{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HIYYXDQAHE6ION73MLXQBPG2GE","short_pith_number":"pith:HIYYXDQA","schema_version":"1.0","canonical_sha256":"3a318b8e00393c8737fb62ef00bcda313344e4634e183541aae44b58563e7828","source":{"kind":"arxiv","id":"2405.15911","version":2},"attestation_state":"computed","paper":{"title":"Learning accurate and interpretable tree-based models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dravyansh Sharma, Maria-Florina Balcan","submitted_at":"2024-05-24T20:10:10Z","abstract_excerpt":"Decision trees and their ensembles are popular in machine learning as easy-to-understand models. Several techniques have been proposed in the literature for learning tree-based classifiers, with different techniques working well for data from different domains. In this work, we develop approaches to design tree-based learning algorithms given repeated access to data from the same domain. We study multiple formulations covering different aspects and popular techniques for learning decision tree based approaches. We propose novel parameterized classes of node splitting criteria in top-down algor"},"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":"2405.15911","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T20:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"4fd90230b70b53470a4283bbba77dba95fc81bbe3972a4037614f8c5be0f30e6","abstract_canon_sha256":"c161226d15ac9c44e2051e1a61bff28eede6c1d6d414f631f438b9b9e8e95312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:37.370518Z","signature_b64":"cPaNAYi1UMk5fvTRIszOqLLeJdxKDQXu/2uNtY+ACHokmDWmrkj96vDOmMN7mTWuBH4z/zkvtVicqNxoYE09Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a318b8e00393c8737fb62ef00bcda313344e4634e183541aae44b58563e7828","last_reissued_at":"2026-07-05T11:04:37.370028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:37.370028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning accurate and interpretable tree-based models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dravyansh Sharma, Maria-Florina Balcan","submitted_at":"2024-05-24T20:10:10Z","abstract_excerpt":"Decision trees and their ensembles are popular in machine learning as easy-to-understand models. Several techniques have been proposed in the literature for learning tree-based classifiers, with different techniques working well for data from different domains. In this work, we develop approaches to design tree-based learning algorithms given repeated access to data from the same domain. We study multiple formulations covering different aspects and popular techniques for learning decision tree based approaches. We propose novel parameterized classes of node splitting criteria in top-down algor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15911","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/2405.15911/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":"2405.15911","created_at":"2026-07-05T11:04:37.370086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15911v2","created_at":"2026-07-05T11:04:37.370086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15911","created_at":"2026-07-05T11:04:37.370086+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIYYXDQAHE6I","created_at":"2026-07-05T11:04:37.370086+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIYYXDQAHE6ION73","created_at":"2026-07-05T11:04:37.370086+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIYYXDQA","created_at":"2026-07-05T11:04:37.370086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05585","citing_title":"An inverse mixed-integer optimization framework for learning interpretable models of expert decision making","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE","json":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE.json","graph_json":"https://pith.science/api/pith-number/HIYYXDQAHE6ION73MLXQBPG2GE/graph.json","events_json":"https://pith.science/api/pith-number/HIYYXDQAHE6ION73MLXQBPG2GE/events.json","paper":"https://pith.science/paper/HIYYXDQA"},"agent_actions":{"view_html":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE","download_json":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE.json","view_paper":"https://pith.science/paper/HIYYXDQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15911&json=true","fetch_graph":"https://pith.science/api/pith-number/HIYYXDQAHE6ION73MLXQBPG2GE/graph.json","fetch_events":"https://pith.science/api/pith-number/HIYYXDQAHE6ION73MLXQBPG2GE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE/action/storage_attestation","attest_author":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE/action/author_attestation","sign_citation":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE/action/citation_signature","submit_replication":"https://pith.science/pith/HIYYXDQAHE6ION73MLXQBPG2GE/action/replication_record"}},"created_at":"2026-07-05T11:04:37.370086+00:00","updated_at":"2026-07-05T11:04:37.370086+00:00"}