{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XUMBFY2EGS34ZI2LH6QT3Z3TWI","short_pith_number":"pith:XUMBFY2E","schema_version":"1.0","canonical_sha256":"bd1812e34434b7cca34b3fa13de773b2116a66fe1a197b761b06724de6c6d343","source":{"kind":"arxiv","id":"2404.01832","version":1},"attestation_state":"computed","paper":{"title":"When does Subagging Work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bas J.M. Werker, Christos Revelas, Otilia Boldea","submitted_at":"2024-04-02T10:44:55Z","abstract_excerpt":"We study the effectiveness of subagging, or subsample aggregating, on regression trees, a popular non-parametric method in machine learning. First, we give sufficient conditions for pointwise consistency of trees. We formalize that (i) the bias depends on the diameter of cells, hence trees with few splits tend to be biased, and (ii) the variance depends on the number of observations in cells, hence trees with many splits tend to have large variance. While these statements for bias and variance are known to hold globally in the covariate space, we show that, under some constraints, they are als"},"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":"2404.01832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-02T10:44:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b98fd21102a2a9d6363c5da2ac1f6cfc6b403ae22a93edfc8f84ced81ca08b7","abstract_canon_sha256":"428d4cdb90d40e3b4dcd79a32fdec6d0d9b0b4a541f4f41fef81c5517a39a3ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:32.284713Z","signature_b64":"Ed+TaROozUIkd1SEVgpPHvOzSXLcC8p05VpshvcuAWybttokcETnZoK1FvC0uKUkg8ZlomI1DFFevL4GvoYJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1812e34434b7cca34b3fa13de773b2116a66fe1a197b761b06724de6c6d343","last_reissued_at":"2026-07-05T08:03:32.284239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:32.284239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When does Subagging Work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bas J.M. Werker, Christos Revelas, Otilia Boldea","submitted_at":"2024-04-02T10:44:55Z","abstract_excerpt":"We study the effectiveness of subagging, or subsample aggregating, on regression trees, a popular non-parametric method in machine learning. First, we give sufficient conditions for pointwise consistency of trees. We formalize that (i) the bias depends on the diameter of cells, hence trees with few splits tend to be biased, and (ii) the variance depends on the number of observations in cells, hence trees with many splits tend to have large variance. While these statements for bias and variance are known to hold globally in the covariate space, we show that, under some constraints, they are als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01832","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/2404.01832/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":"2404.01832","created_at":"2026-07-05T08:03:32.284300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01832v1","created_at":"2026-07-05T08:03:32.284300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01832","created_at":"2026-07-05T08:03:32.284300+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUMBFY2EGS34","created_at":"2026-07-05T08:03:32.284300+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUMBFY2EGS34ZI2L","created_at":"2026-07-05T08:03:32.284300+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUMBFY2E","created_at":"2026-07-05T08:03:32.284300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12860","citing_title":"When do Random Forests work?","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI","json":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI.json","graph_json":"https://pith.science/api/pith-number/XUMBFY2EGS34ZI2LH6QT3Z3TWI/graph.json","events_json":"https://pith.science/api/pith-number/XUMBFY2EGS34ZI2LH6QT3Z3TWI/events.json","paper":"https://pith.science/paper/XUMBFY2E"},"agent_actions":{"view_html":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI","download_json":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI.json","view_paper":"https://pith.science/paper/XUMBFY2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01832&json=true","fetch_graph":"https://pith.science/api/pith-number/XUMBFY2EGS34ZI2LH6QT3Z3TWI/graph.json","fetch_events":"https://pith.science/api/pith-number/XUMBFY2EGS34ZI2LH6QT3Z3TWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI/action/storage_attestation","attest_author":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI/action/author_attestation","sign_citation":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI/action/citation_signature","submit_replication":"https://pith.science/pith/XUMBFY2EGS34ZI2LH6QT3Z3TWI/action/replication_record"}},"created_at":"2026-07-05T08:03:32.284300+00:00","updated_at":"2026-07-05T08:03:32.284300+00:00"}