{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OWRY7UFL46ELI3MXTZGDV4CVGD","short_pith_number":"pith:OWRY7UFL","schema_version":"1.0","canonical_sha256":"75a38fd0abe788b46d979e4c3af05530fb6b501ee154012dc6f97958e328f797","source":{"kind":"arxiv","id":"2404.12862","version":2},"attestation_state":"computed","paper":{"title":"A Guide to Feature Importance Methods for Scientific Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Bernd Bischl, Fiona Katharina Ewald, Giuseppe Casalicchio, Gunnar K\\\"onig, Ludwig Bothmann, Marvin N. Wright","submitted_at":"2024-04-19T13:01:59Z","abstract_excerpt":"While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many ML models cannot directly provide due to their opaque internal mechanisms. Feature importance (FI) methods provide useful insights into the DGP under certain conditions. Since the results of different FI methods have different interpretations, selecting the correct FI method for a concrete use case is crucial and still requires expert knowledge. T"},"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":"2404.12862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-04-19T13:01:59Z","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.TH"],"title_canon_sha256":"94f0d8a1985e973efba637422992585afdf8c8fffc415c31688ad572f8417a76","abstract_canon_sha256":"0f12044d30fbaee9061459265479981971660d8a6cd2d0dcf121d8578d94982c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:36.993358Z","signature_b64":"dA7Nsm+5bzZLLiD1UFaD2O+dhRJt+LtbCxf0R0vxExN23rmQ9oEgzcCndxojMpz3ZYYTsV/HXV1WfylM+4OzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a38fd0abe788b46d979e4c3af05530fb6b501ee154012dc6f97958e328f797","last_reissued_at":"2026-07-05T09:00:36.992929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:36.992929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Guide to Feature Importance Methods for Scientific Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Bernd Bischl, Fiona Katharina Ewald, Giuseppe Casalicchio, Gunnar K\\\"onig, Ludwig Bothmann, Marvin N. Wright","submitted_at":"2024-04-19T13:01:59Z","abstract_excerpt":"While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many ML models cannot directly provide due to their opaque internal mechanisms. Feature importance (FI) methods provide useful insights into the DGP under certain conditions. Since the results of different FI methods have different interpretations, selecting the correct FI method for a concrete use case is crucial and still requires expert knowledge. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12862","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/2404.12862/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":"2404.12862","created_at":"2026-07-05T09:00:36.992980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12862v2","created_at":"2026-07-05T09:00:36.992980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12862","created_at":"2026-07-05T09:00:36.992980+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWRY7UFL46EL","created_at":"2026-07-05T09:00:36.992980+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWRY7UFL46ELI3MX","created_at":"2026-07-05T09:00:36.992980+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWRY7UFL","created_at":"2026-07-05T09:00:36.992980+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/OWRY7UFL46ELI3MXTZGDV4CVGD","json":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD.json","graph_json":"https://pith.science/api/pith-number/OWRY7UFL46ELI3MXTZGDV4CVGD/graph.json","events_json":"https://pith.science/api/pith-number/OWRY7UFL46ELI3MXTZGDV4CVGD/events.json","paper":"https://pith.science/paper/OWRY7UFL"},"agent_actions":{"view_html":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD","download_json":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD.json","view_paper":"https://pith.science/paper/OWRY7UFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12862&json=true","fetch_graph":"https://pith.science/api/pith-number/OWRY7UFL46ELI3MXTZGDV4CVGD/graph.json","fetch_events":"https://pith.science/api/pith-number/OWRY7UFL46ELI3MXTZGDV4CVGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD/action/storage_attestation","attest_author":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD/action/author_attestation","sign_citation":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD/action/citation_signature","submit_replication":"https://pith.science/pith/OWRY7UFL46ELI3MXTZGDV4CVGD/action/replication_record"}},"created_at":"2026-07-05T09:00:36.992980+00:00","updated_at":"2026-07-05T09:00:36.992980+00:00"}