{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JOGMGEFM7UTLCDCDFHJ4QYQTGL","short_pith_number":"pith:JOGMGEFM","schema_version":"1.0","canonical_sha256":"4b8cc310acfd26b10c4329d3c8621332c6cba9195ea2ed93eb26603600e3f9af","source":{"kind":"arxiv","id":"2408.14817","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Assaf Shmuel, Oren Glickman, Teddy Lazebnik","submitted_at":"2024-08-27T06:58:52Z","abstract_excerpt":"The analysis of tabular datasets is highly prevalent both in scientific research and real-world applications of Machine Learning (ML). Unlike many other ML tasks, Deep Learning (DL) models often do not outperform traditional methods in this area. Previous comparative benchmarks have shown that DL performance is frequently equivalent or even inferior to models such as Gradient Boosting Machines (GBMs). In this study, we introduce a comprehensive benchmark aimed at better characterizing the types of datasets where DL models excel. Although several important benchmarks for tabular datasets alread"},"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":"2408.14817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T06:58:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6470c183781c2f38d63be02a7a6bee03f4c8669f771e92a8fd0508cd8ac2dc35","abstract_canon_sha256":"56030834134f691000a7663e23b785974023db55908605035d32ec016d11680a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:39.316495Z","signature_b64":"1/qhF2RXHdpVzfPMkK/8XMC7zrCIIGELKcckK3mPo1ObTQqDqeLKKqMbyfHUZH02sNG8FCJ2pGlGxjtKm7Q1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b8cc310acfd26b10c4329d3c8621332c6cba9195ea2ed93eb26603600e3f9af","last_reissued_at":"2026-07-05T08:59:39.316039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:39.316039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Assaf Shmuel, Oren Glickman, Teddy Lazebnik","submitted_at":"2024-08-27T06:58:52Z","abstract_excerpt":"The analysis of tabular datasets is highly prevalent both in scientific research and real-world applications of Machine Learning (ML). Unlike many other ML tasks, Deep Learning (DL) models often do not outperform traditional methods in this area. Previous comparative benchmarks have shown that DL performance is frequently equivalent or even inferior to models such as Gradient Boosting Machines (GBMs). In this study, we introduce a comprehensive benchmark aimed at better characterizing the types of datasets where DL models excel. Although several important benchmarks for tabular datasets alread"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14817","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/2408.14817/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":"2408.14817","created_at":"2026-07-05T08:59:39.316097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14817v1","created_at":"2026-07-05T08:59:39.316097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14817","created_at":"2026-07-05T08:59:39.316097+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOGMGEFM7UTL","created_at":"2026-07-05T08:59:39.316097+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOGMGEFM7UTLCDCD","created_at":"2026-07-05T08:59:39.316097+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOGMGEFM","created_at":"2026-07-05T08:59:39.316097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25811","citing_title":"Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22812","citing_title":"Clutch: High Performance Vector-Scalar Comparison using DRAM via Chunked Temporal Coding","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02384","citing_title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL","json":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL.json","graph_json":"https://pith.science/api/pith-number/JOGMGEFM7UTLCDCDFHJ4QYQTGL/graph.json","events_json":"https://pith.science/api/pith-number/JOGMGEFM7UTLCDCDFHJ4QYQTGL/events.json","paper":"https://pith.science/paper/JOGMGEFM"},"agent_actions":{"view_html":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL","download_json":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL.json","view_paper":"https://pith.science/paper/JOGMGEFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14817&json=true","fetch_graph":"https://pith.science/api/pith-number/JOGMGEFM7UTLCDCDFHJ4QYQTGL/graph.json","fetch_events":"https://pith.science/api/pith-number/JOGMGEFM7UTLCDCDFHJ4QYQTGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL/action/storage_attestation","attest_author":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL/action/author_attestation","sign_citation":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL/action/citation_signature","submit_replication":"https://pith.science/pith/JOGMGEFM7UTLCDCDFHJ4QYQTGL/action/replication_record"}},"created_at":"2026-07-05T08:59:39.316097+00:00","updated_at":"2026-07-05T08:59:39.316097+00:00"}