{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MOLAXTEU64TBQFGPLVZPDXRNCQ","short_pith_number":"pith:MOLAXTEU","schema_version":"1.0","canonical_sha256":"63960bcc94f7261814cf5d72f1de2d1429f8307d39c6198064877d8e0b00466b","source":{"kind":"arxiv","id":"2104.14539","version":2},"attestation_state":"computed","paper":{"title":"Model-Free Quantum Control with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"A. Eickbusch, B. Royer, H. Liu, I. Tsioutsios, M. H. Devoret, V. V. Sivak","submitted_at":"2021-04-29T17:53:26Z","abstract_excerpt":"Model bias is an inherent limitation of the current dominant approach to optimal quantum control, which relies on a system simulation for optimization of control policies. To overcome this limitation, we propose a circuit-based approach for training a reinforcement learning agent on quantum control tasks in a model-free way. Given a continuously parameterized control circuit, the agent learns its parameters through trial-and-error interaction with the quantum system, using measurement outcomes as the only source of information about the quantum state. Focusing on control of a harmonic oscillat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.14539","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2021-04-29T17:53:26Z","cross_cats_sorted":[],"title_canon_sha256":"0285c178dfee6adbcc1ad5b10b4caec4cf2c73ac6f95f1d7b6cc7ff6f76d0337","abstract_canon_sha256":"f5f77fd59f1922479580dcef998929bab936451e82ba984aa45fe31e117811d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:56.350373Z","signature_b64":"DuBeOShUHxkRwno6gw/40at+s2JC4uRi4ej3yDrWs6l5qob2FOnLm4uHz7qdKCkMY15jRHuvdLnbknp54hMjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63960bcc94f7261814cf5d72f1de2d1429f8307d39c6198064877d8e0b00466b","last_reissued_at":"2026-07-05T04:09:56.349867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:56.349867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Free Quantum Control with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"A. Eickbusch, B. Royer, H. Liu, I. Tsioutsios, M. H. Devoret, V. V. Sivak","submitted_at":"2021-04-29T17:53:26Z","abstract_excerpt":"Model bias is an inherent limitation of the current dominant approach to optimal quantum control, which relies on a system simulation for optimization of control policies. To overcome this limitation, we propose a circuit-based approach for training a reinforcement learning agent on quantum control tasks in a model-free way. Given a continuously parameterized control circuit, the agent learns its parameters through trial-and-error interaction with the quantum system, using measurement outcomes as the only source of information about the quantum state. Focusing on control of a harmonic oscillat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14539","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/2104.14539/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.14539","created_at":"2026-07-05T04:09:56.349928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.14539v2","created_at":"2026-07-05T04:09:56.349928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14539","created_at":"2026-07-05T04:09:56.349928+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOLAXTEU64TB","created_at":"2026-07-05T04:09:56.349928+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOLAXTEU64TBQFGP","created_at":"2026-07-05T04:09:56.349928+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOLAXTEU","created_at":"2026-07-05T04:09:56.349928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03974","citing_title":"Real-time adaptive quantum error correction by model-free multi-agent learning","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ","json":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ.json","graph_json":"https://pith.science/api/pith-number/MOLAXTEU64TBQFGPLVZPDXRNCQ/graph.json","events_json":"https://pith.science/api/pith-number/MOLAXTEU64TBQFGPLVZPDXRNCQ/events.json","paper":"https://pith.science/paper/MOLAXTEU"},"agent_actions":{"view_html":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ","download_json":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ.json","view_paper":"https://pith.science/paper/MOLAXTEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.14539&json=true","fetch_graph":"https://pith.science/api/pith-number/MOLAXTEU64TBQFGPLVZPDXRNCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MOLAXTEU64TBQFGPLVZPDXRNCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ/action/storage_attestation","attest_author":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ/action/author_attestation","sign_citation":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ/action/citation_signature","submit_replication":"https://pith.science/pith/MOLAXTEU64TBQFGPLVZPDXRNCQ/action/replication_record"}},"created_at":"2026-07-05T04:09:56.349928+00:00","updated_at":"2026-07-05T04:09:56.349928+00:00"}