{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:33WG7QEMBTPD37FJ4KQTTHHBAH","short_pith_number":"pith:33WG7QEM","schema_version":"1.0","canonical_sha256":"deec6fc08c0cde3dfca9e2a1399ce101efc97f1e45c42f48b3436c7ed7b8e766","source":{"kind":"arxiv","id":"2506.02406","version":1},"attestation_state":"computed","paper":{"title":"Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Wu, Renat Sergazinov, Shao-An Yin","submitted_at":"2025-06-03T03:45:13Z","abstract_excerpt":"While random Fourier features are a classic tool in kernel methods, their utility as a pre-processing step for deep learning on tabular data has been largely overlooked. Motivated by shortcomings in tabular deep learning pipelines - revealed through Neural Tangent Kernel (NTK) analysis - we revisit and repurpose random Fourier mappings as a parameter-free, architecture-agnostic transformation. By projecting each input into a fixed feature space via sine and cosine projections with frequencies drawn once at initialization, this approach circumvents the need for ad hoc normalization or additiona"},"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":"2506.02406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T03:45:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cbcfdc4c82db8fdf39f80622eec50f73f38aec55047549f09fb026a6382c720c","abstract_canon_sha256":"c392eb550c0577ef819ca0b094159bc80d91845a467380bdfe05d4cfcf208926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:38.191521Z","signature_b64":"ViiNWGXIWzmKo0YQrzfk9tyLffhkSP3OsjWd+3A1Q4IOx6MJkYm8JBd8+rnujvwlfIRP+IG5akljpj4+GXMbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deec6fc08c0cde3dfca9e2a1399ce101efc97f1e45c42f48b3436c7ed7b8e766","last_reissued_at":"2026-07-05T11:14:38.191041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:38.191041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Wu, Renat Sergazinov, Shao-An Yin","submitted_at":"2025-06-03T03:45:13Z","abstract_excerpt":"While random Fourier features are a classic tool in kernel methods, their utility as a pre-processing step for deep learning on tabular data has been largely overlooked. Motivated by shortcomings in tabular deep learning pipelines - revealed through Neural Tangent Kernel (NTK) analysis - we revisit and repurpose random Fourier mappings as a parameter-free, architecture-agnostic transformation. By projecting each input into a fixed feature space via sine and cosine projections with frequencies drawn once at initialization, this approach circumvents the need for ad hoc normalization or additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02406","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/2506.02406/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":"2506.02406","created_at":"2026-07-05T11:14:38.191096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02406v1","created_at":"2026-07-05T11:14:38.191096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02406","created_at":"2026-07-05T11:14:38.191096+00:00"},{"alias_kind":"pith_short_12","alias_value":"33WG7QEMBTPD","created_at":"2026-07-05T11:14:38.191096+00:00"},{"alias_kind":"pith_short_16","alias_value":"33WG7QEMBTPD37FJ","created_at":"2026-07-05T11:14:38.191096+00:00"},{"alias_kind":"pith_short_8","alias_value":"33WG7QEM","created_at":"2026-07-05T11:14:38.191096+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/33WG7QEMBTPD37FJ4KQTTHHBAH","json":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH.json","graph_json":"https://pith.science/api/pith-number/33WG7QEMBTPD37FJ4KQTTHHBAH/graph.json","events_json":"https://pith.science/api/pith-number/33WG7QEMBTPD37FJ4KQTTHHBAH/events.json","paper":"https://pith.science/paper/33WG7QEM"},"agent_actions":{"view_html":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH","download_json":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH.json","view_paper":"https://pith.science/paper/33WG7QEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02406&json=true","fetch_graph":"https://pith.science/api/pith-number/33WG7QEMBTPD37FJ4KQTTHHBAH/graph.json","fetch_events":"https://pith.science/api/pith-number/33WG7QEMBTPD37FJ4KQTTHHBAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH/action/storage_attestation","attest_author":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH/action/author_attestation","sign_citation":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH/action/citation_signature","submit_replication":"https://pith.science/pith/33WG7QEMBTPD37FJ4KQTTHHBAH/action/replication_record"}},"created_at":"2026-07-05T11:14:38.191096+00:00","updated_at":"2026-07-05T11:14:38.191096+00:00"}