{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DPP7ED4IKUAE3OKTNFASNPB6BW","short_pith_number":"pith:DPP7ED4I","schema_version":"1.0","canonical_sha256":"1bdff20f8855004db953694126bc3e0da6172648bdf51dad6624b713afbc037d","source":{"kind":"arxiv","id":"2606.10770","version":1},"attestation_state":"computed","paper":{"title":"Correcting Variable Importance Scored by Random Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Donghui Yan, Guancheng Zhou, Haiping Xu, Jason Liu","submitted_at":"2026-06-09T12:25:51Z","abstract_excerpt":"Variable importance produced by Random Forests (RF) is used widely in statistical data analysis, and has played an important role in a variety of tasks such as assisting model interpretation, model selection and diagnosis, and cost-bounded learning etc. However, the calculation of variable importance in RF does not take into account of the correlations among variables, and variables that are correlated to many other variables tend to receive a lower importance index or being completely masked (i.e., with an importance index near zero) by other strongly correlated variables. To prevent influenc"},"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":"2606.10770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-06-09T12:25:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c689175127b2fe873dd2704c1bf105dec580a3efbdc4e90b01b8bcb1891d0a89","abstract_canon_sha256":"82cf4aafaee00121a7d1a4ef0837a5f865bdbaf1b69ccd70fbcaff02d17d8547"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:39.653973Z","signature_b64":"3Zlim1dJvKOxo2yFqFOqToDUBZ+/s/6g67I+whJGkobSdGccdnx9mzar/4VNgWge4oFmasnbFPqoGuedhlCcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bdff20f8855004db953694126bc3e0da6172648bdf51dad6624b713afbc037d","last_reissued_at":"2026-06-10T01:10:39.653089Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:39.653089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correcting Variable Importance Scored by Random Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Donghui Yan, Guancheng Zhou, Haiping Xu, Jason Liu","submitted_at":"2026-06-09T12:25:51Z","abstract_excerpt":"Variable importance produced by Random Forests (RF) is used widely in statistical data analysis, and has played an important role in a variety of tasks such as assisting model interpretation, model selection and diagnosis, and cost-bounded learning etc. However, the calculation of variable importance in RF does not take into account of the correlations among variables, and variables that are correlated to many other variables tend to receive a lower importance index or being completely masked (i.e., with an importance index near zero) by other strongly correlated variables. To prevent influenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10770","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/2606.10770/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":"2606.10770","created_at":"2026-06-10T01:10:39.653222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10770v1","created_at":"2026-06-10T01:10:39.653222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10770","created_at":"2026-06-10T01:10:39.653222+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPP7ED4IKUAE","created_at":"2026-06-10T01:10:39.653222+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPP7ED4IKUAE3OKT","created_at":"2026-06-10T01:10:39.653222+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPP7ED4I","created_at":"2026-06-10T01:10:39.653222+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/DPP7ED4IKUAE3OKTNFASNPB6BW","json":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW.json","graph_json":"https://pith.science/api/pith-number/DPP7ED4IKUAE3OKTNFASNPB6BW/graph.json","events_json":"https://pith.science/api/pith-number/DPP7ED4IKUAE3OKTNFASNPB6BW/events.json","paper":"https://pith.science/paper/DPP7ED4I"},"agent_actions":{"view_html":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW","download_json":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW.json","view_paper":"https://pith.science/paper/DPP7ED4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10770&json=true","fetch_graph":"https://pith.science/api/pith-number/DPP7ED4IKUAE3OKTNFASNPB6BW/graph.json","fetch_events":"https://pith.science/api/pith-number/DPP7ED4IKUAE3OKTNFASNPB6BW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW/action/storage_attestation","attest_author":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW/action/author_attestation","sign_citation":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW/action/citation_signature","submit_replication":"https://pith.science/pith/DPP7ED4IKUAE3OKTNFASNPB6BW/action/replication_record"}},"created_at":"2026-06-10T01:10:39.653222+00:00","updated_at":"2026-06-10T01:10:39.653222+00:00"}