{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TC24FQDJMTOTJ7AI4GXIS7E4MM","short_pith_number":"pith:TC24FQDJ","schema_version":"1.0","canonical_sha256":"98b5c2c06964dd34fc08e1ae897c9c633258f6e9c51aa27c241555ee1e334e55","source":{"kind":"arxiv","id":"2402.09702","version":3},"attestation_state":"computed","paper":{"title":"Sparse and Faithful Explanations Without Sparse Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Rudin, Tong Wang, Vittorio Orlandi, Yiyang Sun, Zhi Chen","submitted_at":"2024-02-15T04:36:52Z","abstract_excerpt":"Even if a model is not globally sparse, it is possible for decisions made from that model to be accurately and faithfully described by a small number of features. For instance, an application for a large loan might be denied to someone because they have no credit history, which overwhelms any evidence towards their creditworthiness. In this work, we introduce the Sparse Explanation Value (SEV), a new way of measuring sparsity in machine learning models. In the loan denial example above, the SEV is 1 because only one factor is needed to explain why the loan was denied. SEV is a measure of decis"},"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":"2402.09702","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T04:36:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a1cc04d7ea1d5bd7c98a08e9263ff299e3bc6c18ce19fdeda55c995f92a17844","abstract_canon_sha256":"de6371de3cf783ee2f75874141dd4227523265f0c7bdbe3f207dc510a513b120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:08.305454Z","signature_b64":"PYLrYnUrWcGtKGR5hpWmzvQm/xliBrHbs/yLkOkQwkUNwGs58RY+AvrW35g4v3T2TTiZyGiMJD/gAN7fLknIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b5c2c06964dd34fc08e1ae897c9c633258f6e9c51aa27c241555ee1e334e55","last_reissued_at":"2026-07-05T07:54:08.304939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:08.304939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse and Faithful Explanations Without Sparse Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Rudin, Tong Wang, Vittorio Orlandi, Yiyang Sun, Zhi Chen","submitted_at":"2024-02-15T04:36:52Z","abstract_excerpt":"Even if a model is not globally sparse, it is possible for decisions made from that model to be accurately and faithfully described by a small number of features. For instance, an application for a large loan might be denied to someone because they have no credit history, which overwhelms any evidence towards their creditworthiness. In this work, we introduce the Sparse Explanation Value (SEV), a new way of measuring sparsity in machine learning models. In the loan denial example above, the SEV is 1 because only one factor is needed to explain why the loan was denied. SEV is a measure of decis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09702","kind":"arxiv","version":3},"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/2402.09702/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":"2402.09702","created_at":"2026-07-05T07:54:08.305002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09702v3","created_at":"2026-07-05T07:54:08.305002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09702","created_at":"2026-07-05T07:54:08.305002+00:00"},{"alias_kind":"pith_short_12","alias_value":"TC24FQDJMTOT","created_at":"2026-07-05T07:54:08.305002+00:00"},{"alias_kind":"pith_short_16","alias_value":"TC24FQDJMTOTJ7AI","created_at":"2026-07-05T07:54:08.305002+00:00"},{"alias_kind":"pith_short_8","alias_value":"TC24FQDJ","created_at":"2026-07-05T07:54:08.305002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.16759","citing_title":"Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM","json":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM.json","graph_json":"https://pith.science/api/pith-number/TC24FQDJMTOTJ7AI4GXIS7E4MM/graph.json","events_json":"https://pith.science/api/pith-number/TC24FQDJMTOTJ7AI4GXIS7E4MM/events.json","paper":"https://pith.science/paper/TC24FQDJ"},"agent_actions":{"view_html":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM","download_json":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM.json","view_paper":"https://pith.science/paper/TC24FQDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09702&json=true","fetch_graph":"https://pith.science/api/pith-number/TC24FQDJMTOTJ7AI4GXIS7E4MM/graph.json","fetch_events":"https://pith.science/api/pith-number/TC24FQDJMTOTJ7AI4GXIS7E4MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM/action/storage_attestation","attest_author":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM/action/author_attestation","sign_citation":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM/action/citation_signature","submit_replication":"https://pith.science/pith/TC24FQDJMTOTJ7AI4GXIS7E4MM/action/replication_record"}},"created_at":"2026-07-05T07:54:08.305002+00:00","updated_at":"2026-07-05T07:54:08.305002+00:00"}