{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4W5IMY5G5YYQDAHRHZVCT5CQR5","short_pith_number":"pith:4W5IMY5G","canonical_record":{"source":{"id":"2410.17787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T11:37:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da0f383749cf05bcb7810bbdf541121cd6a7007131e2128e2d52fd52e70b831e","abstract_canon_sha256":"6d584bf6dea60fde59ad72979016c46ced315f91fd21198b1c37f1409e708d8e"},"schema_version":"1.0"},"canonical_sha256":"e5ba8663a6ee310180f13e6a29f4508f5a2a1962638181196a0997df8b00d4f7","source":{"kind":"arxiv","id":"2410.17787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17787","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17787v2","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17787","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_12","alias_value":"4W5IMY5G5YYQ","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_16","alias_value":"4W5IMY5G5YYQDAHR","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_8","alias_value":"4W5IMY5G","created_at":"2026-07-05T11:37:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4W5IMY5G5YYQDAHRHZVCT5CQR5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T11:37:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da0f383749cf05bcb7810bbdf541121cd6a7007131e2128e2d52fd52e70b831e","abstract_canon_sha256":"6d584bf6dea60fde59ad72979016c46ced315f91fd21198b1c37f1409e708d8e"},"schema_version":"1.0"},"canonical_sha256":"e5ba8663a6ee310180f13e6a29f4508f5a2a1962638181196a0997df8b00d4f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:11.657004Z","signature_b64":"MIrDTC7kmUpjZkcc6Z8Du9SVi0qa8Zyt0/XyZzRJFjEcGUk+LVZQ+nV+17c716GZJgATgH9VUUJoLJsgv2JyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ba8663a6ee310180f13e6a29f4508f5a2a1962638181196a0997df8b00d4f7","last_reissued_at":"2026-07-05T11:37:11.656633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:11.656633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17787","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:37:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CR6V2MDR9Azxr0ZvOC7H0qdFDsqI7CxPgLqeUcP4Gc+chkV9dlETB6RcBG/WLWmspMWZbGmSZ4wxMwu2EI3YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:10:36.303244Z"},"content_sha256":"2e16c54767050a5c6ac8d23dafdc01e3ebf761a94ea87c15e7ccdcd4b9a07670","schema_version":"1.0","event_id":"sha256:2e16c54767050a5c6ac8d23dafdc01e3ebf761a94ea87c15e7ccdcd4b9a07670"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4W5IMY5G5YYQDAHRHZVCT5CQR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Engineer Too Many Simple Features For Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Jaris K\\\"uken, Lennart Purucker","submitted_at":"2024-10-23T11:37:20Z","abstract_excerpt":"Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time, researchers have observed ethically concerning negative biases in other LLM-related use cases, such as text generation. These developments motivated us to investigate whether LLMs exhibit a bias that negatively impacts the performance of feature engineering. While not ethically concerning, such a bias could hinder practitioners from fully utilizing LLMs for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17787","kind":"arxiv","version":2},"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/2410.17787/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:37:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sd3uZSUFw/J+Hdth238gA42zfTBYUXA3FwukGW7T+Id31zB8Hlhuh2yphbm3V3Z2sBAwfD2jBkIh7jsF5XjfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:10:36.303737Z"},"content_sha256":"f4d235b2270fa9be8ebc1384e8d13bb35425b3c39be9b1d3583550bfa0c14cb6","schema_version":"1.0","event_id":"sha256:f4d235b2270fa9be8ebc1384e8d13bb35425b3c39be9b1d3583550bfa0c14cb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/bundle.json","state_url":"https://pith.science/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:10:36Z","links":{"resolver":"https://pith.science/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5","bundle":"https://pith.science/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/bundle.json","state":"https://pith.science/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4W5IMY5G5YYQDAHRHZVCT5CQR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4W5IMY5G5YYQDAHRHZVCT5CQR5","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":"6d584bf6dea60fde59ad72979016c46ced315f91fd21198b1c37f1409e708d8e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T11:37:20Z","title_canon_sha256":"da0f383749cf05bcb7810bbdf541121cd6a7007131e2128e2d52fd52e70b831e"},"schema_version":"1.0","source":{"id":"2410.17787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17787","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17787v2","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17787","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_12","alias_value":"4W5IMY5G5YYQ","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_16","alias_value":"4W5IMY5G5YYQDAHR","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_8","alias_value":"4W5IMY5G","created_at":"2026-07-05T11:37:11Z"}],"graph_snapshots":[{"event_id":"sha256:f4d235b2270fa9be8ebc1384e8d13bb35425b3c39be9b1d3583550bfa0c14cb6","target":"graph","created_at":"2026-07-05T11:37:11Z","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/2410.17787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time, researchers have observed ethically concerning negative biases in other LLM-related use cases, such as text generation. These developments motivated us to investigate whether LLMs exhibit a bias that negatively impacts the performance of feature engineering. While not ethically concerning, such a bias could hinder practitioners from fully utilizing LLMs for a","authors_text":"Frank Hutter, Jaris K\\\"uken, Lennart Purucker","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T11:37:20Z","title":"Large Language Models Engineer Too Many Simple Features For Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17787","kind":"arxiv","version":2},"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":"sha256:2e16c54767050a5c6ac8d23dafdc01e3ebf761a94ea87c15e7ccdcd4b9a07670","target":"record","created_at":"2026-07-05T11:37:11Z","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":"6d584bf6dea60fde59ad72979016c46ced315f91fd21198b1c37f1409e708d8e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T11:37:20Z","title_canon_sha256":"da0f383749cf05bcb7810bbdf541121cd6a7007131e2128e2d52fd52e70b831e"},"schema_version":"1.0","source":{"id":"2410.17787","kind":"arxiv","version":2}},"canonical_sha256":"e5ba8663a6ee310180f13e6a29f4508f5a2a1962638181196a0997df8b00d4f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5ba8663a6ee310180f13e6a29f4508f5a2a1962638181196a0997df8b00d4f7","first_computed_at":"2026-07-05T11:37:11.656633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:11.656633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MIrDTC7kmUpjZkcc6Z8Du9SVi0qa8Zyt0/XyZzRJFjEcGUk+LVZQ+nV+17c716GZJgATgH9VUUJoLJsgv2JyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:11.657004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e16c54767050a5c6ac8d23dafdc01e3ebf761a94ea87c15e7ccdcd4b9a07670","sha256:f4d235b2270fa9be8ebc1384e8d13bb35425b3c39be9b1d3583550bfa0c14cb6"],"state_sha256":"473712c207ba2bc0ad74a4c5c59c13db3c47831db5eb42a40e4e52725441fd83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAvL4Nmw111ELLtmOMuISLCFAyzX5rgkVnUapFHtx4BWDILatYLGV7jhpgewuKPl5l18YOfKjZ13mwQA1DtUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:10:36.307270Z","bundle_sha256":"6c8bb5dd5f37f50f9ad9bc931447ff742c00ef337885e1702777daf57bb6c5d7"}}