{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4BNGPOHEMNHVTMCEIOED3RCO67","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"053920ab7a72328bfa6900eef2499579d9e541286d3cbd61c7900b68b19c5f27","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-17T02:45:32Z","title_canon_sha256":"f1236513c74f52c4936afc3fbf2fea65f2fa9668cb2284018944827508fcc5ab"},"schema_version":"1.0","source":{"id":"2008.07063","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07063","created_at":"2026-07-05T09:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07063v5","created_at":"2026-07-05T09:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07063","created_at":"2026-07-05T09:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"4BNGPOHEMNHV","created_at":"2026-07-05T09:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"4BNGPOHEMNHVTMCE","created_at":"2026-07-05T09:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"4BNGPOHE","created_at":"2026-07-05T09:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:ae01b9e8711f12fa6c3fb2a9abd7e2c1a83308815e8e8d4502c6ec3df37ed183","target":"graph","created_at":"2026-07-05T09:12:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.07063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is notoriously difficult to build a bad Random Forest (RF). Concurrently, RF blatantly overfits in-sample without any apparent consequence out-of-sample. Standard arguments, like the classic bias-variance trade-off or double descent, cannot rationalize this paradox. I propose a new explanation: bootstrap aggregation and model perturbation as implemented by RF automatically prune a latent \"true\" tree. More generally, randomized ensembles of greedily optimized learners implicitly perform optimal early stopping out-of-sample. So there is no need to tune the stopping point. By construction, nov","authors_text":"Philippe Goulet Coulombe","cross_cats":["cs.LG","econ.EM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-17T02:45:32Z","title":"To Bag is to Prune"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07063","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:06627096e34d1749b7a35f0d7bd2057675caa4bae78773fb32e1c15f25e84969","target":"record","created_at":"2026-07-05T09:12:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"053920ab7a72328bfa6900eef2499579d9e541286d3cbd61c7900b68b19c5f27","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-17T02:45:32Z","title_canon_sha256":"f1236513c74f52c4936afc3fbf2fea65f2fa9668cb2284018944827508fcc5ab"},"schema_version":"1.0","source":{"id":"2008.07063","kind":"arxiv","version":5}},"canonical_sha256":"e05a67b8e4634f59b04443883dc44ef7d89eeeee0d55003187bf421bcc40c422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e05a67b8e4634f59b04443883dc44ef7d89eeeee0d55003187bf421bcc40c422","first_computed_at":"2026-07-05T09:12:51.013301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:51.013301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"++qW3XsVcw0gv9rOFAZiFruYR7XulbfnCZ6wyXXPC3y5AJHHdg0A1lMvvrSdcXIIbkeCa3Aok5qJPcV9o7DPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:51.013650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.07063","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06627096e34d1749b7a35f0d7bd2057675caa4bae78773fb32e1c15f25e84969","sha256:ae01b9e8711f12fa6c3fb2a9abd7e2c1a83308815e8e8d4502c6ec3df37ed183"],"state_sha256":"7b5990c90b8df4811d90de919abc2c02315fea3be05492d196d55e42dd920be6"}