{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E5XXQ7WH3A55VPZ6D2NESDDK52","short_pith_number":"pith:E5XXQ7WH","schema_version":"1.0","canonical_sha256":"276f787ec7d83bdabf3e1e9a490c6aeea0044964ed5677ac95e5565a37b05059","source":{"kind":"arxiv","id":"2203.07337","version":1},"attestation_state":"computed","paper":{"title":"Phenomenology of Double Descent in Finite-Width Neural Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aurelien Lucchi, Bernhard Sch\\\"olkopf, Sidak Pal Singh, Thomas Hofmann","submitted_at":"2022-03-14T17:39:49Z","abstract_excerpt":"`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized. The current theoretical understanding behind the occurrence of this phenomenon is primarily based on linear and kernel regression models -- with informal parallels to neural networks via the Neural Tangent Kernel. Therefore such analyses do not adequately capture the mechanisms behind double descent in finite-width neural networks, as well as, disregard crucial components -- such as the choice of the loss function. We address these shortcomings by leveraging "},"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":"2203.07337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-03-14T17:39:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbada5719cd3df4c69cb7966599fb9ddcf69e378b5458e4b3d36aeb85b3e1903","abstract_canon_sha256":"74bac9fd563f4793e43305da159e5b4aefb373faf15eae0d45c12a2f66d31654"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:02.968370Z","signature_b64":"LTE9aYejpvlhyvgdBjcDIddqMs8Uy6NyuhGhtoF+Nmb9Ad4G/zUt+yuuovQMcKtrzTz2je9GqcdBr3LIXz49CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"276f787ec7d83bdabf3e1e9a490c6aeea0044964ed5677ac95e5565a37b05059","last_reissued_at":"2026-07-05T04:05:02.967909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:02.967909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phenomenology of Double Descent in Finite-Width Neural Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aurelien Lucchi, Bernhard Sch\\\"olkopf, Sidak Pal Singh, Thomas Hofmann","submitted_at":"2022-03-14T17:39:49Z","abstract_excerpt":"`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized. The current theoretical understanding behind the occurrence of this phenomenon is primarily based on linear and kernel regression models -- with informal parallels to neural networks via the Neural Tangent Kernel. Therefore such analyses do not adequately capture the mechanisms behind double descent in finite-width neural networks, as well as, disregard crucial components -- such as the choice of the loss function. We address these shortcomings by leveraging "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07337","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.07337/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":"2203.07337","created_at":"2026-07-05T04:05:02.967960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07337v1","created_at":"2026-07-05T04:05:02.967960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07337","created_at":"2026-07-05T04:05:02.967960+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5XXQ7WH3A55","created_at":"2026-07-05T04:05:02.967960+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5XXQ7WH3A55VPZ6","created_at":"2026-07-05T04:05:02.967960+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5XXQ7WH","created_at":"2026-07-05T04:05:02.967960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21494","citing_title":"Double descent for least-squares interpolation on contaminated data: A simulation study","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52","json":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52.json","graph_json":"https://pith.science/api/pith-number/E5XXQ7WH3A55VPZ6D2NESDDK52/graph.json","events_json":"https://pith.science/api/pith-number/E5XXQ7WH3A55VPZ6D2NESDDK52/events.json","paper":"https://pith.science/paper/E5XXQ7WH"},"agent_actions":{"view_html":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52","download_json":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52.json","view_paper":"https://pith.science/paper/E5XXQ7WH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07337&json=true","fetch_graph":"https://pith.science/api/pith-number/E5XXQ7WH3A55VPZ6D2NESDDK52/graph.json","fetch_events":"https://pith.science/api/pith-number/E5XXQ7WH3A55VPZ6D2NESDDK52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52/action/storage_attestation","attest_author":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52/action/author_attestation","sign_citation":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52/action/citation_signature","submit_replication":"https://pith.science/pith/E5XXQ7WH3A55VPZ6D2NESDDK52/action/replication_record"}},"created_at":"2026-07-05T04:05:02.967960+00:00","updated_at":"2026-07-05T04:05:02.967960+00:00"}