{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5BUFFX5QP7PZHSUFDVL3Y2EJQA","short_pith_number":"pith:5BUFFX5Q","schema_version":"1.0","canonical_sha256":"e86852dfb07fdf93ca851d57bc6889803060daf07f08b92d06cfc2e6d60d8c4d","source":{"kind":"arxiv","id":"1802.06640","version":2},"attestation_state":"computed","paper":{"title":"Finding Influential Training Samples for Gradient Boosted Decision Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Sharchilev, Maarten de Rijke, Pavel Serdyukov, Yury Ustinovsky","submitted_at":"2018-02-19T14:19:40Z","abstract_excerpt":"We address the problem of finding influential training samples for a particular case of tree ensemble-based models, e.g., Random Forest (RF) or Gradient Boosted Decision Trees (GBDT). A natural way of formalizing this problem is studying how the model's predictions change upon leave-one-out retraining, leaving out each individual training sample. Recent work has shown that, for parametric models, this analysis can be conducted in a computationally efficient way. We propose several ways of extending this framework to non-parametric GBDT ensembles under the assumption that tree structures remain"},"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":"1802.06640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-19T14:19:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5c25d2f78872731505082223f6d65a0f36dec7a55b7e3f46ac3860683ce8391","abstract_canon_sha256":"fd468d47039cc73ffd064a6918695557df5f7111adbbcbca5009bbc850edf515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:19.584040Z","signature_b64":"57b9q5hZF1t3l6hHq0iiOZR4Wey2DjN6J1qZx1WOxsU9bNKVAwjRAXEOrKOkVHDOJkavu6x86N/FNtgcaQR1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e86852dfb07fdf93ca851d57bc6889803060daf07f08b92d06cfc2e6d60d8c4d","last_reissued_at":"2026-05-18T00:21:19.583344Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:19.583344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Influential Training Samples for Gradient Boosted Decision Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Sharchilev, Maarten de Rijke, Pavel Serdyukov, Yury Ustinovsky","submitted_at":"2018-02-19T14:19:40Z","abstract_excerpt":"We address the problem of finding influential training samples for a particular case of tree ensemble-based models, e.g., Random Forest (RF) or Gradient Boosted Decision Trees (GBDT). A natural way of formalizing this problem is studying how the model's predictions change upon leave-one-out retraining, leaving out each individual training sample. Recent work has shown that, for parametric models, this analysis can be conducted in a computationally efficient way. We propose several ways of extending this framework to non-parametric GBDT ensembles under the assumption that tree structures remain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06640","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":"1802.06640","created_at":"2026-05-18T00:21:19.583445+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06640v2","created_at":"2026-05-18T00:21:19.583445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06640","created_at":"2026-05-18T00:21:19.583445+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BUFFX5QP7PZ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BUFFX5QP7PZHSUF","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BUFFX5Q","created_at":"2026-05-18T12:32:08.215937+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/5BUFFX5QP7PZHSUFDVL3Y2EJQA","json":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA.json","graph_json":"https://pith.science/api/pith-number/5BUFFX5QP7PZHSUFDVL3Y2EJQA/graph.json","events_json":"https://pith.science/api/pith-number/5BUFFX5QP7PZHSUFDVL3Y2EJQA/events.json","paper":"https://pith.science/paper/5BUFFX5Q"},"agent_actions":{"view_html":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA","download_json":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA.json","view_paper":"https://pith.science/paper/5BUFFX5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06640&json=true","fetch_graph":"https://pith.science/api/pith-number/5BUFFX5QP7PZHSUFDVL3Y2EJQA/graph.json","fetch_events":"https://pith.science/api/pith-number/5BUFFX5QP7PZHSUFDVL3Y2EJQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA/action/storage_attestation","attest_author":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA/action/author_attestation","sign_citation":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA/action/citation_signature","submit_replication":"https://pith.science/pith/5BUFFX5QP7PZHSUFDVL3Y2EJQA/action/replication_record"}},"created_at":"2026-05-18T00:21:19.583445+00:00","updated_at":"2026-05-18T00:21:19.583445+00:00"}