{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HPOQTGERKEOETON7H4RHER72XK","short_pith_number":"pith:HPOQTGER","schema_version":"1.0","canonical_sha256":"3bdd099891511c49b9bf3f227247faba97906cba74efa6fb06e178baa047be18","source":{"kind":"arxiv","id":"1905.10764","version":1},"attestation_state":"computed","paper":{"title":"Lepskii Principle in Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Gilles Blanchard, Nicole M\\\"ucke, Peter Math\\'e","submitted_at":"2019-05-26T08:46:58Z","abstract_excerpt":"In the setting of supervised learning using reproducing kernel methods, we propose a data-dependent regularization parameter selection rule that is adaptive to the unknown regularity of the target function and is optimal both for the least-square (prediction) error and for the reproducing kernel Hilbert space (reconstruction) norm error. It is based on a modified Lepskii balancing principle using a varying family of norms."},"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":"1905.10764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-05-26T08:46:58Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"836b705543a848ff02e8b9f3c31b3eae39b9477b515ed09558ac63a85283554e","abstract_canon_sha256":"42bfd1450ba9c9576dd38e7ba3c1ebe97192deac38a6dd295c6fdc15186cff34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:05.337800Z","signature_b64":"nGPn/VDtlbch39bhmDdmUmlhwb3HaaxhF1eOBsLjaRW/HOukRY7nyKKFrOUc+oHGk7mYyu48JDfiaNhak09iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bdd099891511c49b9bf3f227247faba97906cba74efa6fb06e178baa047be18","last_reissued_at":"2026-05-17T23:45:05.337171Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:05.337171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lepskii Principle in Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Gilles Blanchard, Nicole M\\\"ucke, Peter Math\\'e","submitted_at":"2019-05-26T08:46:58Z","abstract_excerpt":"In the setting of supervised learning using reproducing kernel methods, we propose a data-dependent regularization parameter selection rule that is adaptive to the unknown regularity of the target function and is optimal both for the least-square (prediction) error and for the reproducing kernel Hilbert space (reconstruction) norm error. It is based on a modified Lepskii balancing principle using a varying family of norms."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10764","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":""},"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":"1905.10764","created_at":"2026-05-17T23:45:05.337292+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10764v1","created_at":"2026-05-17T23:45:05.337292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10764","created_at":"2026-05-17T23:45:05.337292+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPOQTGERKEOE","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPOQTGERKEOETON7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPOQTGER","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK","json":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK.json","graph_json":"https://pith.science/api/pith-number/HPOQTGERKEOETON7H4RHER72XK/graph.json","events_json":"https://pith.science/api/pith-number/HPOQTGERKEOETON7H4RHER72XK/events.json","paper":"https://pith.science/paper/HPOQTGER"},"agent_actions":{"view_html":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK","download_json":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK.json","view_paper":"https://pith.science/paper/HPOQTGER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10764&json=true","fetch_graph":"https://pith.science/api/pith-number/HPOQTGERKEOETON7H4RHER72XK/graph.json","fetch_events":"https://pith.science/api/pith-number/HPOQTGERKEOETON7H4RHER72XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK/action/storage_attestation","attest_author":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK/action/author_attestation","sign_citation":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK/action/citation_signature","submit_replication":"https://pith.science/pith/HPOQTGERKEOETON7H4RHER72XK/action/replication_record"}},"created_at":"2026-05-17T23:45:05.337292+00:00","updated_at":"2026-05-17T23:45:05.337292+00:00"}