{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X7NJ6LLDVQLHSBHQQM7AL4QAUV","short_pith_number":"pith:X7NJ6LLD","schema_version":"1.0","canonical_sha256":"bfda9f2d63ac167904f0833e05f200a548043eb1d445c10a9c4f2d5a25d23d00","source":{"kind":"arxiv","id":"1701.05230","version":3},"attestation_state":"computed","paper":{"title":"Surrogate Aided Unsupervised Recovery of Sparse Signals in Single Index Models for Binary Outcomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"Abhishek Chakrabortty, Matey Neykov, Raymond Carroll, Tianxi Cai","submitted_at":"2017-01-18T20:51:27Z","abstract_excerpt":"We consider the recovery of regression coefficients, denoted by $\\boldsymbol{\\beta}_0$, for a single index model (SIM) relating a binary outcome $Y$ to a set of possibly high dimensional covariates $\\boldsymbol{X}$, based on a large but 'unlabeled' dataset $\\mathcal{U}$, with $Y$ never observed. On $\\mathcal{U}$, we fully observe $\\boldsymbol{X}$ and additionally, a surrogate $S$ which, while not being strongly predictive of $Y$ throughout the entirety of its support, can forecast it with high accuracy when it assumes extreme values. Such datasets arise naturally in modern studies involving la"},"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":"1701.05230","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-01-18T20:51:27Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"fb7ac76988393c1a6fc7eadf4ec50bdf4c4b3d29785ab8cba3ad641d4f2e10f5","abstract_canon_sha256":"dba4f66873229d8aad627ecb15c916a193597aa226d877c29acdef8b159eebef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:00.669387Z","signature_b64":"ORbP3+EADlOWrGT5kwdeMjxnt8MfEescKjUm58bmkVyqyOMkmUc2BYpHUlK43BmMbOSxMyXWng0IHGt22f56Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfda9f2d63ac167904f0833e05f200a548043eb1d445c10a9c4f2d5a25d23d00","last_reissued_at":"2026-05-18T00:12:00.668815Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:00.668815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surrogate Aided Unsupervised Recovery of Sparse Signals in Single Index Models for Binary Outcomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"Abhishek Chakrabortty, Matey Neykov, Raymond Carroll, Tianxi Cai","submitted_at":"2017-01-18T20:51:27Z","abstract_excerpt":"We consider the recovery of regression coefficients, denoted by $\\boldsymbol{\\beta}_0$, for a single index model (SIM) relating a binary outcome $Y$ to a set of possibly high dimensional covariates $\\boldsymbol{X}$, based on a large but 'unlabeled' dataset $\\mathcal{U}$, with $Y$ never observed. On $\\mathcal{U}$, we fully observe $\\boldsymbol{X}$ and additionally, a surrogate $S$ which, while not being strongly predictive of $Y$ throughout the entirety of its support, can forecast it with high accuracy when it assumes extreme values. Such datasets arise naturally in modern studies involving la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05230","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":"1701.05230","created_at":"2026-05-18T00:12:00.668892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.05230v3","created_at":"2026-05-18T00:12:00.668892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05230","created_at":"2026-05-18T00:12:00.668892+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7NJ6LLDVQLH","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7NJ6LLDVQLHSBHQ","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7NJ6LLD","created_at":"2026-05-18T12:31:53.515858+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/X7NJ6LLDVQLHSBHQQM7AL4QAUV","json":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV.json","graph_json":"https://pith.science/api/pith-number/X7NJ6LLDVQLHSBHQQM7AL4QAUV/graph.json","events_json":"https://pith.science/api/pith-number/X7NJ6LLDVQLHSBHQQM7AL4QAUV/events.json","paper":"https://pith.science/paper/X7NJ6LLD"},"agent_actions":{"view_html":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV","download_json":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV.json","view_paper":"https://pith.science/paper/X7NJ6LLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.05230&json=true","fetch_graph":"https://pith.science/api/pith-number/X7NJ6LLDVQLHSBHQQM7AL4QAUV/graph.json","fetch_events":"https://pith.science/api/pith-number/X7NJ6LLDVQLHSBHQQM7AL4QAUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV/action/storage_attestation","attest_author":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV/action/author_attestation","sign_citation":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV/action/citation_signature","submit_replication":"https://pith.science/pith/X7NJ6LLDVQLHSBHQQM7AL4QAUV/action/replication_record"}},"created_at":"2026-05-18T00:12:00.668892+00:00","updated_at":"2026-05-18T00:12:00.668892+00:00"}