{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHQNTTMZS2ELYTYYR6ZNXUMF4A","short_pith_number":"pith:OHQNTTMZ","schema_version":"1.0","canonical_sha256":"71e0d9cd999688bc4f188fb2dbd185e01b134e29035c655edde0b9cb77b09107","source":{"kind":"arxiv","id":"2405.20622","version":2},"attestation_state":"computed","paper":{"title":"Superfast Selection for Decision Tree Algorithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gopal Gupta, Huaduo Wang","submitted_at":"2024-05-31T05:18:05Z","abstract_excerpt":"We present a novel and systematic method, called Superfast Selection, for selecting the \"optimal split\" for decision tree and feature selection algorithms over tabular data. The method speeds up split selection on a single feature by lowering the time complexity, from O(MN) (using the standard selection methods) to O(M), where M represents the number of input examples and N the number of unique values. Additionally, the need for pre-encoding, such as one-hot or integer encoding, for feature value heterogeneity is eliminated. To demonstrate the efficiency of Superfast Selection, we empower the "},"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":"2405.20622","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T05:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"a5efc5e172e532cebf658eba0e64e2fbea9971e7a6318eda4a794d0d26a96c0f","abstract_canon_sha256":"ca4d7ec5dcc8f1a8798475c54bfee2d3d6d293c4a66dfe3dbf704331910b0d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:09.373067Z","signature_b64":"oB0sT6VBT270QUmC3vBTWFvbUq93qy2t41WD38vmi39B0N9DPWOrx92YiCWgB5WDcm53l88jMbTRbYf1+84cBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71e0d9cd999688bc4f188fb2dbd185e01b134e29035c655edde0b9cb77b09107","last_reissued_at":"2026-07-05T08:27:09.372591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:09.372591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Superfast Selection for Decision Tree Algorithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gopal Gupta, Huaduo Wang","submitted_at":"2024-05-31T05:18:05Z","abstract_excerpt":"We present a novel and systematic method, called Superfast Selection, for selecting the \"optimal split\" for decision tree and feature selection algorithms over tabular data. The method speeds up split selection on a single feature by lowering the time complexity, from O(MN) (using the standard selection methods) to O(M), where M represents the number of input examples and N the number of unique values. Additionally, the need for pre-encoding, such as one-hot or integer encoding, for feature value heterogeneity is eliminated. To demonstrate the efficiency of Superfast Selection, we empower the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20622","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/2405.20622/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":"2405.20622","created_at":"2026-07-05T08:27:09.372647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20622v2","created_at":"2026-07-05T08:27:09.372647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20622","created_at":"2026-07-05T08:27:09.372647+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHQNTTMZS2EL","created_at":"2026-07-05T08:27:09.372647+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHQNTTMZS2ELYTYY","created_at":"2026-07-05T08:27:09.372647+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHQNTTMZ","created_at":"2026-07-05T08:27:09.372647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A","json":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A.json","graph_json":"https://pith.science/api/pith-number/OHQNTTMZS2ELYTYYR6ZNXUMF4A/graph.json","events_json":"https://pith.science/api/pith-number/OHQNTTMZS2ELYTYYR6ZNXUMF4A/events.json","paper":"https://pith.science/paper/OHQNTTMZ"},"agent_actions":{"view_html":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A","download_json":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A.json","view_paper":"https://pith.science/paper/OHQNTTMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20622&json=true","fetch_graph":"https://pith.science/api/pith-number/OHQNTTMZS2ELYTYYR6ZNXUMF4A/graph.json","fetch_events":"https://pith.science/api/pith-number/OHQNTTMZS2ELYTYYR6ZNXUMF4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A/action/storage_attestation","attest_author":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A/action/author_attestation","sign_citation":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A/action/citation_signature","submit_replication":"https://pith.science/pith/OHQNTTMZS2ELYTYYR6ZNXUMF4A/action/replication_record"}},"created_at":"2026-07-05T08:27:09.372647+00:00","updated_at":"2026-07-05T08:27:09.372647+00:00"}