{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BSPOWMOH5FA675RZLSOXVBQMTE","short_pith_number":"pith:BSPOWMOH","schema_version":"1.0","canonical_sha256":"0c9eeb31c7e941eff6395c9d7a860c991bf42431410571a92088f5af22b19b2a","source":{"kind":"arxiv","id":"2410.23772","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Interactions and Dependencies in Feature Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric G\\\"unther, Gunnar K\\\"onig, Ulrike von Luxburg","submitted_at":"2024-10-31T09:41:10Z","abstract_excerpt":"In explainable machine learning, global feature importance methods try to determine how much each individual feature contributes to predicting the target variable, resulting in one importance score for each feature. But often, predicting the target variable requires interactions between several features (such as in the XOR function), and features might have complex statistical dependencies that allow to partially replace one feature with another one. In commonly used feature importance scores these cooperative effects are conflated with the features' individual contributions, making them prone"},"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":"2410.23772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T09:41:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ce9eed5c92b70c89bc81658d08a4eaf57274d805e5ebbb8c71726b0e9bed02ad","abstract_canon_sha256":"8ccadcee8d92331ab7b7865ee015d96183480a65d307c3c24d74c2f978e0f153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:05.056067Z","signature_b64":"UZq4zGp7YBxPrypyCVQFYzWWXqeWFxE/9wY7Ibm88ElgFL65whMHuXLvgQ0R8vICxXzSp9Nu6aCu59EHXqQgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c9eeb31c7e941eff6395c9d7a860c991bf42431410571a92088f5af22b19b2a","last_reissued_at":"2026-07-05T09:29:05.055619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:05.055619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Interactions and Dependencies in Feature Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric G\\\"unther, Gunnar K\\\"onig, Ulrike von Luxburg","submitted_at":"2024-10-31T09:41:10Z","abstract_excerpt":"In explainable machine learning, global feature importance methods try to determine how much each individual feature contributes to predicting the target variable, resulting in one importance score for each feature. But often, predicting the target variable requires interactions between several features (such as in the XOR function), and features might have complex statistical dependencies that allow to partially replace one feature with another one. In commonly used feature importance scores these cooperative effects are conflated with the features' individual contributions, making them prone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23772","kind":"arxiv","version":1},"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/2410.23772/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":"2410.23772","created_at":"2026-07-05T09:29:05.055679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23772v1","created_at":"2026-07-05T09:29:05.055679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23772","created_at":"2026-07-05T09:29:05.055679+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSPOWMOH5FA6","created_at":"2026-07-05T09:29:05.055679+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSPOWMOH5FA675RZ","created_at":"2026-07-05T09:29:05.055679+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSPOWMOH","created_at":"2026-07-05T09:29:05.055679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07286","citing_title":"From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE","json":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE.json","graph_json":"https://pith.science/api/pith-number/BSPOWMOH5FA675RZLSOXVBQMTE/graph.json","events_json":"https://pith.science/api/pith-number/BSPOWMOH5FA675RZLSOXVBQMTE/events.json","paper":"https://pith.science/paper/BSPOWMOH"},"agent_actions":{"view_html":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE","download_json":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE.json","view_paper":"https://pith.science/paper/BSPOWMOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23772&json=true","fetch_graph":"https://pith.science/api/pith-number/BSPOWMOH5FA675RZLSOXVBQMTE/graph.json","fetch_events":"https://pith.science/api/pith-number/BSPOWMOH5FA675RZLSOXVBQMTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE/action/storage_attestation","attest_author":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE/action/author_attestation","sign_citation":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE/action/citation_signature","submit_replication":"https://pith.science/pith/BSPOWMOH5FA675RZLSOXVBQMTE/action/replication_record"}},"created_at":"2026-07-05T09:29:05.055679+00:00","updated_at":"2026-07-05T09:29:05.055679+00:00"}