{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ADWIBOTFKTATQIZEHH6KAL3XF","short_pith_number":"pith:7ADWIBOT","schema_version":"1.0","canonical_sha256":"f8076405d32aa609c11921cfe5017bb95635272616c2700dcb8abe5ad1385634","source":{"kind":"arxiv","id":"2407.03257","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Huai-Hong Yin, Wei-Lun Chao","submitted_at":"2024-07-03T16:38:57Z","abstract_excerpt":"The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by classical methods, e.g., integration of nearest neighbors into neural networks, we investigate whether these classical methods can be revitalized with modern techniques. We revisit a differentiable version of $K$-nearest neighbors (KNN) -- Neighbourhood Components Analysis (NCA) -- originally designed to learn a linear projection to capture semantic similarities between instances, and seek to gradually add modern deep l"},"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":"2407.03257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T16:38:57Z","cross_cats_sorted":[],"title_canon_sha256":"71d8f141e62eb7cacf228e4c2b85dbeee161c1090cc38ca6a7f1d22c92da788d","abstract_canon_sha256":"e17f94cae2e872535820d388fc39916574d4f1eb548488ca6e9958d95ace0f7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:47.875069Z","signature_b64":"N0VqnAk+A6qIYCnqWpxcFvNEyxIeohqsAXGXjAx0pg5KSOkH6obAir4Pl5WfNoSrGGgHmjj+EarcDBp/FgqEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8076405d32aa609c11921cfe5017bb95635272616c2700dcb8abe5ad1385634","last_reissued_at":"2026-07-05T10:22:47.874133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:47.874133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Huai-Hong Yin, Wei-Lun Chao","submitted_at":"2024-07-03T16:38:57Z","abstract_excerpt":"The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by classical methods, e.g., integration of nearest neighbors into neural networks, we investigate whether these classical methods can be revitalized with modern techniques. We revisit a differentiable version of $K$-nearest neighbors (KNN) -- Neighbourhood Components Analysis (NCA) -- originally designed to learn a linear projection to capture semantic similarities between instances, and seek to gradually add modern deep l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03257","kind":"arxiv","version":2},"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/2407.03257/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":"2407.03257","created_at":"2026-07-05T10:22:47.874329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03257v2","created_at":"2026-07-05T10:22:47.874329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03257","created_at":"2026-07-05T10:22:47.874329+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ADWIBOTFKTA","created_at":"2026-07-05T10:22:47.874329+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ADWIBOTFKTATQIZ","created_at":"2026-07-05T10:22:47.874329+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ADWIBOT","created_at":"2026-07-05T10:22:47.874329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05380","citing_title":"TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning","ref_index":163,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02384","citing_title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16791","citing_title":"TabArena: A Living Benchmark for Machine Learning on Tabular Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06047","citing_title":"TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06047","citing_title":"TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF","json":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF.json","graph_json":"https://pith.science/api/pith-number/7ADWIBOTFKTATQIZEHH6KAL3XF/graph.json","events_json":"https://pith.science/api/pith-number/7ADWIBOTFKTATQIZEHH6KAL3XF/events.json","paper":"https://pith.science/paper/7ADWIBOT"},"agent_actions":{"view_html":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF","download_json":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF.json","view_paper":"https://pith.science/paper/7ADWIBOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03257&json=true","fetch_graph":"https://pith.science/api/pith-number/7ADWIBOTFKTATQIZEHH6KAL3XF/graph.json","fetch_events":"https://pith.science/api/pith-number/7ADWIBOTFKTATQIZEHH6KAL3XF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF/action/storage_attestation","attest_author":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF/action/author_attestation","sign_citation":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF/action/citation_signature","submit_replication":"https://pith.science/pith/7ADWIBOTFKTATQIZEHH6KAL3XF/action/replication_record"}},"created_at":"2026-07-05T10:22:47.874329+00:00","updated_at":"2026-07-05T10:22:47.874329+00:00"}