{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:UAKYSZHWAMU5MOSJIMIORO77BS","short_pith_number":"pith:UAKYSZHW","schema_version":"1.0","canonical_sha256":"a0158964f60329d63a494310e8bbff0c8c185ac6fa5fe43bfca7aa1467e9ac68","source":{"kind":"arxiv","id":"1503.06388","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Concentration of Regression Trees, with Application to Random Forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Guenther Walther, Stefan Wager","submitted_at":"2015-03-22T06:07:14Z","abstract_excerpt":"We study the convergence of the predictive surface of regression trees and forests. To support our analysis we introduce a notion of adaptive concentration for regression trees. This approach breaks tree training into a model selection phase in which we pick the tree splits, followed by a model fitting phase where we find the best regression model consistent with these splits. We then show that the fitted regression tree concentrates around the optimal predictor with the same splits: as d and n get large, the discrepancy is with high probability bounded on the order of sqrt(log(d) log(n)/k) un"},"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":"1503.06388","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2015-03-22T06:07:14Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"9b98df99ceeaddaa620d4c168042943261c202d1ad5c806502753e5da5c8b406","abstract_canon_sha256":"14ca68c6c8dedfddc39b3b4f50682a49e0af86d0b547ea408886fe44dbd58abd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:58.778527Z","signature_b64":"/5G64LGBrzhQmjk3ytf+TwrBCpc6tLvhCg4wED1Wvh1VGLBMD/QWAzEirj14N/Vy8yqtvUv0NsjT+R1oshU5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0158964f60329d63a494310e8bbff0c8c185ac6fa5fe43bfca7aa1467e9ac68","last_reissued_at":"2026-05-18T01:15:58.778008Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:58.778008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Concentration of Regression Trees, with Application to Random Forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Guenther Walther, Stefan Wager","submitted_at":"2015-03-22T06:07:14Z","abstract_excerpt":"We study the convergence of the predictive surface of regression trees and forests. To support our analysis we introduce a notion of adaptive concentration for regression trees. This approach breaks tree training into a model selection phase in which we pick the tree splits, followed by a model fitting phase where we find the best regression model consistent with these splits. We then show that the fitted regression tree concentrates around the optimal predictor with the same splits: as d and n get large, the discrepancy is with high probability bounded on the order of sqrt(log(d) log(n)/k) un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.06388","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":"1503.06388","created_at":"2026-05-18T01:15:58.778087+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.06388v3","created_at":"2026-05-18T01:15:58.778087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.06388","created_at":"2026-05-18T01:15:58.778087+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAKYSZHWAMU5","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAKYSZHWAMU5MOSJ","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAKYSZHW","created_at":"2026-05-18T12:29:44.643036+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/UAKYSZHWAMU5MOSJIMIORO77BS","json":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS.json","graph_json":"https://pith.science/api/pith-number/UAKYSZHWAMU5MOSJIMIORO77BS/graph.json","events_json":"https://pith.science/api/pith-number/UAKYSZHWAMU5MOSJIMIORO77BS/events.json","paper":"https://pith.science/paper/UAKYSZHW"},"agent_actions":{"view_html":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS","download_json":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS.json","view_paper":"https://pith.science/paper/UAKYSZHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.06388&json=true","fetch_graph":"https://pith.science/api/pith-number/UAKYSZHWAMU5MOSJIMIORO77BS/graph.json","fetch_events":"https://pith.science/api/pith-number/UAKYSZHWAMU5MOSJIMIORO77BS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS/action/storage_attestation","attest_author":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS/action/author_attestation","sign_citation":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS/action/citation_signature","submit_replication":"https://pith.science/pith/UAKYSZHWAMU5MOSJIMIORO77BS/action/replication_record"}},"created_at":"2026-05-18T01:15:58.778087+00:00","updated_at":"2026-05-18T01:15:58.778087+00:00"}