{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AFYQOZXNJJAUPUI63RH72NY7Z3","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":"45fd8555dabf0ae6963f98a0155db37a1ce7d1a741329cb6590c0b4fe38828ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2019-02-06T13:18:35Z","title_canon_sha256":"9787d7ebc4396ac49daaef06ab005c023175be7fd9589bf101dd3783d5f3b8ef"},"schema_version":"1.0","source":{"id":"1902.02157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02157","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02157v2","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02157","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"AFYQOZXNJJAU","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"AFYQOZXNJJAUPUI6","created_at":"2026-07-05T02:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"AFYQOZXN","created_at":"2026-07-05T02:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:f9cf8cfe37a0ef677b9ea0785f71b933e85fc0624ec990b002f5458995ca5783","target":"graph","created_at":"2026-07-05T02:37:39Z","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/1902.02157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has been widely used in many problems, including quantum control of qubits. However, such problems can, at the same time, be solved by traditional, non-machine-learning methods, such as stochastic gradient descent and Krotov algorithms, and it remains unclear which one is most suitable when the control has specific constraints. In this work, we perform a comparative study on the efficacy of three reinforcement learning algorithms: tabular Q-learning, deep Q-learning, and policy gradient, as well as two non-machine-learning methods: stochastic gradient descent and Krotov ","authors_text":"Raza Asad, Xiao-Ming Zhang, Xin Wang, Xu-Chen Yang, Zezhu Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2019-02-06T13:18:35Z","title":"When does reinforcement learning stand out in quantum control? A comparative study on state preparation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02157","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:f0c36b90add75b29cdb259cf2584063fc5eb5ce270ab7dc6ff5f6898db8fdea7","target":"record","created_at":"2026-07-05T02:37:39Z","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":"45fd8555dabf0ae6963f98a0155db37a1ce7d1a741329cb6590c0b4fe38828ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2019-02-06T13:18:35Z","title_canon_sha256":"9787d7ebc4396ac49daaef06ab005c023175be7fd9589bf101dd3783d5f3b8ef"},"schema_version":"1.0","source":{"id":"1902.02157","kind":"arxiv","version":2}},"canonical_sha256":"01710766ed4a4147d11edc4ffd371fceede59b947b1d731b599160b3e028de78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01710766ed4a4147d11edc4ffd371fceede59b947b1d731b599160b3e028de78","first_computed_at":"2026-07-05T02:37:39.731212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:39.731212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z3jgEFEnIlVPcGdQKWIA7yjXIr+/uBflmcGlPr5kxtZjgGDoEAJtApuHSBIXYLe1PTosix7SqIX+cw3yHEnvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:39.731629Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c36b90add75b29cdb259cf2584063fc5eb5ce270ab7dc6ff5f6898db8fdea7","sha256:f9cf8cfe37a0ef677b9ea0785f71b933e85fc0624ec990b002f5458995ca5783"],"state_sha256":"74ca7e8aefb8ec49059bfaa482aa68a321d0f9c8b4da9a1624d43861edf1f411"}