{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SQ7BFPDPVHWNF3VR3EDJTJXXSY","short_pith_number":"pith:SQ7BFPDP","schema_version":"1.0","canonical_sha256":"943e12bc6fa9ecd2eeb1d90699a6f7963188d828b797ce45dcc1550febcd940f","source":{"kind":"arxiv","id":"2002.07284","version":2},"attestation_state":"computed","paper":{"title":"Sharp Asymptotics and Optimal Performance for Inference in Binary Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Christos Thrampoulidis, Hossein Taheri, Ramtin Pedarsani","submitted_at":"2020-02-17T22:32:14Z","abstract_excerpt":"We study convex empirical risk minimization for high-dimensional inference in binary models. Our first result sharply predicts the statistical performance of such estimators in the linear asymptotic regime under isotropic Gaussian features. Importantly, the predictions hold for a wide class of convex loss functions, which we exploit in order to prove a bound on the best achievable performance among them. Notably, we show that the proposed bound is tight for popular binary models (such as Signed, Logistic or Probit), by constructing appropriate loss functions that achieve it. More interestingly"},"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":"2002.07284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-02-17T22:32:14Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML","stat.TH"],"title_canon_sha256":"c4eeab8164495e0c854f49befaff400387deb6c4560f6afec4ebe2b3cf958d4c","abstract_canon_sha256":"dcc33fe7014423e0a81917957ac68f6b2b9ba95802c7d0ed62d113b89d02b567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:58.161824Z","signature_b64":"ke/YsU7DzkQUfADRCfB1fLoRVJZm0znpyCGmkWlSUO1wgpPhtyxZKMbTiApJhviCwq800Apt27N30IZbI3nPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"943e12bc6fa9ecd2eeb1d90699a6f7963188d828b797ce45dcc1550febcd940f","last_reissued_at":"2026-07-05T00:43:58.161310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:58.161310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp Asymptotics and Optimal Performance for Inference in Binary Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Christos Thrampoulidis, Hossein Taheri, Ramtin Pedarsani","submitted_at":"2020-02-17T22:32:14Z","abstract_excerpt":"We study convex empirical risk minimization for high-dimensional inference in binary models. Our first result sharply predicts the statistical performance of such estimators in the linear asymptotic regime under isotropic Gaussian features. Importantly, the predictions hold for a wide class of convex loss functions, which we exploit in order to prove a bound on the best achievable performance among them. Notably, we show that the proposed bound is tight for popular binary models (such as Signed, Logistic or Probit), by constructing appropriate loss functions that achieve it. More interestingly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07284","kind":"arxiv","version":2},"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/2002.07284/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":"2002.07284","created_at":"2026-07-05T00:43:58.161386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07284v2","created_at":"2026-07-05T00:43:58.161386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07284","created_at":"2026-07-05T00:43:58.161386+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQ7BFPDPVHWN","created_at":"2026-07-05T00:43:58.161386+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQ7BFPDPVHWNF3VR","created_at":"2026-07-05T00:43:58.161386+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQ7BFPDP","created_at":"2026-07-05T00:43:58.161386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20025","citing_title":"Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY","json":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY.json","graph_json":"https://pith.science/api/pith-number/SQ7BFPDPVHWNF3VR3EDJTJXXSY/graph.json","events_json":"https://pith.science/api/pith-number/SQ7BFPDPVHWNF3VR3EDJTJXXSY/events.json","paper":"https://pith.science/paper/SQ7BFPDP"},"agent_actions":{"view_html":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY","download_json":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY.json","view_paper":"https://pith.science/paper/SQ7BFPDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07284&json=true","fetch_graph":"https://pith.science/api/pith-number/SQ7BFPDPVHWNF3VR3EDJTJXXSY/graph.json","fetch_events":"https://pith.science/api/pith-number/SQ7BFPDPVHWNF3VR3EDJTJXXSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY/action/storage_attestation","attest_author":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY/action/author_attestation","sign_citation":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY/action/citation_signature","submit_replication":"https://pith.science/pith/SQ7BFPDPVHWNF3VR3EDJTJXXSY/action/replication_record"}},"created_at":"2026-07-05T00:43:58.161386+00:00","updated_at":"2026-07-05T00:43:58.161386+00:00"}