{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UC5W6BMG2SW6GNSTBIWSR3DFAW","short_pith_number":"pith:UC5W6BMG","schema_version":"1.0","canonical_sha256":"a0bb6f0586d4ade336530a2d28ec6505a907637ae55ce4e7183af7ee88f77b92","source":{"kind":"arxiv","id":"1908.01364","version":1},"attestation_state":"computed","paper":{"title":"The Capacity of Quantum Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.optics"],"primary_cat":"quant-ph","authors_text":"Logan G. Wright, Peter L. McMahon","submitted_at":"2019-08-04T15:46:48Z","abstract_excerpt":"A key open question in quantum computation is what advantages quantum neural networks (QNNs) may have over classical neural networks (NNs), and in what situations these advantages may transpire. Here we address this question by studying the memory capacity $C$ of QNNs, which is a metric of the expressive power of a QNN that we have adapted from classical NN theory. We present a capacity inequality showing that the capacity of a QNN is bounded by the information $W$ that can be trained into its parameters: $C \\leq W$. One consequence of this bound is that QNNs that are parameterized classically"},"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":"1908.01364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2019-08-04T15:46:48Z","cross_cats_sorted":["physics.optics"],"title_canon_sha256":"1e97c888b7da702c95de0623e9f0f0f6e2bdaecf1ada0cf6a56b87acfe2bbf64","abstract_canon_sha256":"f569a1c00844f405c333c252c56133eecaf33208e09c69afc8d6616fe5dbdd7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:29.603552Z","signature_b64":"eUDmTnCjuFZ3yxbCiJMsvdvSAPKFwzrsdeh6f67kJeGWHwHXOieYFhp74YdO5I10EwdR+HNf1kiiYPRSW/4cBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0bb6f0586d4ade336530a2d28ec6505a907637ae55ce4e7183af7ee88f77b92","last_reissued_at":"2026-07-04T23:51:29.603059Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:29.603059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Capacity of Quantum Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.optics"],"primary_cat":"quant-ph","authors_text":"Logan G. Wright, Peter L. McMahon","submitted_at":"2019-08-04T15:46:48Z","abstract_excerpt":"A key open question in quantum computation is what advantages quantum neural networks (QNNs) may have over classical neural networks (NNs), and in what situations these advantages may transpire. Here we address this question by studying the memory capacity $C$ of QNNs, which is a metric of the expressive power of a QNN that we have adapted from classical NN theory. We present a capacity inequality showing that the capacity of a QNN is bounded by the information $W$ that can be trained into its parameters: $C \\leq W$. One consequence of this bound is that QNNs that are parameterized classically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01364","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/1908.01364/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":"1908.01364","created_at":"2026-07-04T23:51:29.603115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01364v1","created_at":"2026-07-04T23:51:29.603115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01364","created_at":"2026-07-04T23:51:29.603115+00:00"},{"alias_kind":"pith_short_12","alias_value":"UC5W6BMG2SW6","created_at":"2026-07-04T23:51:29.603115+00:00"},{"alias_kind":"pith_short_16","alias_value":"UC5W6BMG2SW6GNST","created_at":"2026-07-04T23:51:29.603115+00:00"},{"alias_kind":"pith_short_8","alias_value":"UC5W6BMG","created_at":"2026-07-04T23:51:29.603115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16918","citing_title":"Quantum Computational-Sensing Advantage","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW","json":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW.json","graph_json":"https://pith.science/api/pith-number/UC5W6BMG2SW6GNSTBIWSR3DFAW/graph.json","events_json":"https://pith.science/api/pith-number/UC5W6BMG2SW6GNSTBIWSR3DFAW/events.json","paper":"https://pith.science/paper/UC5W6BMG"},"agent_actions":{"view_html":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW","download_json":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW.json","view_paper":"https://pith.science/paper/UC5W6BMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01364&json=true","fetch_graph":"https://pith.science/api/pith-number/UC5W6BMG2SW6GNSTBIWSR3DFAW/graph.json","fetch_events":"https://pith.science/api/pith-number/UC5W6BMG2SW6GNSTBIWSR3DFAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW/action/storage_attestation","attest_author":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW/action/author_attestation","sign_citation":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW/action/citation_signature","submit_replication":"https://pith.science/pith/UC5W6BMG2SW6GNSTBIWSR3DFAW/action/replication_record"}},"created_at":"2026-07-04T23:51:29.603115+00:00","updated_at":"2026-07-04T23:51:29.603115+00:00"}