{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:XE7OZLGUEOJF5FTUFR7PXMRHXS","short_pith_number":"pith:XE7OZLGU","schema_version":"1.0","canonical_sha256":"b93eecacd423925e96742c7efbb227bc8d7588026daf51560e3b422fa5307465","source":{"kind":"arxiv","id":"1404.6473","version":2},"attestation_state":"computed","paper":{"title":"Quantifying Uncertainty in Random Forests via Confidence Intervals and Hypothesis Tests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Giles Hooker, Lucas Mentch","submitted_at":"2014-04-25T16:15:59Z","abstract_excerpt":"This work develops formal statistical inference procedures for machine learning ensemble methods. Ensemble methods based on bootstrapping, such as bagging and random forests, have improved the predictive accuracy of individual trees, but fail to provide a framework in which distributional results can be easily determined. Instead of aggregating full bootstrap samples, we consider predicting by averaging over trees built on subsamples of the training set and demonstrate that the resulting estimator takes the form of a U-statistic. As such, predictions for individual feature vectors are asymptot"},"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":"1404.6473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-04-25T16:15:59Z","cross_cats_sorted":["stat.AP","stat.CO","stat.ME"],"title_canon_sha256":"50ec75b05c182dec7160d1bcd543f9a57e384476fcd78c1cb7dbda2f07d981f5","abstract_canon_sha256":"58dd629dc8756127142710ec39a6ae67dda541dc4d0125ac9bd5fb4f6f5301b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:33:32.665868Z","signature_b64":"XVMEoUZO1RZ8MHFlDLokJ2okm9K6ahGhKJyG0G0+JkjHWVlRJt2ledtlKy35lguOKlkZ3eoAvjEfw5np+5uJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b93eecacd423925e96742c7efbb227bc8d7588026daf51560e3b422fa5307465","last_reissued_at":"2026-05-18T01:33:32.665162Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:33:32.665162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Uncertainty in Random Forests via Confidence Intervals and Hypothesis Tests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Giles Hooker, Lucas Mentch","submitted_at":"2014-04-25T16:15:59Z","abstract_excerpt":"This work develops formal statistical inference procedures for machine learning ensemble methods. Ensemble methods based on bootstrapping, such as bagging and random forests, have improved the predictive accuracy of individual trees, but fail to provide a framework in which distributional results can be easily determined. Instead of aggregating full bootstrap samples, we consider predicting by averaging over trees built on subsamples of the training set and demonstrate that the resulting estimator takes the form of a U-statistic. As such, predictions for individual feature vectors are asymptot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.6473","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":""},"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":"1404.6473","created_at":"2026-05-18T01:33:32.665274+00:00"},{"alias_kind":"arxiv_version","alias_value":"1404.6473v2","created_at":"2026-05-18T01:33:32.665274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.6473","created_at":"2026-05-18T01:33:32.665274+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE7OZLGUEOJF","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE7OZLGUEOJF5FTU","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE7OZLGU","created_at":"2026-05-18T12:28:57.508820+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/XE7OZLGUEOJF5FTUFR7PXMRHXS","json":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS.json","graph_json":"https://pith.science/api/pith-number/XE7OZLGUEOJF5FTUFR7PXMRHXS/graph.json","events_json":"https://pith.science/api/pith-number/XE7OZLGUEOJF5FTUFR7PXMRHXS/events.json","paper":"https://pith.science/paper/XE7OZLGU"},"agent_actions":{"view_html":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS","download_json":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS.json","view_paper":"https://pith.science/paper/XE7OZLGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1404.6473&json=true","fetch_graph":"https://pith.science/api/pith-number/XE7OZLGUEOJF5FTUFR7PXMRHXS/graph.json","fetch_events":"https://pith.science/api/pith-number/XE7OZLGUEOJF5FTUFR7PXMRHXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS/action/storage_attestation","attest_author":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS/action/author_attestation","sign_citation":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS/action/citation_signature","submit_replication":"https://pith.science/pith/XE7OZLGUEOJF5FTUFR7PXMRHXS/action/replication_record"}},"created_at":"2026-05-18T01:33:32.665274+00:00","updated_at":"2026-05-18T01:33:32.665274+00:00"}