{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:O2ZY2CRY4MBWUDTAKNCUWJ7URZ","short_pith_number":"pith:O2ZY2CRY","schema_version":"1.0","canonical_sha256":"76b38d0a38e3036a0e6053454b27f48e670df11e4a2b63028ab24359a638981c","source":{"kind":"arxiv","id":"1706.06060","version":6},"attestation_state":"computed","paper":{"title":"Consistent feature attribution for tree ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Scott M. Lundberg, Su-In Lee","submitted_at":"2017-06-19T17:03:46Z","abstract_excerpt":"Note that a newer expanded version of this paper is now available at: arXiv:1802.03888\n  It is critical in many applications to understand what features are important for a model, and why individual predictions were made. For tree ensemble methods these questions are usually answered by attributing importance values to input features, either globally or for a single prediction. Here we show that current feature attribution methods are inconsistent, which means changing the model to rely more on a given feature can actually decrease the importance assigned to that feature. To address this probl"},"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":"1706.06060","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-19T17:03:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"09a50fd614bd40ae21d4301cd8ac2f51f4c0c27d0edad88ef1b07fcc444ebbd8","abstract_canon_sha256":"ed29d3631e109a1429c7b8f5421f0d34d8464b008b8c72f6924ef75eb258a0d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:08.808552Z","signature_b64":"eM5M5UOa81y17Y9RiRntTSXet2p30BBcfeWpS8XQDU2bdXBlYdWDRzByi9iA1AtJQtoZWuD+TU08dyU/epGdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76b38d0a38e3036a0e6053454b27f48e670df11e4a2b63028ab24359a638981c","last_reissued_at":"2026-05-18T00:23:08.807790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:08.807790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent feature attribution for tree ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Scott M. Lundberg, Su-In Lee","submitted_at":"2017-06-19T17:03:46Z","abstract_excerpt":"Note that a newer expanded version of this paper is now available at: arXiv:1802.03888\n  It is critical in many applications to understand what features are important for a model, and why individual predictions were made. For tree ensemble methods these questions are usually answered by attributing importance values to input features, either globally or for a single prediction. Here we show that current feature attribution methods are inconsistent, which means changing the model to rely more on a given feature can actually decrease the importance assigned to that feature. To address this probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06060","kind":"arxiv","version":6},"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":"1706.06060","created_at":"2026-05-18T00:23:08.807924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06060v6","created_at":"2026-05-18T00:23:08.807924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06060","created_at":"2026-05-18T00:23:08.807924+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2ZY2CRY4MBW","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2ZY2CRY4MBWUDTA","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2ZY2CRY","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18864","citing_title":"ParamBoost: Gradient Boosted Piecewise Cubic Polynomials","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ","json":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ.json","graph_json":"https://pith.science/api/pith-number/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/graph.json","events_json":"https://pith.science/api/pith-number/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/events.json","paper":"https://pith.science/paper/O2ZY2CRY"},"agent_actions":{"view_html":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ","download_json":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ.json","view_paper":"https://pith.science/paper/O2ZY2CRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06060&json=true","fetch_graph":"https://pith.science/api/pith-number/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/graph.json","fetch_events":"https://pith.science/api/pith-number/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/action/storage_attestation","attest_author":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/action/author_attestation","sign_citation":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/action/citation_signature","submit_replication":"https://pith.science/pith/O2ZY2CRY4MBWUDTAKNCUWJ7URZ/action/replication_record"}},"created_at":"2026-05-18T00:23:08.807924+00:00","updated_at":"2026-05-18T00:23:08.807924+00:00"}