{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNU7Z6FPGJHFINTB73KG4A2WZ2","short_pith_number":"pith:DNU7Z6FP","schema_version":"1.0","canonical_sha256":"1b69fcf8af324e543661fed46e0356ceb495bbdfed8648acec54344211a699fb","source":{"kind":"arxiv","id":"2402.02870","version":5},"attestation_state":"computed","paper":{"title":"Rethinking Explainable Machine Learning as Applied Statistics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Raidl, Sebastian Bordt, Ulrike von Luxburg","submitted_at":"2024-02-05T10:36:48Z","abstract_excerpt":"In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuiti"},"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":"2402.02870","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T10:36:48Z","cross_cats_sorted":[],"title_canon_sha256":"f50101723176741b118371f21feb33f082b62c8d24e5f3a11dd621b125163b23","abstract_canon_sha256":"ce35423f465526df893a81d6be09bfd474d7fbb7ff9bb5b079fe12769733fde0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:31.029724Z","signature_b64":"DKAC6ZyhDN9+QTVzI5mgybvy2FjQC3xHhG442rpNpvJOovyx+3HWMAu1qnRndP3BoWes6YldRcHr2iJ5IaM8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b69fcf8af324e543661fed46e0356ceb495bbdfed8648acec54344211a699fb","last_reissued_at":"2026-07-05T11:21:31.029185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:31.029185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Explainable Machine Learning as Applied Statistics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Raidl, Sebastian Bordt, Ulrike von Luxburg","submitted_at":"2024-02-05T10:36:48Z","abstract_excerpt":"In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02870","kind":"arxiv","version":5},"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/2402.02870/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":"2402.02870","created_at":"2026-07-05T11:21:31.029244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02870v5","created_at":"2026-07-05T11:21:31.029244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02870","created_at":"2026-07-05T11:21:31.029244+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNU7Z6FPGJHF","created_at":"2026-07-05T11:21:31.029244+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNU7Z6FPGJHFINTB","created_at":"2026-07-05T11:21:31.029244+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNU7Z6FP","created_at":"2026-07-05T11:21:31.029244+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/DNU7Z6FPGJHFINTB73KG4A2WZ2","json":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2.json","graph_json":"https://pith.science/api/pith-number/DNU7Z6FPGJHFINTB73KG4A2WZ2/graph.json","events_json":"https://pith.science/api/pith-number/DNU7Z6FPGJHFINTB73KG4A2WZ2/events.json","paper":"https://pith.science/paper/DNU7Z6FP"},"agent_actions":{"view_html":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2","download_json":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2.json","view_paper":"https://pith.science/paper/DNU7Z6FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02870&json=true","fetch_graph":"https://pith.science/api/pith-number/DNU7Z6FPGJHFINTB73KG4A2WZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/DNU7Z6FPGJHFINTB73KG4A2WZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2/action/storage_attestation","attest_author":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2/action/author_attestation","sign_citation":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2/action/citation_signature","submit_replication":"https://pith.science/pith/DNU7Z6FPGJHFINTB73KG4A2WZ2/action/replication_record"}},"created_at":"2026-07-05T11:21:31.029244+00:00","updated_at":"2026-07-05T11:21:31.029244+00:00"}