{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXSIITGNABOBMUJSYN53PUB7DW","short_pith_number":"pith:MXSIITGN","schema_version":"1.0","canonical_sha256":"65e4844ccd005c165132c37bb7d03f1dae7b5c50bd48ca58bea2856d231aa076","source":{"kind":"arxiv","id":"2505.06852","version":2},"attestation_state":"computed","paper":{"title":"Improving Random Forests by Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel F. Schmidt, Mario Boley, Phuc Luong, Ziyi Liu","submitted_at":"2025-05-11T05:39:08Z","abstract_excerpt":"Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it effective across diverse application domains. However, the piecewise constant nature of random forest predictions means each partition is predicted independently, ignoring potential smoothness in the underlying function. Particularly in the small data regime, this lack of information sharing across the input space can lead to suboptimal performance. In this work, we propose a kernel-based smoothing mechanism that enhances random forests by introduci"},"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":"2505.06852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T05:39:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aba46190dfacd58ac4aa3dc7a2d8143c42be76f6d640bd96b2fc1924baa9b6c1","abstract_canon_sha256":"7221e185aa3c1255977eea758623b629527158166efd5c382aeba2f1c23aabba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:09.258602Z","signature_b64":"Q+Kn8jOZ13LsYmP9P+S30b9bYGVLaTQROtlUIURWTW9sh7WaRap+xTssovWJtmK1+VIOUlhG/7eteu5evKtqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e4844ccd005c165132c37bb7d03f1dae7b5c50bd48ca58bea2856d231aa076","last_reissued_at":"2026-05-20T00:04:09.257985Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:09.257985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Random Forests by Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel F. Schmidt, Mario Boley, Phuc Luong, Ziyi Liu","submitted_at":"2025-05-11T05:39:08Z","abstract_excerpt":"Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it effective across diverse application domains. However, the piecewise constant nature of random forest predictions means each partition is predicted independently, ignoring potential smoothness in the underlying function. Particularly in the small data regime, this lack of information sharing across the input space can lead to suboptimal performance. In this work, we propose a kernel-based smoothing mechanism that enhances random forests by introduci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06852","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.06852/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":"2505.06852","created_at":"2026-05-20T00:04:09.258069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06852v2","created_at":"2026-05-20T00:04:09.258069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06852","created_at":"2026-05-20T00:04:09.258069+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXSIITGNABOB","created_at":"2026-05-20T00:04:09.258069+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXSIITGNABOBMUJS","created_at":"2026-05-20T00:04:09.258069+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXSIITGN","created_at":"2026-05-20T00:04:09.258069+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/MXSIITGNABOBMUJSYN53PUB7DW","json":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW.json","graph_json":"https://pith.science/api/pith-number/MXSIITGNABOBMUJSYN53PUB7DW/graph.json","events_json":"https://pith.science/api/pith-number/MXSIITGNABOBMUJSYN53PUB7DW/events.json","paper":"https://pith.science/paper/MXSIITGN"},"agent_actions":{"view_html":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW","download_json":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW.json","view_paper":"https://pith.science/paper/MXSIITGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06852&json=true","fetch_graph":"https://pith.science/api/pith-number/MXSIITGNABOBMUJSYN53PUB7DW/graph.json","fetch_events":"https://pith.science/api/pith-number/MXSIITGNABOBMUJSYN53PUB7DW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW/action/storage_attestation","attest_author":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW/action/author_attestation","sign_citation":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW/action/citation_signature","submit_replication":"https://pith.science/pith/MXSIITGNABOBMUJSYN53PUB7DW/action/replication_record"}},"created_at":"2026-05-20T00:04:09.258069+00:00","updated_at":"2026-05-20T00:04:09.258069+00:00"}