{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OGSDHMJ5HTMWWDN3GXGPDR7CAI","short_pith_number":"pith:OGSDHMJ5","schema_version":"1.0","canonical_sha256":"71a433b13d3cd96b0dbb35ccf1c7e2023f61a413d208f9f0c2a481df7f2e9864","source":{"kind":"arxiv","id":"1709.09782","version":1},"attestation_state":"computed","paper":{"title":"Structure-aware error bounds for linear classification with the zero-one loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Ata Kaban, Robert J. Durrant","submitted_at":"2017-09-28T02:07:02Z","abstract_excerpt":"We prove risk bounds for binary classification in high-dimensional settings when the sample size is allowed to be smaller than the dimensionality of the training set observations. In particular, we prove upper bounds for both 'compressive learning' by empirical risk minimization (ERM) (that is when the ERM classifier is learned from data that have been projected from high-dimensions onto a randomly selected low-dimensional subspace) as well as uniform upper bounds in the full high-dimensional space. A novel tool we employ in both settings is the 'flipping probability' of Durrant and Kaban (ICM"},"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":"1709.09782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-28T02:07:02Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"c90a9deb9baa22ff8e55ada6542320f57cd8cf706eb73b2925e350968cf32474","abstract_canon_sha256":"40670b216d4413051a553a8b432fd63adf70ff2a896cce31a12e5ebaacffe91e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:06.779730Z","signature_b64":"Gj2ee2NqDiyHDe5lpuEHZvLZ9KoDSpVw/f+lO6+o5w2RS40kgWkVsUo5teWC4JCDF6DUT5cajpYUE0ku1unhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71a433b13d3cd96b0dbb35ccf1c7e2023f61a413d208f9f0c2a481df7f2e9864","last_reissued_at":"2026-05-18T00:34:06.778696Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:06.778696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-aware error bounds for linear classification with the zero-one loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Ata Kaban, Robert J. Durrant","submitted_at":"2017-09-28T02:07:02Z","abstract_excerpt":"We prove risk bounds for binary classification in high-dimensional settings when the sample size is allowed to be smaller than the dimensionality of the training set observations. In particular, we prove upper bounds for both 'compressive learning' by empirical risk minimization (ERM) (that is when the ERM classifier is learned from data that have been projected from high-dimensions onto a randomly selected low-dimensional subspace) as well as uniform upper bounds in the full high-dimensional space. A novel tool we employ in both settings is the 'flipping probability' of Durrant and Kaban (ICM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09782","kind":"arxiv","version":1},"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":"1709.09782","created_at":"2026-05-18T00:34:06.778793+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.09782v1","created_at":"2026-05-18T00:34:06.778793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09782","created_at":"2026-05-18T00:34:06.778793+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGSDHMJ5HTMW","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGSDHMJ5HTMWWDN3","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGSDHMJ5","created_at":"2026-05-18T12:31:34.259226+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/OGSDHMJ5HTMWWDN3GXGPDR7CAI","json":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI.json","graph_json":"https://pith.science/api/pith-number/OGSDHMJ5HTMWWDN3GXGPDR7CAI/graph.json","events_json":"https://pith.science/api/pith-number/OGSDHMJ5HTMWWDN3GXGPDR7CAI/events.json","paper":"https://pith.science/paper/OGSDHMJ5"},"agent_actions":{"view_html":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI","download_json":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI.json","view_paper":"https://pith.science/paper/OGSDHMJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.09782&json=true","fetch_graph":"https://pith.science/api/pith-number/OGSDHMJ5HTMWWDN3GXGPDR7CAI/graph.json","fetch_events":"https://pith.science/api/pith-number/OGSDHMJ5HTMWWDN3GXGPDR7CAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI/action/storage_attestation","attest_author":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI/action/author_attestation","sign_citation":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI/action/citation_signature","submit_replication":"https://pith.science/pith/OGSDHMJ5HTMWWDN3GXGPDR7CAI/action/replication_record"}},"created_at":"2026-05-18T00:34:06.778793+00:00","updated_at":"2026-05-18T00:34:06.778793+00:00"}