{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MZGXPY2BMT5YMBJH3WOZLOYHYZ","short_pith_number":"pith:MZGXPY2B","schema_version":"1.0","canonical_sha256":"664d77e34164fb860527dd9d95bb07c6671836ba934ad14782d85a1a774f71a9","source":{"kind":"arxiv","id":"2205.13525","version":3},"attestation_state":"computed","paper":{"title":"On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Beaglehole, Mikhail Belkin, Parthe Pandit","submitted_at":"2022-05-26T17:43:20Z","abstract_excerpt":"``Benign overfitting'', the ability of certain algorithms to interpolate noisy training data and yet perform well out-of-sample, has been a topic of considerable recent interest. We show, using a fixed design setup, that an important class of predictors, kernel machines with translation-invariant kernels, does not exhibit benign overfitting in fixed dimensions. In particular, the estimated predictor does not converge to the ground truth with increasing sample size, for any non-zero regression function and any (even adaptive) bandwidth selection. To prove these results, we give exact expression"},"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":"2205.13525","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T17:43:20Z","cross_cats_sorted":[],"title_canon_sha256":"7db4ef1815841bbb1d495a915008067e32cd3c2ef5cf8168e8895cb4b9a072b0","abstract_canon_sha256":"d0999ecbe635b5de112949a65fe2ed6db3d45ef1784be26c0eed3529538c0a0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:30.881148Z","signature_b64":"JuCTN0YjNjIGWBYGTG6xNiHdzTJ2FLKacC45/+EGLc92n+Hp5kgI072740nRDMbGeaCJFhThON5UJPPBtEBzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664d77e34164fb860527dd9d95bb07c6671836ba934ad14782d85a1a774f71a9","last_reissued_at":"2026-07-05T06:00:30.880678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:30.880678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Beaglehole, Mikhail Belkin, Parthe Pandit","submitted_at":"2022-05-26T17:43:20Z","abstract_excerpt":"``Benign overfitting'', the ability of certain algorithms to interpolate noisy training data and yet perform well out-of-sample, has been a topic of considerable recent interest. We show, using a fixed design setup, that an important class of predictors, kernel machines with translation-invariant kernels, does not exhibit benign overfitting in fixed dimensions. In particular, the estimated predictor does not converge to the ground truth with increasing sample size, for any non-zero regression function and any (even adaptive) bandwidth selection. To prove these results, we give exact expression"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13525","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/2205.13525/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":"2205.13525","created_at":"2026-07-05T06:00:30.880734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13525v3","created_at":"2026-07-05T06:00:30.880734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13525","created_at":"2026-07-05T06:00:30.880734+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZGXPY2BMT5Y","created_at":"2026-07-05T06:00:30.880734+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZGXPY2BMT5YMBJH","created_at":"2026-07-05T06:00:30.880734+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZGXPY2B","created_at":"2026-07-05T06:00:30.880734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14200","citing_title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","ref_index":207,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ","json":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ.json","graph_json":"https://pith.science/api/pith-number/MZGXPY2BMT5YMBJH3WOZLOYHYZ/graph.json","events_json":"https://pith.science/api/pith-number/MZGXPY2BMT5YMBJH3WOZLOYHYZ/events.json","paper":"https://pith.science/paper/MZGXPY2B"},"agent_actions":{"view_html":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ","download_json":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ.json","view_paper":"https://pith.science/paper/MZGXPY2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13525&json=true","fetch_graph":"https://pith.science/api/pith-number/MZGXPY2BMT5YMBJH3WOZLOYHYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MZGXPY2BMT5YMBJH3WOZLOYHYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ/action/storage_attestation","attest_author":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ/action/author_attestation","sign_citation":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ/action/citation_signature","submit_replication":"https://pith.science/pith/MZGXPY2BMT5YMBJH3WOZLOYHYZ/action/replication_record"}},"created_at":"2026-07-05T06:00:30.880734+00:00","updated_at":"2026-07-05T06:00:30.880734+00:00"}