{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XLORXLSJDOA4IMOOVHP3YXQEW7","short_pith_number":"pith:XLORXLSJ","schema_version":"1.0","canonical_sha256":"badd1bae491b81c431cea9dfbc5e04b7fd6ce6306ac2490d9edeb5a15b57e368","source":{"kind":"arxiv","id":"2508.13932","version":1},"attestation_state":"computed","paper":{"title":"How Usable is Automated Feature Engineering for Tabular Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bastian Sch\\\"afer, Frank Hutter, Lennart Purucker, Maciej Janowski","submitted_at":"2025-08-19T15:23:52Z","abstract_excerpt":"Tabular data, consisting of rows and columns, is omnipresent across various machine learning applications. Each column represents a feature, and features can be combined or transformed to create new, more informative features. Such feature engineering is essential to achieve peak performance in machine learning. Since manual feature engineering is expensive and time-consuming, a substantial effort has been put into automating it. Yet, existing automated feature engineering (AutoFE) methods have never been investigated regarding their usability for practitioners. Thus, we investigated 53 AutoFE"},"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":"2508.13932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-19T15:23:52Z","cross_cats_sorted":[],"title_canon_sha256":"1403213588818c2a313175891e6c2fe477010d24e8a61d0dca96188f0238f1c6","abstract_canon_sha256":"54f4ccf843698e1fe0fbf8aff1d6284c4f9ef6428a57760b2224a50d4c58baa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:09.733703Z","signature_b64":"oCrLbJiyqRiZGnMw2MJbGeRO4op9qnhRk5H1AkbhnIFWVoyln0dOzKW62bYOoBWR8uAqP7OI+iOGV4RGbaWBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"badd1bae491b81c431cea9dfbc5e04b7fd6ce6306ac2490d9edeb5a15b57e368","last_reissued_at":"2026-07-05T11:56:09.733205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:09.733205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Usable is Automated Feature Engineering for Tabular Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bastian Sch\\\"afer, Frank Hutter, Lennart Purucker, Maciej Janowski","submitted_at":"2025-08-19T15:23:52Z","abstract_excerpt":"Tabular data, consisting of rows and columns, is omnipresent across various machine learning applications. Each column represents a feature, and features can be combined or transformed to create new, more informative features. Such feature engineering is essential to achieve peak performance in machine learning. Since manual feature engineering is expensive and time-consuming, a substantial effort has been put into automating it. Yet, existing automated feature engineering (AutoFE) methods have never been investigated regarding their usability for practitioners. Thus, we investigated 53 AutoFE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13932","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/2508.13932/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":"2508.13932","created_at":"2026-07-05T11:56:09.733263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13932v1","created_at":"2026-07-05T11:56:09.733263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13932","created_at":"2026-07-05T11:56:09.733263+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLORXLSJDOA4","created_at":"2026-07-05T11:56:09.733263+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLORXLSJDOA4IMOO","created_at":"2026-07-05T11:56:09.733263+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLORXLSJ","created_at":"2026-07-05T11:56:09.733263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02384","citing_title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7","json":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7.json","graph_json":"https://pith.science/api/pith-number/XLORXLSJDOA4IMOOVHP3YXQEW7/graph.json","events_json":"https://pith.science/api/pith-number/XLORXLSJDOA4IMOOVHP3YXQEW7/events.json","paper":"https://pith.science/paper/XLORXLSJ"},"agent_actions":{"view_html":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7","download_json":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7.json","view_paper":"https://pith.science/paper/XLORXLSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13932&json=true","fetch_graph":"https://pith.science/api/pith-number/XLORXLSJDOA4IMOOVHP3YXQEW7/graph.json","fetch_events":"https://pith.science/api/pith-number/XLORXLSJDOA4IMOOVHP3YXQEW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7/action/storage_attestation","attest_author":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7/action/author_attestation","sign_citation":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7/action/citation_signature","submit_replication":"https://pith.science/pith/XLORXLSJDOA4IMOOVHP3YXQEW7/action/replication_record"}},"created_at":"2026-07-05T11:56:09.733263+00:00","updated_at":"2026-07-05T11:56:09.733263+00:00"}