{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HDFNW3WLBND3MBH3IB52JKYQNJ","short_pith_number":"pith:HDFNW3WL","schema_version":"1.0","canonical_sha256":"38cadb6ecb0b47b604fb407ba4ab106a7f2872b23f3bfb9401803c8cb746858a","source":{"kind":"arxiv","id":"1908.01755","version":4},"attestation_state":"computed","paper":{"title":"On the Existence of Simpler Machine Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Rudin, Lesia Semenova, Ronald Parr","submitted_at":"2019-08-05T17:52:53Z","abstract_excerpt":"It is almost always easier to find an accurate-but-complex model than an accurate-yet-simple model. Finding optimal, sparse, accurate models of various forms (linear models with integer coefficients, decision sets, rule lists, decision trees) is generally NP-hard. We often do not know whether the search for a simpler model will be worthwhile, and thus we do not go to the trouble of searching for one. In this work, we ask an important practical question: can accurate-yet-simple models be proven to exist, or shown likely to exist, before explicitly searching for them? We hypothesize that there i"},"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":"1908.01755","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T17:52:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"11478cad27dc06ebd48834a5cca849899f528de1b1d3c1d685d07fda9ecaab89","abstract_canon_sha256":"124d910ab708d65197a4238e99ae3e61c9b75d30087badd28f1d26afea87f3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:48.522990Z","signature_b64":"ZOFjUWstjvAR3pKAoxsBpwt8XZL6rV3bEcF2Bje4b4SlkMm5mtDtfivJKpnR42kIVOZQ/Tp/u6Ry547isRcjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38cadb6ecb0b47b604fb407ba4ab106a7f2872b23f3bfb9401803c8cb746858a","last_reissued_at":"2026-07-05T04:22:48.522580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:48.522580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Existence of Simpler Machine Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Rudin, Lesia Semenova, Ronald Parr","submitted_at":"2019-08-05T17:52:53Z","abstract_excerpt":"It is almost always easier to find an accurate-but-complex model than an accurate-yet-simple model. Finding optimal, sparse, accurate models of various forms (linear models with integer coefficients, decision sets, rule lists, decision trees) is generally NP-hard. We often do not know whether the search for a simpler model will be worthwhile, and thus we do not go to the trouble of searching for one. In this work, we ask an important practical question: can accurate-yet-simple models be proven to exist, or shown likely to exist, before explicitly searching for them? We hypothesize that there i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01755","kind":"arxiv","version":4},"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/1908.01755/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":"1908.01755","created_at":"2026-07-05T04:22:48.522644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01755v4","created_at":"2026-07-05T04:22:48.522644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01755","created_at":"2026-07-05T04:22:48.522644+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDFNW3WLBND3","created_at":"2026-07-05T04:22:48.522644+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDFNW3WLBND3MBH3","created_at":"2026-07-05T04:22:48.522644+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDFNW3WL","created_at":"2026-07-05T04:22:48.522644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02632","citing_title":"Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09520","citing_title":"Rashomon Sets and Model Multiplicity in Federated Learning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08964","citing_title":"Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09452","citing_title":"SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ","json":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ.json","graph_json":"https://pith.science/api/pith-number/HDFNW3WLBND3MBH3IB52JKYQNJ/graph.json","events_json":"https://pith.science/api/pith-number/HDFNW3WLBND3MBH3IB52JKYQNJ/events.json","paper":"https://pith.science/paper/HDFNW3WL"},"agent_actions":{"view_html":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ","download_json":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ.json","view_paper":"https://pith.science/paper/HDFNW3WL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01755&json=true","fetch_graph":"https://pith.science/api/pith-number/HDFNW3WLBND3MBH3IB52JKYQNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HDFNW3WLBND3MBH3IB52JKYQNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ/action/storage_attestation","attest_author":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ/action/author_attestation","sign_citation":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ/action/citation_signature","submit_replication":"https://pith.science/pith/HDFNW3WLBND3MBH3IB52JKYQNJ/action/replication_record"}},"created_at":"2026-07-05T04:22:48.522644+00:00","updated_at":"2026-07-05T04:22:48.522644+00:00"}