{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PI3BQH4DG2SFW4SL7QWH5AHLW7","short_pith_number":"pith:PI3BQH4D","schema_version":"1.0","canonical_sha256":"7a36181f8336a45b724bfc2c7e80ebb7dda6158e783c93976e604a6c8a4f748f","source":{"kind":"arxiv","id":"2406.19380","version":4},"attestation_state":"computed","paper":{"title":"TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy","submitted_at":"2024-06-27T17:55:31Z","abstract_excerpt":"Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical deployment. In this work, we analyze existing tabular benchmarks and find two common characteristics of tabular data in typical industrial applications that are underrepresented in the datasets usually used for evaluation in the literature. First, in real-world deployment scenarios, distribution of data often changes over time. To account for this distributi"},"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":"2406.19380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T17:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"cedf432df1b07c6792bba0db7be22ee2ae03354cd97ffbc8bd9ef2a03e1e121f","abstract_canon_sha256":"76585e0d54daaa992d38db281294202625d3cc7b950aee3efb6c6190c03fd5c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:20.068833Z","signature_b64":"85RAj72GeyPFwiMNI7AzXKkCxUX1H+nxrsq9DnpC9IrfBMi2LWKKoJv9iVqEPEjmNA76JYuXM91zxEjcEb0BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a36181f8336a45b724bfc2c7e80ebb7dda6158e783c93976e604a6c8a4f748f","last_reissued_at":"2026-07-05T09:25:20.068331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:20.068331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy","submitted_at":"2024-06-27T17:55:31Z","abstract_excerpt":"Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical deployment. In this work, we analyze existing tabular benchmarks and find two common characteristics of tabular data in typical industrial applications that are underrepresented in the datasets usually used for evaluation in the literature. First, in real-world deployment scenarios, distribution of data often changes over time. To account for this distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19380","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/2406.19380/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":"2406.19380","created_at":"2026-07-05T09:25:20.068408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19380v4","created_at":"2026-07-05T09:25:20.068408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19380","created_at":"2026-07-05T09:25:20.068408+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI3BQH4DG2SF","created_at":"2026-07-05T09:25:20.068408+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI3BQH4DG2SFW4SL","created_at":"2026-07-05T09:25:20.068408+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI3BQH4D","created_at":"2026-07-05T09:25:20.068408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02384","citing_title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22644","citing_title":"Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16791","citing_title":"TabArena: A Living Benchmark for Machine Learning on Tabular Data","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06290","citing_title":"Data Language Models: A New Foundation Model Class for Tabular Data","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7","json":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7.json","graph_json":"https://pith.science/api/pith-number/PI3BQH4DG2SFW4SL7QWH5AHLW7/graph.json","events_json":"https://pith.science/api/pith-number/PI3BQH4DG2SFW4SL7QWH5AHLW7/events.json","paper":"https://pith.science/paper/PI3BQH4D"},"agent_actions":{"view_html":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7","download_json":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7.json","view_paper":"https://pith.science/paper/PI3BQH4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19380&json=true","fetch_graph":"https://pith.science/api/pith-number/PI3BQH4DG2SFW4SL7QWH5AHLW7/graph.json","fetch_events":"https://pith.science/api/pith-number/PI3BQH4DG2SFW4SL7QWH5AHLW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7/action/storage_attestation","attest_author":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7/action/author_attestation","sign_citation":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7/action/citation_signature","submit_replication":"https://pith.science/pith/PI3BQH4DG2SFW4SL7QWH5AHLW7/action/replication_record"}},"created_at":"2026-07-05T09:25:20.068408+00:00","updated_at":"2026-07-05T09:25:20.068408+00:00"}