{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:WXC5VQD4ELUVAKB3WLE3G54R2E","short_pith_number":"pith:WXC5VQD4","schema_version":"1.0","canonical_sha256":"b5c5dac07c22e950283bb2c9b37791d10341c087e509c5f8bbba97d75f345ab8","source":{"kind":"arxiv","id":"1310.5726","version":5},"attestation_state":"computed","paper":{"title":"Correlation and variable importance in random forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Baptiste Gregorutti, Bertrand Michel, Philippe Saint-Pierre","submitted_at":"2013-10-21T20:47:05Z","abstract_excerpt":"This paper is about variable selection with the random forests algorithm in presence of correlated predictors. In high-dimensional regression or classification frameworks, variable selection is a difficult task, that becomes even more challenging in the presence of highly correlated predictors. Firstly we provide a theoretical study of the permutation importance measure for an additive regression model. This allows us to describe how the correlation between predictors impacts the permutation importance. Our results motivate the use of the Recursive Feature Elimination (RFE) algorithm for varia"},"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":"1310.5726","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2013-10-21T20:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"700f9ef631c7a69e9990b43b24794cc43c4dcfea07732ae9516f15a9e1f9b7c2","abstract_canon_sha256":"69697b2f7ec7651ec8c07a0d741d1994c9cc51f01b071f5ae4cd8c47cdc50bcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:01.397375Z","signature_b64":"uIslSLCOOaJlanEerk+0301GJKXfU2+YgTsokkS5XGQd0wbDJdYSVrrfmRS9xpA/kJjiTmXTRgDRCVJkt1CbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5c5dac07c22e950283bb2c9b37791d10341c087e509c5f8bbba97d75f345ab8","last_reissued_at":"2026-05-18T01:17:01.396547Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:01.396547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correlation and variable importance in random forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Baptiste Gregorutti, Bertrand Michel, Philippe Saint-Pierre","submitted_at":"2013-10-21T20:47:05Z","abstract_excerpt":"This paper is about variable selection with the random forests algorithm in presence of correlated predictors. In high-dimensional regression or classification frameworks, variable selection is a difficult task, that becomes even more challenging in the presence of highly correlated predictors. Firstly we provide a theoretical study of the permutation importance measure for an additive regression model. This allows us to describe how the correlation between predictors impacts the permutation importance. Our results motivate the use of the Recursive Feature Elimination (RFE) algorithm for varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1310.5726","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1310.5726","created_at":"2026-05-18T01:17:01.396721+00:00"},{"alias_kind":"arxiv_version","alias_value":"1310.5726v5","created_at":"2026-05-18T01:17:01.396721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1310.5726","created_at":"2026-05-18T01:17:01.396721+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXC5VQD4ELUV","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXC5VQD4ELUVAKB3","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXC5VQD4","created_at":"2026-05-18T12:28:06.772260+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/WXC5VQD4ELUVAKB3WLE3G54R2E","json":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E.json","graph_json":"https://pith.science/api/pith-number/WXC5VQD4ELUVAKB3WLE3G54R2E/graph.json","events_json":"https://pith.science/api/pith-number/WXC5VQD4ELUVAKB3WLE3G54R2E/events.json","paper":"https://pith.science/paper/WXC5VQD4"},"agent_actions":{"view_html":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E","download_json":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E.json","view_paper":"https://pith.science/paper/WXC5VQD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1310.5726&json=true","fetch_graph":"https://pith.science/api/pith-number/WXC5VQD4ELUVAKB3WLE3G54R2E/graph.json","fetch_events":"https://pith.science/api/pith-number/WXC5VQD4ELUVAKB3WLE3G54R2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E/action/storage_attestation","attest_author":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E/action/author_attestation","sign_citation":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E/action/citation_signature","submit_replication":"https://pith.science/pith/WXC5VQD4ELUVAKB3WLE3G54R2E/action/replication_record"}},"created_at":"2026-05-18T01:17:01.396721+00:00","updated_at":"2026-05-18T01:17:01.396721+00:00"}