{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SJB4LLNLLAUOANJIXUXYEH3ODP","short_pith_number":"pith:SJB4LLNL","schema_version":"1.0","canonical_sha256":"9243c5adab5828e03528bd2f821f6e1bd0ab1e5347b3a69279baad490bca8eb1","source":{"kind":"arxiv","id":"2411.04324","version":1},"attestation_state":"computed","paper":{"title":"Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carlos Huertas","submitted_at":"2024-11-06T23:54:09Z","abstract_excerpt":"Large Language Models (LLM) have brought numerous of new applications to Machine Learning (ML). In the context of tabular data (TD), recent studies show that TabLLM is a very powerful mechanism for few-shot-learning (FSL) applications, even if gradient boosting decisions trees (GBDT) have historically dominated the TD field. In this work we demonstrate that although LLMs are a viable alternative, the evidence suggests that baselines used to gauge performance can be improved. We replicated public benchmarks and our methodology improves LightGBM by 290%, this is mainly driven by forcing node spl"},"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":"2411.04324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T23:54:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b7d97fb220b925d9ea2882907e76fe4c7e2c46610393a1666406ae896949228","abstract_canon_sha256":"78f9a27de7c48e2298883ace871c14a5bc93ad90fa25eebd0722407f11020142"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:17.558408Z","signature_b64":"CEeXBCVi8VlknqE/oz9t4cHnpK97XxTqfZ1dP3VMjI1TZ+NTz98zA6u/pIsIDqnV7Dz2NxkBry1I8nQAYeUkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9243c5adab5828e03528bd2f821f6e1bd0ab1e5347b3a69279baad490bca8eb1","last_reissued_at":"2026-07-05T09:32:17.557976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:17.557976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carlos Huertas","submitted_at":"2024-11-06T23:54:09Z","abstract_excerpt":"Large Language Models (LLM) have brought numerous of new applications to Machine Learning (ML). In the context of tabular data (TD), recent studies show that TabLLM is a very powerful mechanism for few-shot-learning (FSL) applications, even if gradient boosting decisions trees (GBDT) have historically dominated the TD field. In this work we demonstrate that although LLMs are a viable alternative, the evidence suggests that baselines used to gauge performance can be improved. We replicated public benchmarks and our methodology improves LightGBM by 290%, this is mainly driven by forcing node spl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04324","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/2411.04324/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":"2411.04324","created_at":"2026-07-05T09:32:17.558031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04324v1","created_at":"2026-07-05T09:32:17.558031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04324","created_at":"2026-07-05T09:32:17.558031+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJB4LLNLLAUO","created_at":"2026-07-05T09:32:17.558031+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJB4LLNLLAUOANJI","created_at":"2026-07-05T09:32:17.558031+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJB4LLNL","created_at":"2026-07-05T09:32:17.558031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17113","citing_title":"The Critical Role of Model Selection in Causal Inference: A Comparative Analysis of Classification Models within the InferBERT Framework for Pharmacovigilance","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16791","citing_title":"TabArena: A Living Benchmark for Machine Learning on Tabular Data","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP","json":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP.json","graph_json":"https://pith.science/api/pith-number/SJB4LLNLLAUOANJIXUXYEH3ODP/graph.json","events_json":"https://pith.science/api/pith-number/SJB4LLNLLAUOANJIXUXYEH3ODP/events.json","paper":"https://pith.science/paper/SJB4LLNL"},"agent_actions":{"view_html":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP","download_json":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP.json","view_paper":"https://pith.science/paper/SJB4LLNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04324&json=true","fetch_graph":"https://pith.science/api/pith-number/SJB4LLNLLAUOANJIXUXYEH3ODP/graph.json","fetch_events":"https://pith.science/api/pith-number/SJB4LLNLLAUOANJIXUXYEH3ODP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP/action/storage_attestation","attest_author":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP/action/author_attestation","sign_citation":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP/action/citation_signature","submit_replication":"https://pith.science/pith/SJB4LLNLLAUOANJIXUXYEH3ODP/action/replication_record"}},"created_at":"2026-07-05T09:32:17.558031+00:00","updated_at":"2026-07-05T09:32:17.558031+00:00"}