{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5DVVJNM33Z3B4EIR7HKESXTTRP","short_pith_number":"pith:5DVVJNM3","schema_version":"1.0","canonical_sha256":"e8eb54b59bde761e1111f9d4495e738bcd95d5e14d7721c29272929517b54cbf","source":{"kind":"arxiv","id":"1804.06620","version":3},"attestation_state":"computed","paper":{"title":"Visualizing the Feature Importance for Black Box Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernd Bischl, Christoph Molnar, Giuseppe Casalicchio","submitted_at":"2018-04-18T09:35:38Z","abstract_excerpt":"In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations. Our proposed methods are related to partial dependenc"},"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":"1804.06620","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T09:35:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"71b009851c31167a90f09c32a452311f8a7a0da0d0001e4a33147308a34bda64","abstract_canon_sha256":"57f712dd5676c5cdf004b24e0eec98117f720d91e89370ae6dc7cff5af1e48ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:14.462262Z","signature_b64":"BRIoqQa0AfvhD1fCh4m+V6VoA9LZ4nahMZ4wPmlt1gP9e71X2e3IGm8/jO1+4sZqgFI4k5ksxpod/z5Mptp0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8eb54b59bde761e1111f9d4495e738bcd95d5e14d7721c29272929517b54cbf","last_reissued_at":"2026-07-05T01:18:14.461847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:14.461847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualizing the Feature Importance for Black Box Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernd Bischl, Christoph Molnar, Giuseppe Casalicchio","submitted_at":"2018-04-18T09:35:38Z","abstract_excerpt":"In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations. Our proposed methods are related to partial dependenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06620","kind":"arxiv","version":3},"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/1804.06620/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":"1804.06620","created_at":"2026-07-05T01:18:14.461906+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06620v3","created_at":"2026-07-05T01:18:14.461906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06620","created_at":"2026-07-05T01:18:14.461906+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DVVJNM33Z3B","created_at":"2026-07-05T01:18:14.461906+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DVVJNM33Z3B4EIR","created_at":"2026-07-05T01:18:14.461906+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DVVJNM3","created_at":"2026-07-05T01:18:14.461906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13623","citing_title":"Unifying Attribution-Based Explanations Using Functional Decomposition","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP","json":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP.json","graph_json":"https://pith.science/api/pith-number/5DVVJNM33Z3B4EIR7HKESXTTRP/graph.json","events_json":"https://pith.science/api/pith-number/5DVVJNM33Z3B4EIR7HKESXTTRP/events.json","paper":"https://pith.science/paper/5DVVJNM3"},"agent_actions":{"view_html":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP","download_json":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP.json","view_paper":"https://pith.science/paper/5DVVJNM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06620&json=true","fetch_graph":"https://pith.science/api/pith-number/5DVVJNM33Z3B4EIR7HKESXTTRP/graph.json","fetch_events":"https://pith.science/api/pith-number/5DVVJNM33Z3B4EIR7HKESXTTRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP/action/storage_attestation","attest_author":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP/action/author_attestation","sign_citation":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP/action/citation_signature","submit_replication":"https://pith.science/pith/5DVVJNM33Z3B4EIR7HKESXTTRP/action/replication_record"}},"created_at":"2026-07-05T01:18:14.461906+00:00","updated_at":"2026-07-05T01:18:14.461906+00:00"}