{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V4F6USRLRUGYLHQA7NO2B3BG7Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8e0a2e5520a2b33f5838ee8bf9a96de5d208ca0b4d0b07c9b14cf431f577b725","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T09:54:39Z","title_canon_sha256":"314096f47d72f72877e23aa98198b2c348cddc76620218f10428589fea6b2475"},"schema_version":"1.0","source":{"id":"2407.02112","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02112","created_at":"2026-07-05T09:50:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02112v3","created_at":"2026-07-05T09:50:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02112","created_at":"2026-07-05T09:50:49Z"},{"alias_kind":"pith_short_12","alias_value":"V4F6USRLRUGY","created_at":"2026-07-05T09:50:49Z"},{"alias_kind":"pith_short_16","alias_value":"V4F6USRLRUGYLHQA","created_at":"2026-07-05T09:50:49Z"},{"alias_kind":"pith_short_8","alias_value":"V4F6USRL","created_at":"2026-07-05T09:50:49Z"}],"graph_snapshots":[{"event_id":"sha256:75cd1cfc686f16ebb053a472e27ca3de7520c5c2ae738925329d168a8443509a","target":"graph","created_at":"2026-07-05T09:50:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.02112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrej Tschalzev, Christian Bartelt, Heiner Stuckenschmidt, Sascha Marton, Stefan L\\\"udtke","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T09:54:39Z","title":"A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02112","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:90ab4e702ca19d44c72a36f6f695388fea571ff4b5531b47f26d4e4f86750918","target":"record","created_at":"2026-07-05T09:50:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8e0a2e5520a2b33f5838ee8bf9a96de5d208ca0b4d0b07c9b14cf431f577b725","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T09:54:39Z","title_canon_sha256":"314096f47d72f72877e23aa98198b2c348cddc76620218f10428589fea6b2475"},"schema_version":"1.0","source":{"id":"2407.02112","kind":"arxiv","version":3}},"canonical_sha256":"af0bea4a2b8d0d859e00fb5da0ec26fe022aba6d75cc7ddcc2ba42ea46df1196","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af0bea4a2b8d0d859e00fb5da0ec26fe022aba6d75cc7ddcc2ba42ea46df1196","first_computed_at":"2026-07-05T09:50:49.489001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:49.489001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cEAsYjempFcfuET5atiT0X/l8S7ZBKIeDGfLT4zeR/EGXOH+6IJgQwqaBcQ3K+jrkqtDSxeDjAZ2kKfThbbxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:49.489533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02112","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90ab4e702ca19d44c72a36f6f695388fea571ff4b5531b47f26d4e4f86750918","sha256:75cd1cfc686f16ebb053a472e27ca3de7520c5c2ae738925329d168a8443509a"],"state_sha256":"449a61d4adf962279a3e1580658e842b50a163d9eaeabec081972b3b59faa341"}