{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BBKERH6FSJSCFI4P34HV6O76HO","short_pith_number":"pith:BBKERH6F","schema_version":"1.0","canonical_sha256":"0854489fc5926422a38fdf0f5f3bfe3bb750e1a7144dece0d41d4bdcbb6f49cd","source":{"kind":"arxiv","id":"2009.05567","version":2},"attestation_state":"computed","paper":{"title":"Machine Unlearning for Random Forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Lowd, Jonathan Brophy","submitted_at":"2020-09-11T17:53:20Z","abstract_excerpt":"Responding to user data deletion requests, removing noisy examples, or deleting corrupted training data are just a few reasons for wanting to delete instances from a machine learning (ML) model. However, efficiently removing this data from an ML model is generally difficult. In this paper, we introduce data removal-enabled (DaRE) forests, a variant of random forests that enables the removal of training data with minimal retraining. Model updates for each DaRE tree in the forest are exact, meaning that removing instances from a DaRE model yields exactly the same model as retraining from scratch"},"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":"2009.05567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-11T17:53:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8979a338cc1d574b430678bc2f659d492ccde912711fd956e212810d8f9d4e8b","abstract_canon_sha256":"a418b24ecad686cfa261f801fbd79b2952850b39ae384f31a51c61e744353862"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:33.945270Z","signature_b64":"i3tyfxZRdsXe4QxEJmMlb2OWdue1efkBcRMLl2TMv8XkffFWmlhH27FUMat8vw9uzFPj+t+UukgO/oOJfmsAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0854489fc5926422a38fdf0f5f3bfe3bb750e1a7144dece0d41d4bdcbb6f49cd","last_reissued_at":"2026-07-05T02:48:33.944843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:33.944843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Unlearning for Random Forests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Lowd, Jonathan Brophy","submitted_at":"2020-09-11T17:53:20Z","abstract_excerpt":"Responding to user data deletion requests, removing noisy examples, or deleting corrupted training data are just a few reasons for wanting to delete instances from a machine learning (ML) model. However, efficiently removing this data from an ML model is generally difficult. In this paper, we introduce data removal-enabled (DaRE) forests, a variant of random forests that enables the removal of training data with minimal retraining. Model updates for each DaRE tree in the forest are exact, meaning that removing instances from a DaRE model yields exactly the same model as retraining from scratch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05567","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/2009.05567/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":"2009.05567","created_at":"2026-07-05T02:48:33.944909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05567v2","created_at":"2026-07-05T02:48:33.944909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05567","created_at":"2026-07-05T02:48:33.944909+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBKERH6FSJSC","created_at":"2026-07-05T02:48:33.944909+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBKERH6FSJSCFI4P","created_at":"2026-07-05T02:48:33.944909+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBKERH6F","created_at":"2026-07-05T02:48:33.944909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01634","citing_title":"Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO","json":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO.json","graph_json":"https://pith.science/api/pith-number/BBKERH6FSJSCFI4P34HV6O76HO/graph.json","events_json":"https://pith.science/api/pith-number/BBKERH6FSJSCFI4P34HV6O76HO/events.json","paper":"https://pith.science/paper/BBKERH6F"},"agent_actions":{"view_html":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO","download_json":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO.json","view_paper":"https://pith.science/paper/BBKERH6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05567&json=true","fetch_graph":"https://pith.science/api/pith-number/BBKERH6FSJSCFI4P34HV6O76HO/graph.json","fetch_events":"https://pith.science/api/pith-number/BBKERH6FSJSCFI4P34HV6O76HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO/action/storage_attestation","attest_author":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO/action/author_attestation","sign_citation":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO/action/citation_signature","submit_replication":"https://pith.science/pith/BBKERH6FSJSCFI4P34HV6O76HO/action/replication_record"}},"created_at":"2026-07-05T02:48:33.944909+00:00","updated_at":"2026-07-05T02:48:33.944909+00:00"}