{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TWSRZPJCYSR6KPVSYNF7GMX5DK","short_pith_number":"pith:TWSRZPJC","schema_version":"1.0","canonical_sha256":"9da51cbd22c4a3e53eb2c34bf332fd1aa830bc5515a9b9fcd09906e634091339","source":{"kind":"arxiv","id":"2506.20357","version":1},"attestation_state":"computed","paper":{"title":"Tabular Feature Discovery With Reasoning Type Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Seungeon Lee, Sungkyu Park, Sungwon Han","submitted_at":"2025-06-25T12:18:34Z","abstract_excerpt":"Feature engineering for tabular data remains a critical yet challenging step in machine learning. Recently, large language models (LLMs) have been used to automatically generate new features by leveraging their vast knowledge. However, existing LLM-based approaches often produce overly simple or repetitive features, partly due to inherent biases in the transformations the LLM chooses and the lack of structured reasoning guidance during generation. In this paper, we propose a novel method REFeat, which guides an LLM to discover diverse and informative features by leveraging multiple types of re"},"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":"2506.20357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-25T12:18:34Z","cross_cats_sorted":[],"title_canon_sha256":"0a3700c210b3f71480376ed8fb573ae605b847f6b87c777cc1d669ba8c6de0bc","abstract_canon_sha256":"6c40a3694187c29e3529887002da5ed4e57a65ee2993c2b258923767af6d1059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:04.172447Z","signature_b64":"2dVS53mYxgUBvIasJGEvH6hRHmyd5dUhlFhzcolvZWsM8Mic0w6O7W5ZvsmVe/5YuIdq2ez8/dGFeD9Gp5kYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9da51cbd22c4a3e53eb2c34bf332fd1aa830bc5515a9b9fcd09906e634091339","last_reissued_at":"2026-07-05T11:27:04.171939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:04.171939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tabular Feature Discovery With Reasoning Type Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Seungeon Lee, Sungkyu Park, Sungwon Han","submitted_at":"2025-06-25T12:18:34Z","abstract_excerpt":"Feature engineering for tabular data remains a critical yet challenging step in machine learning. Recently, large language models (LLMs) have been used to automatically generate new features by leveraging their vast knowledge. However, existing LLM-based approaches often produce overly simple or repetitive features, partly due to inherent biases in the transformations the LLM chooses and the lack of structured reasoning guidance during generation. In this paper, we propose a novel method REFeat, which guides an LLM to discover diverse and informative features by leveraging multiple types of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20357","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/2506.20357/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":"2506.20357","created_at":"2026-07-05T11:27:04.171999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20357v1","created_at":"2026-07-05T11:27:04.171999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20357","created_at":"2026-07-05T11:27:04.171999+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWSRZPJCYSR6","created_at":"2026-07-05T11:27:04.171999+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWSRZPJCYSR6KPVS","created_at":"2026-07-05T11:27:04.171999+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWSRZPJC","created_at":"2026-07-05T11:27:04.171999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK","json":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK.json","graph_json":"https://pith.science/api/pith-number/TWSRZPJCYSR6KPVSYNF7GMX5DK/graph.json","events_json":"https://pith.science/api/pith-number/TWSRZPJCYSR6KPVSYNF7GMX5DK/events.json","paper":"https://pith.science/paper/TWSRZPJC"},"agent_actions":{"view_html":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK","download_json":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK.json","view_paper":"https://pith.science/paper/TWSRZPJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20357&json=true","fetch_graph":"https://pith.science/api/pith-number/TWSRZPJCYSR6KPVSYNF7GMX5DK/graph.json","fetch_events":"https://pith.science/api/pith-number/TWSRZPJCYSR6KPVSYNF7GMX5DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK/action/storage_attestation","attest_author":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK/action/author_attestation","sign_citation":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK/action/citation_signature","submit_replication":"https://pith.science/pith/TWSRZPJCYSR6KPVSYNF7GMX5DK/action/replication_record"}},"created_at":"2026-07-05T11:27:04.171999+00:00","updated_at":"2026-07-05T11:27:04.171999+00:00"}