{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:63Y3ZC4XSXQFYTLGXFRQXSCIXQ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"14b8241e23373358aed43cc9168fec1ad57d35d97bfa9942342c90d2da8ac3d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T05:46:31Z","title_canon_sha256":"18624d13aadd5a9b7008d8464174ce45aa33879fe9804c98fa68adc4f04f4495"},"schema_version":"1.0","source":{"id":"2605.15240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15240","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15240v1","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15240","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"63Y3ZC4XSXQF","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_16","alias_value":"63Y3ZC4XSXQFYTLG","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_8","alias_value":"63Y3ZC4X","created_at":"2026-05-20T00:00:47Z"}],"graph_snapshots":[{"event_id":"sha256:a2285b08e83b4c7ee616c5aebfd8d0c4319f87a454e3a18e5c6dbf72a9ea4096","target":"graph","created_at":"2026-05-20T00:00:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we establish a generalization bound from an eigenvalues/eigenvectors estimation perspective, showing that strong generalization requires increasing eigenvector alignment, eigenvalue magnitude, or gaps between consecutive eigenvalues."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The analysis relies on finite-sample settings and the generalization error arising from a suboptimal finite training set, with the claim that near-zero reconstruction error is trivially obtained for high-rank kernels (abstract paragraph on findings)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Derives a finite-sample generalization bound for KRR by analyzing how perturbations in the kernel matrix affect eigenvector and eigenvalue estimates, concluding that reconstruction error has limited value for high-rank kernels."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"In kernel ridge regression, generalization performance depends on the alignment of kernel eigenvectors with the target vectors rather than just reconstruction accuracy."}],"snapshot_sha256":"7f7cbcc8b4cca444b1b43eefb4017fc3d10bfcf434a4f2b28008068758f96ef1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.478076Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:27:11.650379Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T16:01:54.846103Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.823389Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15240/integrity.json","findings":[],"snapshot_sha256":"55df6f5beb37498ab72b1168dd01bb8dc60ac8f508c337d9f129b0fdae589fc6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the critical role of eigenalignments between the kernel matrix and learning targets in achieving robust generalization in learning problems. We establish a direct connection between generalization performance in kernel methods and the estimation of eigenvectors and eigenvalues of matrices, offering a more intuitive understanding compared to prior work with minimal assumptions. We also show that, since the prediction task in KRR is essentially the weighted sum of eigenvectors/singular vectors, by analyzing how much error can be caused by perturbations to the kernel matri","authors_text":"Daniel Krutz, Ernest Fokoue, Richard Lange, Yang Liu","cross_cats":["cs.LG"],"headline":"In kernel ridge regression, generalization performance depends on the alignment of kernel eigenvectors with the target vectors rather than just reconstruction accuracy.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T05:46:31Z","title":"On Kernel Eigen-alignments of KRR: Reconstruction and Generalization"},"references":{"count":300,"internal_anchors":0,"resolved_work":300,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Functional Analysis","work_id":"d008c9ef-4bb6-4628-b86c-4480965f7fad","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"On regularization algorithms in learning theory","work_id":"194c30b8-ff4a-4366-9967-603377b4cd58","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Approximation theory and harmonic analysis on spheres and balls","work_id":"1285f2aa-0a2c-4d68-952d-859fa02f6e0a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Aspects of Harmonic Analysis and Representation Theory","work_id":"1c41302d-ac21-4e94-9423-5a1fb98e757e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Replica Method for the Machine Learning Theorist","work_id":"3fb96779-0acf-47d1-93ce-87ad1bd12cde","year":null}],"snapshot_sha256":"02c88f0ebf44fd21b0bbafc3635260ff33a54334fbf76a0402856cd99896c51d"},"source":{"id":"2605.15240","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T16:20:04.582258Z","id":"5ed2cae9-cb45-450a-8309-ff14fddda4cd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Derives a finite-sample generalization bound for KRR by analyzing how perturbations in the kernel matrix affect eigenvector and eigenvalue estimates, concluding that reconstruction error has limited value for high-rank kernels.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"In kernel ridge regression, generalization performance depends on the alignment of kernel eigenvectors with the target vectors rather than just reconstruction accuracy.","strongest_claim":"we establish a generalization bound from an eigenvalues/eigenvectors estimation perspective, showing that strong generalization requires increasing eigenvector alignment, eigenvalue magnitude, or gaps between consecutive eigenvalues.","weakest_assumption":"The analysis relies on finite-sample settings and the generalization error arising from a suboptimal finite training set, with the claim that near-zero reconstruction error is trivially obtained for high-rank kernels (abstract paragraph on findings)."}},"verdict_id":"5ed2cae9-cb45-450a-8309-ff14fddda4cd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac2311ef96d33a4d674e05146692dd3ac56dad6029d6ebf1f18e81dcfb4cd105","target":"record","created_at":"2026-05-20T00:00:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"14b8241e23373358aed43cc9168fec1ad57d35d97bfa9942342c90d2da8ac3d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T05:46:31Z","title_canon_sha256":"18624d13aadd5a9b7008d8464174ce45aa33879fe9804c98fa68adc4f04f4495"},"schema_version":"1.0","source":{"id":"2605.15240","kind":"arxiv","version":1}},"canonical_sha256":"f6f1bc8b9795e05c4d66b9630bc848bc3a4937a082c398bac259a676507b848f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6f1bc8b9795e05c4d66b9630bc848bc3a4937a082c398bac259a676507b848f","first_computed_at":"2026-05-20T00:00:47.929077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:47.929077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ndKg9uKjC4rILz+awS346OsoDzAnJwlvNJF1xRulSudOzJRx0FApGfHgI9rUN6B4WpirFlLMVR/ntvXDoE2Cw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:47.929859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac2311ef96d33a4d674e05146692dd3ac56dad6029d6ebf1f18e81dcfb4cd105","sha256:a2285b08e83b4c7ee616c5aebfd8d0c4319f87a454e3a18e5c6dbf72a9ea4096","sha256:4b54012549ab480187b2f0bfbd288f51ba7a9ff4782ce6d0d3bc8149f86a9475"],"state_sha256":"434ae3423d48513cbea762a94529594b07b57e156d13a148ac6a1850e71848e6"}