9k5VHsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:37:27.544599Z"},"content_sha256":"bd7f58d3d100ede734dd13eb8a53655b01f176c191cbefad172cb6e2915ec7a5","schema_version":"1.0","event_id":"sha256:bd7f58d3d100ede734dd13eb8a53655b01f176c191cbefad172cb6e2915ec7a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PPLRSA3E6RO3JXJ52EITK4IAJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Moritz August","submitted_at":"2018-02-12T14:27:54Z","abstract_excerpt":"In this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04063","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":""},"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":"2026-05-18T00:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HUOsiTbAcVaAizaMY5cjluiCpBtFsJO+ZBTBZNc9qa4N1LuOMZx+3WDY8AdBwK2W+jkI462sewR8YjszPeJQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:37:27.544973Z"},"content_sha256":"873bc5efcdf53ad61ac3b279181e1065e948ba49fc520bb9b6e44f0e659b1f1a","schema_version":"1.0","event_id":"sha256:873bc5efcdf53ad61ac3b279181e1065e948ba49fc520bb9b6e44f0e659b1f1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/bundle.json","state_url":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/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":"2026-06-03T05:37:27Z","links":{"resolver":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY","bundle":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/bundle.json","state":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PPLRSA3E6RO3JXJ52EITK4IAJY","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":"8d79e542c1431d26e4739ec72a1942ce7f8a39182cf1864de71de8b48eaaa4ff","cross_cats_sorted":["quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","title_canon_sha256":"c47af10100698f98d235d5228938be57c887efbf6ffc206da016f7c88790d6bf"},"schema_version":"1.0","source":{"id":"1802.04063","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04063","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04063v2","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04063","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"PPLRSA3E6RO3","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPLRSA3E6RO3JXJ5","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPLRSA3E","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:873bc5efcdf53ad61ac3b279181e1065e948ba49fc520bb9b6e44f0e659b1f1a","target":"graph","created_at":"2026-05-18T00:18:35Z","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"},"paper":{"abstract_excerpt":"In this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Moritz August","cross_cats":["quant-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","title":"Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04063","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:bd7f58d3d100ede734dd13eb8a53655b01f176c191cbefad172cb6e2915ec7a5","target":"record","created_at":"2026-05-18T00:18:35Z","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":"8d79e542c1431d26e4739ec72a1942ce7f8a39182cf1864de71de8b48eaaa4ff","cross_cats_sorted":["quant-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","title_canon_sha256":"c47af10100698f98d235d5228938be57c887efbf6ffc206da016f7c88790d6bf"},"schema_version":"1.0","source":{"id":"1802.04063","kind":"arxiv","version":2}},"canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","first_computed_at":"2026-05-18T00:18:35.612567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:35.612567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8h9oD9X9KHbPeNA3rTyrNUZ5dPUMpl5UVmCehgoywHHxprzd/Yy3rRCELBPo/iYlUl1pUoLDn1ocWEC6RS+pDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:35.613306Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04063","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd7f58d3d100ede734dd13eb8a53655b01f176c191cbefad172cb6e2915ec7a5","sha256:873bc5efcdf53ad61ac3b279181e1065e948ba49fc520bb9b6e44f0e659b1f1a"],"state_sha256":"9f230adb345e32c5c921f0213dae632f27e49d0fc5b9163c15860352540252d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+N5xy/3ealxBmzgGloH2cU8adlld9K7FflceoNPsCMXHvv/kfxqC9MU2vpyBSOBfOG4wkiHixYhFbGIHMzVPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T05:37:27.546897Z","bundle_sha256":"8d338835a77c1ff8ed75d6cefbdc0edcacde1eef24c43e0e52df43bd288567b5"}}