{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:OBRT3ECI5AYBK3KGVQW4PJWNRJ","short_pith_number":"pith:OBRT3ECI","schema_version":"1.0","canonical_sha256":"70633d9048e830156d46ac2dc7a6cd8a68f8fa1d525a52ef76d958f70583d2e0","source":{"kind":"arxiv","id":"1512.01617","version":3},"attestation_state":"computed","paper":{"title":"Guarding against Spurious Discoveries in High Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Wen-Xin Zhou","submitted_at":"2015-12-05T03:48:46Z","abstract_excerpt":"Many data mining and statistical machine learning algorithms have been developed to select a subset of covariates to associate with a response variable. Spurious discoveries can easily arise in high-dimensional data analysis due to enormous possibilities of such selections. How can we know statistically our discoveries better than those by chance? In this paper, we define a measure of goodness of spurious fit, which shows how good a response variable can be fitted by an optimally selected subset of covariates under the null model, and propose a simple and effective LAMM algorithm to compute it"},"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":"1512.01617","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2015-12-05T03:48:46Z","cross_cats_sorted":["stat.ME","stat.TH"],"title_canon_sha256":"e2fb6bd42181867d608307de46f2f8934caadb5663685ec2ad013e423a115c46","abstract_canon_sha256":"9999ae54cf6de6e068df77416a7bc1af9a02e250b3c7a4884f98f7ff73f8a1b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:36.077437Z","signature_b64":"vVpCBdGwYAOzf5aSSr4MFmS7K/riz0SiPhyMx8WMM/eVBbi7CKnkkXGUqSuEpvyGRbvuSrguZrAmJzrupHP0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70633d9048e830156d46ac2dc7a6cd8a68f8fa1d525a52ef76d958f70583d2e0","last_reissued_at":"2026-05-18T01:01:36.076894Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:36.076894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guarding against Spurious Discoveries in High Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Wen-Xin Zhou","submitted_at":"2015-12-05T03:48:46Z","abstract_excerpt":"Many data mining and statistical machine learning algorithms have been developed to select a subset of covariates to associate with a response variable. Spurious discoveries can easily arise in high-dimensional data analysis due to enormous possibilities of such selections. How can we know statistically our discoveries better than those by chance? In this paper, we define a measure of goodness of spurious fit, which shows how good a response variable can be fitted by an optimally selected subset of covariates under the null model, and propose a simple and effective LAMM algorithm to compute it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01617","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":""},"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":"1512.01617","created_at":"2026-05-18T01:01:36.076977+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.01617v3","created_at":"2026-05-18T01:01:36.076977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01617","created_at":"2026-05-18T01:01:36.076977+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBRT3ECI5AYB","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBRT3ECI5AYBK3KG","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBRT3ECI","created_at":"2026-05-18T12:29:34.919912+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/OBRT3ECI5AYBK3KGVQW4PJWNRJ","json":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ.json","graph_json":"https://pith.science/api/pith-number/OBRT3ECI5AYBK3KGVQW4PJWNRJ/graph.json","events_json":"https://pith.science/api/pith-number/OBRT3ECI5AYBK3KGVQW4PJWNRJ/events.json","paper":"https://pith.science/paper/OBRT3ECI"},"agent_actions":{"view_html":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ","download_json":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ.json","view_paper":"https://pith.science/paper/OBRT3ECI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.01617&json=true","fetch_graph":"https://pith.science/api/pith-number/OBRT3ECI5AYBK3KGVQW4PJWNRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OBRT3ECI5AYBK3KGVQW4PJWNRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ/action/storage_attestation","attest_author":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ/action/author_attestation","sign_citation":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ/action/citation_signature","submit_replication":"https://pith.science/pith/OBRT3ECI5AYBK3KGVQW4PJWNRJ/action/replication_record"}},"created_at":"2026-05-18T01:01:36.076977+00:00","updated_at":"2026-05-18T01:01:36.076977+00:00"}