{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2A4FSO6F6CU2G77GNXNHDZG7IR","short_pith_number":"pith:2A4FSO6F","schema_version":"1.0","canonical_sha256":"d038593bc5f0a9a37fe66dda71e4df444562b0a2989e08cd92936a6accff5c7a","source":{"kind":"arxiv","id":"2109.11676","version":1},"attestation_state":"computed","paper":{"title":"Theory of overparametrization in quantum neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Diego Garc\\'ia-Mart\\'in, Martin Larocca, M. Cerezo, Nathan Ju, Patrick J. Coles","submitted_at":"2021-09-23T22:39:48Z","abstract_excerpt":"The prospect of achieving quantum advantage with Quantum Neural Networks (QNNs) is exciting. Understanding how QNN properties (e.g., the number of parameters $M$) affect the loss landscape is crucial to the design of scalable QNN architectures. Here, we rigorously analyze the overparametrization phenomenon in QNNs with periodic structure. We define overparametrization as the regime where the QNN has more than a critical number of parameters $M_c$ that allows it to explore all relevant directions in state space. Our main results show that the dimension of the Lie algebra obtained from the gener"},"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":"2109.11676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2021-09-23T22:39:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ef13d59c3779aa61f8e133d17f6953ece2398265bd2ff42391310e5b76423ba1","abstract_canon_sha256":"2791777c42d54d99432c6ebfe35e8290b6c5921fa73d7958576763bbac8deba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:43.182880Z","signature_b64":"CrvTiuHZfXTqB+6DxzP9weLI8ZG+Zr/bY8/RiSKkCcyu739T9DHIFB/V17DXODEmt/aAzf7AaCiT8h1RIP2JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d038593bc5f0a9a37fe66dda71e4df444562b0a2989e08cd92936a6accff5c7a","last_reissued_at":"2026-07-05T06:24:43.182406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:43.182406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory of overparametrization in quantum neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Diego Garc\\'ia-Mart\\'in, Martin Larocca, M. Cerezo, Nathan Ju, Patrick J. Coles","submitted_at":"2021-09-23T22:39:48Z","abstract_excerpt":"The prospect of achieving quantum advantage with Quantum Neural Networks (QNNs) is exciting. Understanding how QNN properties (e.g., the number of parameters $M$) affect the loss landscape is crucial to the design of scalable QNN architectures. Here, we rigorously analyze the overparametrization phenomenon in QNNs with periodic structure. We define overparametrization as the regime where the QNN has more than a critical number of parameters $M_c$ that allows it to explore all relevant directions in state space. Our main results show that the dimension of the Lie algebra obtained from the gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11676","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/2109.11676/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":"2109.11676","created_at":"2026-07-05T06:24:43.182467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11676v1","created_at":"2026-07-05T06:24:43.182467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11676","created_at":"2026-07-05T06:24:43.182467+00:00"},{"alias_kind":"pith_short_12","alias_value":"2A4FSO6F6CU2","created_at":"2026-07-05T06:24:43.182467+00:00"},{"alias_kind":"pith_short_16","alias_value":"2A4FSO6F6CU2G77G","created_at":"2026-07-05T06:24:43.182467+00:00"},{"alias_kind":"pith_short_8","alias_value":"2A4FSO6F","created_at":"2026-07-05T06:24:43.182467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05719","citing_title":"Symmetries and overparametrization properties of Hamiltonian variational ansatzes for the $(1+1)$d $\\mathbb{Z}_2$ lattice gauge theory","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16141","citing_title":"Reductions of QAOA Induced by Classical Symmetries: Theoretical Insights and Practical Implications","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05942","citing_title":"Architecture Shape Governs QNN Trainability: Jacobian Null Space Growth and Parameter Efficiency","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17202","citing_title":"Double Descent in Quantum Kernel Ridge Regression","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR","json":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR.json","graph_json":"https://pith.science/api/pith-number/2A4FSO6F6CU2G77GNXNHDZG7IR/graph.json","events_json":"https://pith.science/api/pith-number/2A4FSO6F6CU2G77GNXNHDZG7IR/events.json","paper":"https://pith.science/paper/2A4FSO6F"},"agent_actions":{"view_html":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR","download_json":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR.json","view_paper":"https://pith.science/paper/2A4FSO6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11676&json=true","fetch_graph":"https://pith.science/api/pith-number/2A4FSO6F6CU2G77GNXNHDZG7IR/graph.json","fetch_events":"https://pith.science/api/pith-number/2A4FSO6F6CU2G77GNXNHDZG7IR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR/action/storage_attestation","attest_author":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR/action/author_attestation","sign_citation":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR/action/citation_signature","submit_replication":"https://pith.science/pith/2A4FSO6F6CU2G77GNXNHDZG7IR/action/replication_record"}},"created_at":"2026-07-05T06:24:43.182467+00:00","updated_at":"2026-07-05T06:24:43.182467+00:00"}