{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FYRJA6EXCAELWSKSNNUP2HCJ53","short_pith_number":"pith:FYRJA6EX","schema_version":"1.0","canonical_sha256":"2e229078971008bb49526b68fd1c49eece0c6b67b33d2c2ae32c48bde616185f","source":{"kind":"arxiv","id":"2501.16247","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Decision Tree Construction via Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andr\\'es Abeliuk, Felipe Urrutia, Lucas Carrasco","submitted_at":"2025-01-27T17:48:48Z","abstract_excerpt":"This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index. In contrast, we propose a method that uses the pre-trained knowledge embedded in LLMs to build decision trees without requiring training data. Our approach leverages LLMs to perform operations essential for decision tree construction, including "},"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":"2501.16247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T17:48:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"58801456e314e3572870f9bde9ff144a325cc8be4dcbb4851ebfad2a1a868ad3","abstract_canon_sha256":"0da32c801f306ea58557e7e7b806b483794e1ef870f257f99e84d436b98ae209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:57.375222Z","signature_b64":"4P0PtV0Y7mmWWu7jrxCoKsiDBjEdADaiq+EVJ7FUOKrKjyUkdN+EXVvHaAv5EPi1oUrEu9patHkAHOtNZB0xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e229078971008bb49526b68fd1c49eece0c6b67b33d2c2ae32c48bde616185f","last_reissued_at":"2026-07-05T10:05:57.374696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:57.374696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Decision Tree Construction via Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andr\\'es Abeliuk, Felipe Urrutia, Lucas Carrasco","submitted_at":"2025-01-27T17:48:48Z","abstract_excerpt":"This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index. In contrast, we propose a method that uses the pre-trained knowledge embedded in LLMs to build decision trees without requiring training data. Our approach leverages LLMs to perform operations essential for decision tree construction, including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16247","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/2501.16247/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":"2501.16247","created_at":"2026-07-05T10:05:57.374756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16247v1","created_at":"2026-07-05T10:05:57.374756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16247","created_at":"2026-07-05T10:05:57.374756+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYRJA6EXCAEL","created_at":"2026-07-05T10:05:57.374756+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYRJA6EXCAELWSKS","created_at":"2026-07-05T10:05:57.374756+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYRJA6EX","created_at":"2026-07-05T10:05:57.374756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09418","citing_title":"Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53","json":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53.json","graph_json":"https://pith.science/api/pith-number/FYRJA6EXCAELWSKSNNUP2HCJ53/graph.json","events_json":"https://pith.science/api/pith-number/FYRJA6EXCAELWSKSNNUP2HCJ53/events.json","paper":"https://pith.science/paper/FYRJA6EX"},"agent_actions":{"view_html":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53","download_json":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53.json","view_paper":"https://pith.science/paper/FYRJA6EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16247&json=true","fetch_graph":"https://pith.science/api/pith-number/FYRJA6EXCAELWSKSNNUP2HCJ53/graph.json","fetch_events":"https://pith.science/api/pith-number/FYRJA6EXCAELWSKSNNUP2HCJ53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53/action/storage_attestation","attest_author":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53/action/author_attestation","sign_citation":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53/action/citation_signature","submit_replication":"https://pith.science/pith/FYRJA6EXCAELWSKSNNUP2HCJ53/action/replication_record"}},"created_at":"2026-07-05T10:05:57.374756+00:00","updated_at":"2026-07-05T10:05:57.374756+00:00"}