{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5N65AIP5HWDZUSZZ63ACHSIQJG","short_pith_number":"pith:5N65AIP5","schema_version":"1.0","canonical_sha256":"eb7dd021fd3d879a4b39f6c023c910499997692f4f253ed9fbeca8005aed9614","source":{"kind":"arxiv","id":"2408.08294","version":4},"attestation_state":"computed","paper":{"title":"eGAD! double descent is explained by Generalized Aliasing Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math-ph","math.MP","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Gus L. W. Hart, Jared P. Whitehead, Mark K. Transtrum, Tyler J. Jarvis","submitted_at":"2024-08-15T17:49:24Z","abstract_excerpt":"A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that balances model simplicity with its ability to fit complex functions. However, over-parameterized models exhibit counterintuitive behaviors, such as \"double descent\" in which models of increasing complexity exhibit decreasing generalization error. Others may exhibit more complicated patterns of predictive error with multiple peaks and valleys. Neither double "},"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":"2408.08294","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2024-08-15T17:49:24Z","cross_cats_sorted":["cs.LG","math-ph","math.MP","stat.ML","stat.TH"],"title_canon_sha256":"a1e453b938d82be1018ae565e32695078352621d316bfdfc930f564cd1820170","abstract_canon_sha256":"be6c968637f8f0b4dc0fba9b7fe85ff29b599136268bae2a85c330f4b7f50bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:24.311841Z","signature_b64":"D49VmwPiSp1VHvomTdvOrQWgy7uLNVp3mVDz1GmF/vLCPRbf0HT5MWXu+ICCj6Vupg5HQnYP5UWjZerhRht0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7dd021fd3d879a4b39f6c023c910499997692f4f253ed9fbeca8005aed9614","last_reissued_at":"2026-07-05T11:14:24.311341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:24.311341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"eGAD! double descent is explained by Generalized Aliasing Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math-ph","math.MP","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Gus L. W. Hart, Jared P. Whitehead, Mark K. Transtrum, Tyler J. Jarvis","submitted_at":"2024-08-15T17:49:24Z","abstract_excerpt":"A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that balances model simplicity with its ability to fit complex functions. However, over-parameterized models exhibit counterintuitive behaviors, such as \"double descent\" in which models of increasing complexity exhibit decreasing generalization error. Others may exhibit more complicated patterns of predictive error with multiple peaks and valleys. Neither double "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08294","kind":"arxiv","version":4},"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/2408.08294/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":"2408.08294","created_at":"2026-07-05T11:14:24.311402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08294v4","created_at":"2026-07-05T11:14:24.311402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08294","created_at":"2026-07-05T11:14:24.311402+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N65AIP5HWDZ","created_at":"2026-07-05T11:14:24.311402+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N65AIP5HWDZUSZZ","created_at":"2026-07-05T11:14:24.311402+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N65AIP5","created_at":"2026-07-05T11:14:24.311402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG","json":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG.json","graph_json":"https://pith.science/api/pith-number/5N65AIP5HWDZUSZZ63ACHSIQJG/graph.json","events_json":"https://pith.science/api/pith-number/5N65AIP5HWDZUSZZ63ACHSIQJG/events.json","paper":"https://pith.science/paper/5N65AIP5"},"agent_actions":{"view_html":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG","download_json":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG.json","view_paper":"https://pith.science/paper/5N65AIP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08294&json=true","fetch_graph":"https://pith.science/api/pith-number/5N65AIP5HWDZUSZZ63ACHSIQJG/graph.json","fetch_events":"https://pith.science/api/pith-number/5N65AIP5HWDZUSZZ63ACHSIQJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG/action/storage_attestation","attest_author":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG/action/author_attestation","sign_citation":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG/action/citation_signature","submit_replication":"https://pith.science/pith/5N65AIP5HWDZUSZZ63ACHSIQJG/action/replication_record"}},"created_at":"2026-07-05T11:14:24.311402+00:00","updated_at":"2026-07-05T11:14:24.311402+00:00"}