{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HM5INLNFOJOQ6YEU6GFSZN2IOK","short_pith_number":"pith:HM5INLNF","schema_version":"1.0","canonical_sha256":"3b3a86ada5725d0f6094f18b2cb74872a9a65c527b6f671ef8c4c335b316665c","source":{"kind":"arxiv","id":"1709.04794","version":2},"attestation_state":"computed","paper":{"title":"Fast semi-supervised discriminant analysis for binary classification of large data-sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.PF"],"primary_cat":"cs.AI","authors_text":"Hugo Ceulemans, Jaak Simm, Joerg Kurt Wegner, Joris Tavernier, Karl Meerbergen, Yves Moreau","submitted_at":"2017-09-14T13:53:49Z","abstract_excerpt":"High-dimensional data requires scalable algorithms. We propose and analyze three scalable and related algorithms for semi-supervised discriminant analysis (SDA). These methods are based on Krylov subspace methods which exploit the data sparsity and the shift-invariance of Krylov subspaces. In addition, the problem definition was improved by adding centralization to the semi-supervised setting. The proposed methods are evaluated on a industry-scale data set from a pharmaceutical company to predict compound activity on target proteins. The results show that SDA achieves good predictive performan"},"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":"1709.04794","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-14T13:53:49Z","cross_cats_sorted":["cs.NA","cs.PF"],"title_canon_sha256":"419ea266ce600360ed95189a87b7bbffb174ed190068372dc68fbb0625d8ff3f","abstract_canon_sha256":"02cff339f40924305e651e4fa4146fa68edc257b58714d4ef64b77be7490fcd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:11.991856Z","signature_b64":"69mZyTwG1KrpQIUQQJ3dFbmmxPSVMFbGK/rRxZYX+SOFBV1xJjDTtWGxy5mC/wcvNzLmrUxpmEPT4tcHk1lPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b3a86ada5725d0f6094f18b2cb74872a9a65c527b6f671ef8c4c335b316665c","last_reissued_at":"2026-05-17T23:53:11.991130Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:11.991130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast semi-supervised discriminant analysis for binary classification of large data-sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.PF"],"primary_cat":"cs.AI","authors_text":"Hugo Ceulemans, Jaak Simm, Joerg Kurt Wegner, Joris Tavernier, Karl Meerbergen, Yves Moreau","submitted_at":"2017-09-14T13:53:49Z","abstract_excerpt":"High-dimensional data requires scalable algorithms. We propose and analyze three scalable and related algorithms for semi-supervised discriminant analysis (SDA). These methods are based on Krylov subspace methods which exploit the data sparsity and the shift-invariance of Krylov subspaces. In addition, the problem definition was improved by adding centralization to the semi-supervised setting. The proposed methods are evaluated on a industry-scale data set from a pharmaceutical company to predict compound activity on target proteins. The results show that SDA achieves good predictive performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04794","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":""},"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":"1709.04794","created_at":"2026-05-17T23:53:11.991260+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04794v2","created_at":"2026-05-17T23:53:11.991260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04794","created_at":"2026-05-17T23:53:11.991260+00:00"},{"alias_kind":"pith_short_12","alias_value":"HM5INLNFOJOQ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HM5INLNFOJOQ6YEU","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HM5INLNF","created_at":"2026-05-18T12:31:18.294218+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/HM5INLNFOJOQ6YEU6GFSZN2IOK","json":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK.json","graph_json":"https://pith.science/api/pith-number/HM5INLNFOJOQ6YEU6GFSZN2IOK/graph.json","events_json":"https://pith.science/api/pith-number/HM5INLNFOJOQ6YEU6GFSZN2IOK/events.json","paper":"https://pith.science/paper/HM5INLNF"},"agent_actions":{"view_html":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK","download_json":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK.json","view_paper":"https://pith.science/paper/HM5INLNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04794&json=true","fetch_graph":"https://pith.science/api/pith-number/HM5INLNFOJOQ6YEU6GFSZN2IOK/graph.json","fetch_events":"https://pith.science/api/pith-number/HM5INLNFOJOQ6YEU6GFSZN2IOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK/action/storage_attestation","attest_author":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK/action/author_attestation","sign_citation":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK/action/citation_signature","submit_replication":"https://pith.science/pith/HM5INLNFOJOQ6YEU6GFSZN2IOK/action/replication_record"}},"created_at":"2026-05-17T23:53:11.991260+00:00","updated_at":"2026-05-17T23:53:11.991260+00:00"}