{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:HDFT3SUMFRBJQDPSZ4UIC2YUFV","short_pith_number":"pith:HDFT3SUM","schema_version":"1.0","canonical_sha256":"38cb3dca8c2c42980df2cf28816b142d407f98a5cd8117e830ca689ce738a36c","source":{"kind":"arxiv","id":"1202.1574","version":3},"attestation_state":"computed","paper":{"title":"Classification with High-Dimensional Sparse Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","math.ST","stat.TH"],"primary_cat":"cs.IT","authors_text":"Dayu Huang, Sean Meyn","submitted_at":"2012-02-08T01:32:24Z","abstract_excerpt":"The task of the binary classification problem is to determine which of two distributions has generated a length-$n$ test sequence. The two distributions are unknown; two training sequences of length $N$, one from each distribution, are observed. The distributions share an alphabet of size $m$, which is significantly larger than $n$ and $N$. How does $N,n,m$ affect the probability of classification error? We characterize the achievable error rate in a high-dimensional setting in which $N,n,m$ all tend to infinity, under the assumption that probability of any symbol is $O(m^{-1})$. The results a"},"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":"1202.1574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2012-02-08T01:32:24Z","cross_cats_sorted":["math.IT","math.ST","stat.TH"],"title_canon_sha256":"3b0c22e4e61906f01f909e83a46edac72949bbdac616455b55951f5be976968c","abstract_canon_sha256":"45b5b290b6a99e5ef01b3c31263270fdb3e65d12140604e721eb52b5d0c76d7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:05.920399Z","signature_b64":"kwAPYzmtqYSkA4814OUuNB4DZ81qOmubKIvjVaK7kMHw479yj9pRKjX2i7JKY+AKCURPU+4LPK+esc3a0BiHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38cb3dca8c2c42980df2cf28816b142d407f98a5cd8117e830ca689ce738a36c","last_reissued_at":"2026-05-18T01:17:05.919651Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:05.919651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification with High-Dimensional Sparse Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT","math.ST","stat.TH"],"primary_cat":"cs.IT","authors_text":"Dayu Huang, Sean Meyn","submitted_at":"2012-02-08T01:32:24Z","abstract_excerpt":"The task of the binary classification problem is to determine which of two distributions has generated a length-$n$ test sequence. The two distributions are unknown; two training sequences of length $N$, one from each distribution, are observed. The distributions share an alphabet of size $m$, which is significantly larger than $n$ and $N$. How does $N,n,m$ affect the probability of classification error? We characterize the achievable error rate in a high-dimensional setting in which $N,n,m$ all tend to infinity, under the assumption that probability of any symbol is $O(m^{-1})$. The results a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1574","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":"1202.1574","created_at":"2026-05-18T01:17:05.919773+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.1574v3","created_at":"2026-05-18T01:17:05.919773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1574","created_at":"2026-05-18T01:17:05.919773+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDFT3SUMFRBJ","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDFT3SUMFRBJQDPS","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDFT3SUM","created_at":"2026-05-18T12:27:09.501522+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/HDFT3SUMFRBJQDPSZ4UIC2YUFV","json":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV.json","graph_json":"https://pith.science/api/pith-number/HDFT3SUMFRBJQDPSZ4UIC2YUFV/graph.json","events_json":"https://pith.science/api/pith-number/HDFT3SUMFRBJQDPSZ4UIC2YUFV/events.json","paper":"https://pith.science/paper/HDFT3SUM"},"agent_actions":{"view_html":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV","download_json":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV.json","view_paper":"https://pith.science/paper/HDFT3SUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.1574&json=true","fetch_graph":"https://pith.science/api/pith-number/HDFT3SUMFRBJQDPSZ4UIC2YUFV/graph.json","fetch_events":"https://pith.science/api/pith-number/HDFT3SUMFRBJQDPSZ4UIC2YUFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV/action/storage_attestation","attest_author":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV/action/author_attestation","sign_citation":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV/action/citation_signature","submit_replication":"https://pith.science/pith/HDFT3SUMFRBJQDPSZ4UIC2YUFV/action/replication_record"}},"created_at":"2026-05-18T01:17:05.919773+00:00","updated_at":"2026-05-18T01:17:05.919773+00:00"}