{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V4F6USRLRUGYLHQA7NO2B3BG7Y","short_pith_number":"pith:V4F6USRL","schema_version":"1.0","canonical_sha256":"af0bea4a2b8d0d859e00fb5da0ec26fe022aba6d75cc7ddcc2ba42ea46df1196","source":{"kind":"arxiv","id":"2407.02112","version":3},"attestation_state":"computed","paper":{"title":"A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrej Tschalzev, Christian Bartelt, Heiner Stuckenschmidt, Sascha Marton, Stefan L\\\"udtke","submitted_at":"2024-07-02T09:54:39Z","abstract_excerpt":"Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and i"},"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":"2407.02112","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T09:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"314096f47d72f72877e23aa98198b2c348cddc76620218f10428589fea6b2475","abstract_canon_sha256":"8e0a2e5520a2b33f5838ee8bf9a96de5d208ca0b4d0b07c9b14cf431f577b725"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:49.489533Z","signature_b64":"cEAsYjempFcfuET5atiT0X/l8S7ZBKIeDGfLT4zeR/EGXOH+6IJgQwqaBcQ3K+jrkqtDSxeDjAZ2kKfThbbxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af0bea4a2b8d0d859e00fb5da0ec26fe022aba6d75cc7ddcc2ba42ea46df1196","last_reissued_at":"2026-07-05T09:50:49.489001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:49.489001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrej Tschalzev, Christian Bartelt, Heiner Stuckenschmidt, Sascha Marton, Stefan L\\\"udtke","submitted_at":"2024-07-02T09:54:39Z","abstract_excerpt":"Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02112","kind":"arxiv","version":3},"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/2407.02112/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":"2407.02112","created_at":"2026-07-05T09:50:49.489066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02112v3","created_at":"2026-07-05T09:50:49.489066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02112","created_at":"2026-07-05T09:50:49.489066+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4F6USRLRUGY","created_at":"2026-07-05T09:50:49.489066+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4F6USRLRUGYLHQA","created_at":"2026-07-05T09:50:49.489066+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4F6USRL","created_at":"2026-07-05T09:50:49.489066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14312","citing_title":"MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y","json":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y.json","graph_json":"https://pith.science/api/pith-number/V4F6USRLRUGYLHQA7NO2B3BG7Y/graph.json","events_json":"https://pith.science/api/pith-number/V4F6USRLRUGYLHQA7NO2B3BG7Y/events.json","paper":"https://pith.science/paper/V4F6USRL"},"agent_actions":{"view_html":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y","download_json":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y.json","view_paper":"https://pith.science/paper/V4F6USRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02112&json=true","fetch_graph":"https://pith.science/api/pith-number/V4F6USRLRUGYLHQA7NO2B3BG7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/V4F6USRLRUGYLHQA7NO2B3BG7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y/action/storage_attestation","attest_author":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y/action/author_attestation","sign_citation":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y/action/citation_signature","submit_replication":"https://pith.science/pith/V4F6USRLRUGYLHQA7NO2B3BG7Y/action/replication_record"}},"created_at":"2026-07-05T09:50:49.489066+00:00","updated_at":"2026-07-05T09:50:49.489066+00:00"}