{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NHM4EATMZQS753NYSLG3Q4WCIR","short_pith_number":"pith:NHM4EATM","schema_version":"1.0","canonical_sha256":"69d9c2026ccc25feedb892cdb872c2446bad1bd769ea1f892dc3d28e7b017b25","source":{"kind":"arxiv","id":"1706.09865","version":2},"attestation_state":"computed","paper":{"title":"Generalising Random Forest Parameter Optimisation to Include Stability and Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Angelo Cardoso, Benjamin Paul Chamberlain, C.H. Bryan Liu, Duncan A. Little","submitted_at":"2017-06-29T17:23:44Z","abstract_excerpt":"Random forests are among the most popular classification and regression methods used in industrial applications. To be effective, the parameters of random forests must be carefully tuned. This is usually done by choosing values that minimize the prediction error on a held out dataset. We argue that error reduction is only one of several metrics that must be considered when optimizing random forest parameters for commercial applications. We propose a novel metric that captures the stability of random forests predictions, which we argue is key for scenarios that require successive predictions. W"},"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":"1706.09865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-29T17:23:44Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"b3dd8fe040c4ff23646fa5855a4bb8c459717274f415065e392fd7f2ae0db9a8","abstract_canon_sha256":"70fae1aac1619b0d4ed986ad5b1bb889debc710269eed6f2fe3ee264ba2966bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:58.170892Z","signature_b64":"kpY3eBmSlvxYSk/jxk51zpNCdJ2gSeWfXKSd/6MhteVfV4wOrYRwynTSw/Ub5cuFuV10F2XrmF7luuM/z91tAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d9c2026ccc25feedb892cdb872c2446bad1bd769ea1f892dc3d28e7b017b25","last_reissued_at":"2026-05-18T00:11:58.170365Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:58.170365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalising Random Forest Parameter Optimisation to Include Stability and Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Angelo Cardoso, Benjamin Paul Chamberlain, C.H. Bryan Liu, Duncan A. Little","submitted_at":"2017-06-29T17:23:44Z","abstract_excerpt":"Random forests are among the most popular classification and regression methods used in industrial applications. To be effective, the parameters of random forests must be carefully tuned. This is usually done by choosing values that minimize the prediction error on a held out dataset. We argue that error reduction is only one of several metrics that must be considered when optimizing random forest parameters for commercial applications. We propose a novel metric that captures the stability of random forests predictions, which we argue is key for scenarios that require successive predictions. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09865","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":"1706.09865","created_at":"2026-05-18T00:11:58.170446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.09865v2","created_at":"2026-05-18T00:11:58.170446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09865","created_at":"2026-05-18T00:11:58.170446+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHM4EATMZQS7","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHM4EATMZQS753NY","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHM4EATM","created_at":"2026-05-18T12:31:31.346846+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/NHM4EATMZQS753NYSLG3Q4WCIR","json":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR.json","graph_json":"https://pith.science/api/pith-number/NHM4EATMZQS753NYSLG3Q4WCIR/graph.json","events_json":"https://pith.science/api/pith-number/NHM4EATMZQS753NYSLG3Q4WCIR/events.json","paper":"https://pith.science/paper/NHM4EATM"},"agent_actions":{"view_html":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR","download_json":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR.json","view_paper":"https://pith.science/paper/NHM4EATM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.09865&json=true","fetch_graph":"https://pith.science/api/pith-number/NHM4EATMZQS753NYSLG3Q4WCIR/graph.json","fetch_events":"https://pith.science/api/pith-number/NHM4EATMZQS753NYSLG3Q4WCIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR/action/storage_attestation","attest_author":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR/action/author_attestation","sign_citation":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR/action/citation_signature","submit_replication":"https://pith.science/pith/NHM4EATMZQS753NYSLG3Q4WCIR/action/replication_record"}},"created_at":"2026-05-18T00:11:58.170446+00:00","updated_at":"2026-05-18T00:11:58.170446+00:00"}