{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WAIQ3KSLVJQWOJ6M7HOFBKZ6YD","short_pith_number":"pith:WAIQ3KSL","schema_version":"1.0","canonical_sha256":"b0110daa4baa616727ccf9dc50ab3ec0f263765d8e378efdd3cf5671cf1afdb5","source":{"kind":"arxiv","id":"2509.00232","version":1},"attestation_state":"computed","paper":{"title":"Feature Augmentations for High-Dimensional Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Bingyan Wang, Jianqing Fan, Xiaonan Zhu","submitted_at":"2025-08-29T20:50:16Z","abstract_excerpt":"High-dimensional measurements are often correlated which motivates their approximation by factor models. This holds also true when features are engineered via low-dimensional interactions or kernel tricks. This often results in over parametrization and requires a fast dimensionality reduction. We propose a simple technique to enhance the performance of supervised learning algorithms by augmenting features with factors extracted from design matrices and their transformations. This is implemented by using the factors and idiosyncratic residuals which significantly weaken the correlations between"},"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":"2509.00232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-08-29T20:50:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfcabf6390cc59a18cdee70cc3b16365be84190c19c1c293e09bae34498e8b0","abstract_canon_sha256":"dece10b7bfc33299494ec4adbf64d191bdb0d8809cc9b125bb8f87a4ff0bacf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:11.836361Z","signature_b64":"96Hg0q16ab7YDcouvIBruRGMJV07NMv5SaUKK7xo93Rb2/ldZmmTR48mTO2buKZJWD7UAaIajmD9DxpUqFAqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0110daa4baa616727ccf9dc50ab3ec0f263765d8e378efdd3cf5671cf1afdb5","last_reissued_at":"2026-07-05T12:02:11.835831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:11.835831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Augmentations for High-Dimensional Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Bingyan Wang, Jianqing Fan, Xiaonan Zhu","submitted_at":"2025-08-29T20:50:16Z","abstract_excerpt":"High-dimensional measurements are often correlated which motivates their approximation by factor models. This holds also true when features are engineered via low-dimensional interactions or kernel tricks. This often results in over parametrization and requires a fast dimensionality reduction. We propose a simple technique to enhance the performance of supervised learning algorithms by augmenting features with factors extracted from design matrices and their transformations. This is implemented by using the factors and idiosyncratic residuals which significantly weaken the correlations between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00232","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/2509.00232/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":"2509.00232","created_at":"2026-07-05T12:02:11.835899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00232v1","created_at":"2026-07-05T12:02:11.835899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00232","created_at":"2026-07-05T12:02:11.835899+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAIQ3KSLVJQW","created_at":"2026-07-05T12:02:11.835899+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAIQ3KSLVJQWOJ6M","created_at":"2026-07-05T12:02:11.835899+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAIQ3KSL","created_at":"2026-07-05T12:02:11.835899+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/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD","json":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD.json","graph_json":"https://pith.science/api/pith-number/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/graph.json","events_json":"https://pith.science/api/pith-number/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/events.json","paper":"https://pith.science/paper/WAIQ3KSL"},"agent_actions":{"view_html":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD","download_json":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD.json","view_paper":"https://pith.science/paper/WAIQ3KSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00232&json=true","fetch_graph":"https://pith.science/api/pith-number/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/graph.json","fetch_events":"https://pith.science/api/pith-number/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/action/storage_attestation","attest_author":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/action/author_attestation","sign_citation":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/action/citation_signature","submit_replication":"https://pith.science/pith/WAIQ3KSLVJQWOJ6M7HOFBKZ6YD/action/replication_record"}},"created_at":"2026-07-05T12:02:11.835899+00:00","updated_at":"2026-07-05T12:02:11.835899+00:00"}