{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BCF5GBVQKQZTCJO6FDHH3JIRXY","short_pith_number":"pith:BCF5GBVQ","canonical_record":{"source":{"id":"2406.08527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:31:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00beedab5d959f1b13a0d41f09d192919de06519631de5bb87ee94ca716e4742","abstract_canon_sha256":"77633870aced64fdc303a4bef1b2658b09e7d9a1c2d8166a499747f3558cf0f6"},"schema_version":"1.0"},"canonical_sha256":"088bd306b054333125de28ce7da511be2f60ccbb4c3ac0bf77c15867c2827f33","source":{"kind":"arxiv","id":"2406.08527","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08527","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08527v2","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08527","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"BCF5GBVQKQZT","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"BCF5GBVQKQZTCJO6","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"BCF5GBVQ","created_at":"2026-07-05T09:36:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BCF5GBVQKQZTCJO6FDHH3JIRXY","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:31:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00beedab5d959f1b13a0d41f09d192919de06519631de5bb87ee94ca716e4742","abstract_canon_sha256":"77633870aced64fdc303a4bef1b2658b09e7d9a1c2d8166a499747f3558cf0f6"},"schema_version":"1.0"},"canonical_sha256":"088bd306b054333125de28ce7da511be2f60ccbb4c3ac0bf77c15867c2827f33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:45.839403Z","signature_b64":"O38+xsVOEt4cht1glTi+uZY3KFxMHbOW5X6258e4v4+h6/c+fBKRrewl455BnhZ1iLiyZ++DOZnOmO30fX4hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"088bd306b054333125de28ce7da511be2f60ccbb4c3ac0bf77c15867c2827f33","last_reissued_at":"2026-07-05T09:36:45.838923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:45.838923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08527","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":"2026-07-05T09:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKiQBxrgy/FrdP5C3/vCbLcgcxrnom1rHR0B7kyugDxV/Q5+QCHn3yg9hXhGlFxKFiAUqkZ/tyC85pa82hC4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:23:03.283362Z"},"content_sha256":"ca1f0d9af4dce83b5ac661b7ba3ab389cce82e4409aa1c803345aa3c00e485a1","schema_version":"1.0","event_id":"sha256:ca1f0d9af4dce83b5ac661b7ba3ab389cce82e4409aa1c803345aa3c00e485a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BCF5GBVQKQZTCJO6FDHH3JIRXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaehyung Kim, Jaehyun Nam, Jihoon Tack, Jinwoo Shin, Kyuyoung Kim, Seunghyuk Oh","submitted_at":"2024-06-12T08:31:34Z","abstract_excerpt":"In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. While these feature engineering techniques are effective, they typically depend on a pre-defined search space and primarily use validation scores for feature selection, thereby missing valuable insights from previous experiments. To address these limitations, we propose a novel tabular learning framework that utilizes large language models (LLMs), termed Optimizing Column feature generator with decision Tree reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08527","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/2406.08527/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":"2026-07-05T09:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFlfFxckMXv7KUSkiNLLjCEqcRi2XOnFk0PrGWjSnBdqtTG+Ww/GWG68yvs5fwGUNYb6d+xOAcel5C61cC3BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:23:03.283783Z"},"content_sha256":"b9e8eee0a3da073e000632044a702b35dd4b2f888ce0624bcb3a18e2642fd981","schema_version":"1.0","event_id":"sha256:b9e8eee0a3da073e000632044a702b35dd4b2f888ce0624bcb3a18e2642fd981"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/bundle.json","state_url":"https://pith.science/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/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":"2026-07-31T23:23:03Z","links":{"resolver":"https://pith.science/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY","bundle":"https://pith.science/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/bundle.json","state":"https://pith.science/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCF5GBVQKQZTCJO6FDHH3JIRXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BCF5GBVQKQZTCJO6FDHH3JIRXY","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":"77633870aced64fdc303a4bef1b2658b09e7d9a1c2d8166a499747f3558cf0f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:31:34Z","title_canon_sha256":"00beedab5d959f1b13a0d41f09d192919de06519631de5bb87ee94ca716e4742"},"schema_version":"1.0","source":{"id":"2406.08527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08527","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08527v2","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08527","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"BCF5GBVQKQZT","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"BCF5GBVQKQZTCJO6","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"BCF5GBVQ","created_at":"2026-07-05T09:36:45Z"}],"graph_snapshots":[{"event_id":"sha256:b9e8eee0a3da073e000632044a702b35dd4b2f888ce0624bcb3a18e2642fd981","target":"graph","created_at":"2026-07-05T09:36:45Z","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/2406.08527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. While these feature engineering techniques are effective, they typically depend on a pre-defined search space and primarily use validation scores for feature selection, thereby missing valuable insights from previous experiments. To address these limitations, we propose a novel tabular learning framework that utilizes large language models (LLMs), termed Optimizing Column feature generator with decision Tree reasoning","authors_text":"Jaehyung Kim, Jaehyun Nam, Jihoon Tack, Jinwoo Shin, Kyuyoung Kim, Seunghyuk Oh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:31:34Z","title":"Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08527","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:ca1f0d9af4dce83b5ac661b7ba3ab389cce82e4409aa1c803345aa3c00e485a1","target":"record","created_at":"2026-07-05T09:36:45Z","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":"77633870aced64fdc303a4bef1b2658b09e7d9a1c2d8166a499747f3558cf0f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:31:34Z","title_canon_sha256":"00beedab5d959f1b13a0d41f09d192919de06519631de5bb87ee94ca716e4742"},"schema_version":"1.0","source":{"id":"2406.08527","kind":"arxiv","version":2}},"canonical_sha256":"088bd306b054333125de28ce7da511be2f60ccbb4c3ac0bf77c15867c2827f33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"088bd306b054333125de28ce7da511be2f60ccbb4c3ac0bf77c15867c2827f33","first_computed_at":"2026-07-05T09:36:45.838923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:45.838923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O38+xsVOEt4cht1glTi+uZY3KFxMHbOW5X6258e4v4+h6/c+fBKRrewl455BnhZ1iLiyZ++DOZnOmO30fX4hCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:45.839403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca1f0d9af4dce83b5ac661b7ba3ab389cce82e4409aa1c803345aa3c00e485a1","sha256:b9e8eee0a3da073e000632044a702b35dd4b2f888ce0624bcb3a18e2642fd981"],"state_sha256":"ee9eced57e0c5ad0dc1269b8b2491e5337678dc4269df8a77be86bb2d62d459d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiKq8xKOFnovPmrSVHwC/CSbhXQVS2F2+GwzGj2nsYZ+IGh4QfN3JVW1GawZBZ+kagsSEdUEz20QHmuGxBiPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:23:03.289937Z","bundle_sha256":"0899c4c809d80070987af02d2a35d54c421c5855612a6e517a14ee6b93141c45"}}