{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HBL6P5YYPIWT3QEIQ7C273LRNS","short_pith_number":"pith:HBL6P5YY","schema_version":"1.0","canonical_sha256":"3857e7f7187a2d3dc08887c5afed716c93a305d7b920f714fa05d84c834df295","source":{"kind":"arxiv","id":"2211.08875","version":3},"attestation_state":"computed","paper":{"title":"Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Mattes Mollenhauer, Nicole M\\\"ucke, T. J. Sullivan","submitted_at":"2022-11-16T12:33:01Z","abstract_excerpt":"We consider the problem of learning a linear operator $\\theta$ between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensions. We show that this goal can be reformulated as an inverse problem for $\\theta$ with the feature that its forward operator is generally non-compact (even if $\\theta$ is assumed to be compact or of $p$-Schatten class). However, we prove that, in terms of spectral properties and regularisation theory, this inverse problem is equivalent to the known compact inverse problem associated with scalar response regress"},"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":"2211.08875","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2022-11-16T12:33:01Z","cross_cats_sorted":["math.FA","math.PR","stat.ML","stat.TH"],"title_canon_sha256":"131c6dccd286026cadd8840c871a63e3cbe48313bfc0759a1a6049499f7e0603","abstract_canon_sha256":"47d233f1d013d6752c180299def97ef97797770c06ea1811e79dd8a8f8978de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:58.241295Z","signature_b64":"Qfjj3BLOn23WqTjQxhI0f0/nmlMMNwJpGWurUK6NEEj/JTNwpwr8XZ1IRUU5YTP3q1Q49DsAxhYTFTaZeZpfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3857e7f7187a2d3dc08887c5afed716c93a305d7b920f714fa05d84c834df295","last_reissued_at":"2026-07-05T08:41:58.240953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:58.240953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Mattes Mollenhauer, Nicole M\\\"ucke, T. J. Sullivan","submitted_at":"2022-11-16T12:33:01Z","abstract_excerpt":"We consider the problem of learning a linear operator $\\theta$ between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensions. We show that this goal can be reformulated as an inverse problem for $\\theta$ with the feature that its forward operator is generally non-compact (even if $\\theta$ is assumed to be compact or of $p$-Schatten class). However, we prove that, in terms of spectral properties and regularisation theory, this inverse problem is equivalent to the known compact inverse problem associated with scalar response regress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08875","kind":"arxiv","version":3},"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/2211.08875/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":"2211.08875","created_at":"2026-07-05T08:41:58.241007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08875v3","created_at":"2026-07-05T08:41:58.241007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08875","created_at":"2026-07-05T08:41:58.241007+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBL6P5YYPIWT","created_at":"2026-07-05T08:41:58.241007+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBL6P5YYPIWT3QEI","created_at":"2026-07-05T08:41:58.241007+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBL6P5YY","created_at":"2026-07-05T08:41:58.241007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00296","citing_title":"Is Zero-Shot Super-Resolution Possible in Operator Learning?","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16733","citing_title":"Concentration Inequalities for Sample Cross-Covariances","ref_index":259,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18288","citing_title":"Operator Learning for Schr\\\"{o}dinger Equation: Unitarity, Error Bounds, and Time Generalization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06087","citing_title":"Safety Certification is Classification","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS","json":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS.json","graph_json":"https://pith.science/api/pith-number/HBL6P5YYPIWT3QEIQ7C273LRNS/graph.json","events_json":"https://pith.science/api/pith-number/HBL6P5YYPIWT3QEIQ7C273LRNS/events.json","paper":"https://pith.science/paper/HBL6P5YY"},"agent_actions":{"view_html":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS","download_json":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS.json","view_paper":"https://pith.science/paper/HBL6P5YY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08875&json=true","fetch_graph":"https://pith.science/api/pith-number/HBL6P5YYPIWT3QEIQ7C273LRNS/graph.json","fetch_events":"https://pith.science/api/pith-number/HBL6P5YYPIWT3QEIQ7C273LRNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS/action/storage_attestation","attest_author":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS/action/author_attestation","sign_citation":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS/action/citation_signature","submit_replication":"https://pith.science/pith/HBL6P5YYPIWT3QEIQ7C273LRNS/action/replication_record"}},"created_at":"2026-07-05T08:41:58.241007+00:00","updated_at":"2026-07-05T08:41:58.241007+00:00"}