{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3HHVIWTHKLAFEEDBYV4UCSH763","short_pith_number":"pith:3HHVIWTH","schema_version":"1.0","canonical_sha256":"d9cf545a6752c0521061c5794148fff6c54ac83b89735c1bbe59d1e859dbf6f6","source":{"kind":"arxiv","id":"2208.11060","version":2},"attestation_state":"computed","paper":{"title":"Exponential concentration in quantum kernel methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"M. Cerezo, Samson Wang, Supanut Thanasilp, Zo\\\"e Holmes","submitted_at":"2022-08-23T16:06:10Z","abstract_excerpt":"Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model's parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance of quantum kernel models from the perspective of the resources needed to accurately estimate kernel va"},"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":"2208.11060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-08-23T16:06:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9e8f222509cec405b0d8c4e68362f0c7a837b8aeca2de658d19f23ceffc6f7ac","abstract_canon_sha256":"957a9093d9274a65074116d64d730f9ae37b281e6a691df570c1177a8d91e42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:54.500483Z","signature_b64":"wgwW/DWZoDQM61sES4yjOYo/fMhgJazLXbXvVhMvU+OAs5SR5+5io0oDEEIMpzRBg8NtnBxJBzn15OQaKuqXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9cf545a6752c0521061c5794148fff6c54ac83b89735c1bbe59d1e859dbf6f6","last_reissued_at":"2026-07-05T08:07:54.499957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:54.499957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exponential concentration in quantum kernel methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"M. Cerezo, Samson Wang, Supanut Thanasilp, Zo\\\"e Holmes","submitted_at":"2022-08-23T16:06:10Z","abstract_excerpt":"Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model's parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance of quantum kernel models from the perspective of the resources needed to accurately estimate kernel va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11060","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/2208.11060/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":"2208.11060","created_at":"2026-07-05T08:07:54.500033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11060v2","created_at":"2026-07-05T08:07:54.500033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11060","created_at":"2026-07-05T08:07:54.500033+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HHVIWTHKLAF","created_at":"2026-07-05T08:07:54.500033+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HHVIWTHKLAFEEDB","created_at":"2026-07-05T08:07:54.500033+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HHVIWTH","created_at":"2026-07-05T08:07:54.500033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31449","citing_title":"Support Vector Machine with a Scalable Quantum Kernel","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28927","citing_title":"Quantum encodings that preserve persistent homology","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21276","citing_title":"Benchmarking a machine-learning differential equations solver on a neutral-atom logical processor","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04414","citing_title":"Eliminating Vendor Lock-In in Quantum Machine Learning via Framework-Agnostic Neural Networks","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17202","citing_title":"Double Descent in Quantum Kernel Ridge Regression","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763","json":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763.json","graph_json":"https://pith.science/api/pith-number/3HHVIWTHKLAFEEDBYV4UCSH763/graph.json","events_json":"https://pith.science/api/pith-number/3HHVIWTHKLAFEEDBYV4UCSH763/events.json","paper":"https://pith.science/paper/3HHVIWTH"},"agent_actions":{"view_html":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763","download_json":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763.json","view_paper":"https://pith.science/paper/3HHVIWTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11060&json=true","fetch_graph":"https://pith.science/api/pith-number/3HHVIWTHKLAFEEDBYV4UCSH763/graph.json","fetch_events":"https://pith.science/api/pith-number/3HHVIWTHKLAFEEDBYV4UCSH763/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763/action/storage_attestation","attest_author":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763/action/author_attestation","sign_citation":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763/action/citation_signature","submit_replication":"https://pith.science/pith/3HHVIWTHKLAFEEDBYV4UCSH763/action/replication_record"}},"created_at":"2026-07-05T08:07:54.500033+00:00","updated_at":"2026-07-05T08:07:54.500033+00:00"}