{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UV4FL4LU2PKWYM55ATBMHHA5Q2","short_pith_number":"pith:UV4FL4LU","schema_version":"1.0","canonical_sha256":"a57855f174d3d56c33bd04c2c39c1d86a29743bdd0b5adf3c3aac653342b69db","source":{"kind":"arxiv","id":"2405.15992","version":2},"attestation_state":"computed","paper":{"title":"Data Complexity Estimates for Operator Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Hrushikesh Mhaskar, Nikola B. Kovachki, Samuel Lanthaler","submitted_at":"2024-05-25T00:16:21Z","abstract_excerpt":"Operator learning has emerged as a new paradigm for the data-driven approximation of nonlinear operators. Despite its empirical success, the theoretical underpinnings governing the conditions for efficient operator learning remain incomplete. The present work develops theory to study the data complexity of operator learning, complementing existing research on the parametric complexity. We investigate the fundamental question: How many input/output samples are needed in operator learning to achieve a desired accuracy $\\epsilon$? This question is addressed from the point of view of $n$-widths, a"},"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":"2405.15992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T00:16:21Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"a47dbd65265ca09778c6f1606174aeb1dc7d9e936ab68a51e983682456bf68b1","abstract_canon_sha256":"0bfe704c13346e1a9733794152238622047557e2c8414cde6157a8b4ce0bdfcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:18.242094Z","signature_b64":"EC4EKzZy59yl/zi8jZlwQZhMByiWw9XPB8jhUkrcK4qrD2+G+HPqbQACI/n7yGJUjRHMaeCvTQhAFer2Q0DlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57855f174d3d56c33bd04c2c39c1d86a29743bdd0b5adf3c3aac653342b69db","last_reissued_at":"2026-07-05T09:22:18.241558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:18.241558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Complexity Estimates for Operator Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Hrushikesh Mhaskar, Nikola B. Kovachki, Samuel Lanthaler","submitted_at":"2024-05-25T00:16:21Z","abstract_excerpt":"Operator learning has emerged as a new paradigm for the data-driven approximation of nonlinear operators. Despite its empirical success, the theoretical underpinnings governing the conditions for efficient operator learning remain incomplete. The present work develops theory to study the data complexity of operator learning, complementing existing research on the parametric complexity. We investigate the fundamental question: How many input/output samples are needed in operator learning to achieve a desired accuracy $\\epsilon$? This question is addressed from the point of view of $n$-widths, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15992","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/2405.15992/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":"2405.15992","created_at":"2026-07-05T09:22:18.241618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15992v2","created_at":"2026-07-05T09:22:18.241618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15992","created_at":"2026-07-05T09:22:18.241618+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV4FL4LU2PKW","created_at":"2026-07-05T09:22:18.241618+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV4FL4LU2PKWYM55","created_at":"2026-07-05T09:22:18.241618+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV4FL4LU","created_at":"2026-07-05T09:22:18.241618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00320","citing_title":"From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01335","citing_title":"Transpose-free linear algebra","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01244","citing_title":"Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00296","citing_title":"Is Zero-Shot Super-Resolution Possible in Operator Learning?","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2","json":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2.json","graph_json":"https://pith.science/api/pith-number/UV4FL4LU2PKWYM55ATBMHHA5Q2/graph.json","events_json":"https://pith.science/api/pith-number/UV4FL4LU2PKWYM55ATBMHHA5Q2/events.json","paper":"https://pith.science/paper/UV4FL4LU"},"agent_actions":{"view_html":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2","download_json":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2.json","view_paper":"https://pith.science/paper/UV4FL4LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15992&json=true","fetch_graph":"https://pith.science/api/pith-number/UV4FL4LU2PKWYM55ATBMHHA5Q2/graph.json","fetch_events":"https://pith.science/api/pith-number/UV4FL4LU2PKWYM55ATBMHHA5Q2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2/action/storage_attestation","attest_author":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2/action/author_attestation","sign_citation":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2/action/citation_signature","submit_replication":"https://pith.science/pith/UV4FL4LU2PKWYM55ATBMHHA5Q2/action/replication_record"}},"created_at":"2026-07-05T09:22:18.241618+00:00","updated_at":"2026-07-05T09:22:18.241618+00:00"}