{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:624EJRTBCIYDKRH7LJCY3L2PIJ","short_pith_number":"pith:624EJRTB","schema_version":"1.0","canonical_sha256":"f6b844c66112303544ff5a458daf4f42461e89a5060d674cddb526c1bd2e8222","source":{"kind":"arxiv","id":"2506.08338","version":1},"attestation_state":"computed","paper":{"title":"midr: Learning from Black-Box Models by Maximum Interpretation Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Hirokazu Iwasawa, Reiji Kozuma, Ryoichi Asashiba","submitted_at":"2025-06-10T01:46:49Z","abstract_excerpt":"The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by minimizing the squared error between the model's prediction function and this additive representation. "},"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":"2506.08338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-06-10T01:46:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39f0da5fc40fc653c8e7154dc9f9a5c58d85b8f6b69ef87c4fa777dd28a5fcd3","abstract_canon_sha256":"b518f5ae246233e4019688bc92eba39a57ec0faf66c0812631c116a9a8c88a95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:48.237762Z","signature_b64":"8+/1jAnyN11w1ZeKg8hIA9Ovnq9SBpQs96i8IlpgxI/cUUJzLOj6197ZcFR1VjlsLHibfzuyT+sxpme4An6dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b844c66112303544ff5a458daf4f42461e89a5060d674cddb526c1bd2e8222","last_reissued_at":"2026-07-05T11:18:48.237378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:48.237378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"midr: Learning from Black-Box Models by Maximum Interpretation Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Hirokazu Iwasawa, Reiji Kozuma, Ryoichi Asashiba","submitted_at":"2025-06-10T01:46:49Z","abstract_excerpt":"The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by minimizing the squared error between the model's prediction function and this additive representation. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08338","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/2506.08338/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":"2506.08338","created_at":"2026-07-05T11:18:48.237433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08338v1","created_at":"2026-07-05T11:18:48.237433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08338","created_at":"2026-07-05T11:18:48.237433+00:00"},{"alias_kind":"pith_short_12","alias_value":"624EJRTBCIYD","created_at":"2026-07-05T11:18:48.237433+00:00"},{"alias_kind":"pith_short_16","alias_value":"624EJRTBCIYDKRH7","created_at":"2026-07-05T11:18:48.237433+00:00"},{"alias_kind":"pith_short_8","alias_value":"624EJRTB","created_at":"2026-07-05T11:18:48.237433+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/624EJRTBCIYDKRH7LJCY3L2PIJ","json":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ.json","graph_json":"https://pith.science/api/pith-number/624EJRTBCIYDKRH7LJCY3L2PIJ/graph.json","events_json":"https://pith.science/api/pith-number/624EJRTBCIYDKRH7LJCY3L2PIJ/events.json","paper":"https://pith.science/paper/624EJRTB"},"agent_actions":{"view_html":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ","download_json":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ.json","view_paper":"https://pith.science/paper/624EJRTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08338&json=true","fetch_graph":"https://pith.science/api/pith-number/624EJRTBCIYDKRH7LJCY3L2PIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/624EJRTBCIYDKRH7LJCY3L2PIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ/action/storage_attestation","attest_author":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ/action/author_attestation","sign_citation":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ/action/citation_signature","submit_replication":"https://pith.science/pith/624EJRTBCIYDKRH7LJCY3L2PIJ/action/replication_record"}},"created_at":"2026-07-05T11:18:48.237433+00:00","updated_at":"2026-07-05T11:18:48.237433+00:00"}