{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:RJ2C42OZSW37PZMUIO5BNVXQP3","short_pith_number":"pith:RJ2C42OZ","schema_version":"1.0","canonical_sha256":"8a742e69d995b7f7e59443ba16d6f07ef3a8344b0f43c5b77e8c72de46fdafa3","source":{"kind":"arxiv","id":"1209.6425","version":3},"attestation_state":"computed","paper":{"title":"Gene selection with guided regularized random forest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"George Runger, Houtao Deng","submitted_at":"2012-09-28T04:59:33Z","abstract_excerpt":"The regularized random forest (RRF) was recently proposed for feature selection by building only one ensemble. In RRF the features are evaluated on a part of the training data at each tree node. We derive an upper bound for the number of distinct Gini information gain values in a node, and show that many features can share the same information gain at a node with a small number of instances and a large number of features. Therefore, in a node with a small number of instances, RRF is likely to select a feature not strongly relevant. Here an enhanced RRF, referred to as the guided RRF (GRRF), is"},"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":"1209.6425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-28T04:59:33Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"5fe4800e269cf0ba16cc34fe8d1ef017b4f10c6a3b44bb930d33046ca5147751","abstract_canon_sha256":"89500e1545ce9a8eb0fb73362da1b0386ba3b37b9e62d3a91a79923639426dbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:20:32.659670Z","signature_b64":"S1iN37bsWMt7IzAmZFj3AFnPaXiP9gCC3J7QVeBM42/dbsxCMjicDeld2MdQpqB//cMAC4ff96k6/4WKBWn8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a742e69d995b7f7e59443ba16d6f07ef3a8344b0f43c5b77e8c72de46fdafa3","last_reissued_at":"2026-05-18T03:20:32.658712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:20:32.658712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gene selection with guided regularized random forest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"George Runger, Houtao Deng","submitted_at":"2012-09-28T04:59:33Z","abstract_excerpt":"The regularized random forest (RRF) was recently proposed for feature selection by building only one ensemble. In RRF the features are evaluated on a part of the training data at each tree node. We derive an upper bound for the number of distinct Gini information gain values in a node, and show that many features can share the same information gain at a node with a small number of instances and a large number of features. Therefore, in a node with a small number of instances, RRF is likely to select a feature not strongly relevant. Here an enhanced RRF, referred to as the guided RRF (GRRF), is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1209.6425","kind":"arxiv","version":3},"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":"1209.6425","created_at":"2026-05-18T03:20:32.658875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1209.6425v3","created_at":"2026-05-18T03:20:32.658875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1209.6425","created_at":"2026-05-18T03:20:32.658875+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ2C42OZSW37","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ2C42OZSW37PZMU","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ2C42OZ","created_at":"2026-05-18T12:27:20.899486+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/RJ2C42OZSW37PZMUIO5BNVXQP3","json":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3.json","graph_json":"https://pith.science/api/pith-number/RJ2C42OZSW37PZMUIO5BNVXQP3/graph.json","events_json":"https://pith.science/api/pith-number/RJ2C42OZSW37PZMUIO5BNVXQP3/events.json","paper":"https://pith.science/paper/RJ2C42OZ"},"agent_actions":{"view_html":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3","download_json":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3.json","view_paper":"https://pith.science/paper/RJ2C42OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1209.6425&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ2C42OZSW37PZMUIO5BNVXQP3/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ2C42OZSW37PZMUIO5BNVXQP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3/action/storage_attestation","attest_author":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3/action/author_attestation","sign_citation":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3/action/citation_signature","submit_replication":"https://pith.science/pith/RJ2C42OZSW37PZMUIO5BNVXQP3/action/replication_record"}},"created_at":"2026-05-18T03:20:32.658875+00:00","updated_at":"2026-05-18T03:20:32.658875+00:00"}