{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:37X6HCJ44T3ILQLHFO6ZO4LNJ2","short_pith_number":"pith:37X6HCJ4","schema_version":"1.0","canonical_sha256":"dfefe3893ce4f685c1672bbd97716d4e92f522bba40b29ce8566e6e41d20e221","source":{"kind":"arxiv","id":"2402.08726","version":2},"attestation_state":"computed","paper":{"title":"Trained quantum neural networks are Gaussian processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math-ph","math.MP","math.PR"],"primary_cat":"quant-ph","authors_text":"Filippo Girardi, Giacomo De Palma","submitted_at":"2024-02-13T19:00:08Z","abstract_excerpt":"We study quantum neural networks made by parametric one-qubit gates and fixed two-qubit gates in the limit of infinite width, where the generated function is the expectation value of the sum of single-qubit observables over all the qubits. First, we prove that the probability distribution of the function generated by the untrained network with randomly initialized parameters converges in distribution to a Gaussian process whenever each measured qubit is correlated only with few other measured qubits. Then, we analytically characterize the training of the network via gradient descent with squar"},"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":"2402.08726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2024-02-13T19:00:08Z","cross_cats_sorted":["cs.LG","math-ph","math.MP","math.PR"],"title_canon_sha256":"c6f6f02a0fb68c0e4e9279e3705e9465d8fa6969afc19edfb70af844385e9a33","abstract_canon_sha256":"8efded46ac7d2e0dd989fa84f4c64bf626fcc7106a5e73214edc28e0bf412570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:08.167391Z","signature_b64":"T+f7ESDXBVGUw3yNqWGmwQ9OPkawD4THesLBi6IE22HvYkhkCFH/pd2tW4m3rVZrlv4hNNuWtFo5/s9m5V6nBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfefe3893ce4f685c1672bbd97716d4e92f522bba40b29ce8566e6e41d20e221","last_reissued_at":"2026-05-26T01:03:08.166421Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:08.166421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trained quantum neural networks are Gaussian processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math-ph","math.MP","math.PR"],"primary_cat":"quant-ph","authors_text":"Filippo Girardi, Giacomo De Palma","submitted_at":"2024-02-13T19:00:08Z","abstract_excerpt":"We study quantum neural networks made by parametric one-qubit gates and fixed two-qubit gates in the limit of infinite width, where the generated function is the expectation value of the sum of single-qubit observables over all the qubits. First, we prove that the probability distribution of the function generated by the untrained network with randomly initialized parameters converges in distribution to a Gaussian process whenever each measured qubit is correlated only with few other measured qubits. Then, we analytically characterize the training of the network via gradient descent with squar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08726","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/2402.08726/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":"2402.08726","created_at":"2026-05-26T01:03:08.166558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08726v2","created_at":"2026-05-26T01:03:08.166558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08726","created_at":"2026-05-26T01:03:08.166558+00:00"},{"alias_kind":"pith_short_12","alias_value":"37X6HCJ44T3I","created_at":"2026-05-26T01:03:08.166558+00:00"},{"alias_kind":"pith_short_16","alias_value":"37X6HCJ44T3ILQLH","created_at":"2026-05-26T01:03:08.166558+00:00"},{"alias_kind":"pith_short_8","alias_value":"37X6HCJ4","created_at":"2026-05-26T01:03:08.166558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2501.14660","citing_title":"Mean-field limit from general mixtures of experts to quantum neural networks","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2508.04498","citing_title":"Efficient classical computation of the neural tangent kernel of quantum neural networks","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2","json":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2.json","graph_json":"https://pith.science/api/pith-number/37X6HCJ44T3ILQLHFO6ZO4LNJ2/graph.json","events_json":"https://pith.science/api/pith-number/37X6HCJ44T3ILQLHFO6ZO4LNJ2/events.json","paper":"https://pith.science/paper/37X6HCJ4"},"agent_actions":{"view_html":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2","download_json":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2.json","view_paper":"https://pith.science/paper/37X6HCJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08726&json=true","fetch_graph":"https://pith.science/api/pith-number/37X6HCJ44T3ILQLHFO6ZO4LNJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/37X6HCJ44T3ILQLHFO6ZO4LNJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2/action/storage_attestation","attest_author":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2/action/author_attestation","sign_citation":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2/action/citation_signature","submit_replication":"https://pith.science/pith/37X6HCJ44T3ILQLHFO6ZO4LNJ2/action/replication_record"}},"created_at":"2026-05-26T01:03:08.166558+00:00","updated_at":"2026-05-26T01:03:08.166558+00:00"}