{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6AOXCV5VGSOXPYBPFKZK6EDE6R","short_pith_number":"pith:6AOXCV5V","schema_version":"1.0","canonical_sha256":"f01d7157b5349d77e02f2ab2af1064f451c0e0af95b4c53dd7e37f35b6de17dd","source":{"kind":"arxiv","id":"2412.17152","version":2},"attestation_state":"computed","paper":{"title":"Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Barbara Hammer, Eyke H\\\"ullermeier, Fabian Fumagalli, Julia Herbinger, Maximilian Muschalik","submitted_at":"2024-12-22T20:12:16Z","abstract_excerpt":"Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distribut"},"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":"2412.17152","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T20:12:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6ec76485f6e66d4f643e84d1b559625147a44a01b48a97a30abdb0272f9d41b7","abstract_canon_sha256":"9a8fb167ebd4fd28bc12c5f4374e31131438f19a7ecc424e9fdb94da5a931f71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:31.869018Z","signature_b64":"huBEPNx+sEQyoNlEMNDKrJmEtIDZf95u8mTygSJ3Q1ysyIXcTcTclIhzPr8YokUkSTM9xSkZdQYXhuvivR4JBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01d7157b5349d77e02f2ab2af1064f451c0e0af95b4c53dd7e37f35b6de17dd","last_reissued_at":"2026-07-05T10:50:31.868517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:31.868517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Barbara Hammer, Eyke H\\\"ullermeier, Fabian Fumagalli, Julia Herbinger, Maximilian Muschalik","submitted_at":"2024-12-22T20:12:16Z","abstract_excerpt":"Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17152","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/2412.17152/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":"2412.17152","created_at":"2026-07-05T10:50:31.868583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17152v2","created_at":"2026-07-05T10:50:31.868583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17152","created_at":"2026-07-05T10:50:31.868583+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AOXCV5VGSOX","created_at":"2026-07-05T10:50:31.868583+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AOXCV5VGSOXPYBP","created_at":"2026-07-05T10:50:31.868583+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AOXCV5V","created_at":"2026-07-05T10:50:31.868583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07578","citing_title":"$\\phi$-Table: A Statistical Explanation for Global SHAP","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R","json":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R.json","graph_json":"https://pith.science/api/pith-number/6AOXCV5VGSOXPYBPFKZK6EDE6R/graph.json","events_json":"https://pith.science/api/pith-number/6AOXCV5VGSOXPYBPFKZK6EDE6R/events.json","paper":"https://pith.science/paper/6AOXCV5V"},"agent_actions":{"view_html":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R","download_json":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R.json","view_paper":"https://pith.science/paper/6AOXCV5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17152&json=true","fetch_graph":"https://pith.science/api/pith-number/6AOXCV5VGSOXPYBPFKZK6EDE6R/graph.json","fetch_events":"https://pith.science/api/pith-number/6AOXCV5VGSOXPYBPFKZK6EDE6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R/action/storage_attestation","attest_author":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R/action/author_attestation","sign_citation":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R/action/citation_signature","submit_replication":"https://pith.science/pith/6AOXCV5VGSOXPYBPFKZK6EDE6R/action/replication_record"}},"created_at":"2026-07-05T10:50:31.868583+00:00","updated_at":"2026-07-05T10:50:31.868583+00:00"}