{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F7NMDQKOAJUVEMMYHYRFKDVTUP","short_pith_number":"pith:F7NMDQKO","schema_version":"1.0","canonical_sha256":"2fdac1c14e02695231983e22550eb3a3c9bbab6bd822a6542a1d3e9fc0691d50","source":{"kind":"arxiv","id":"1901.08560","version":3},"attestation_state":"computed","paper":{"title":"Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher C Holmes, Matthew Willetts, Stephen J Roberts","submitted_at":"2019-01-24T18:24:39Z","abstract_excerpt":"In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the case that some classes of data are found only in the unlabelled dataset -- perhaps the labelling process was biased -- so we do not have any labelled examples to train on for some classes. We call this learning regime $\\textit{semi-unsupervised learning}$, an extreme case of semi-supervised learning, where some classes have no labelled exemplars in the train"},"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":"1901.08560","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-24T18:24:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b959cc4494554fb03a568b21c6864d8536a22c5dde62d22b9608157cca6f333","abstract_canon_sha256":"9b3d4566d0512192936c01915da5626919acb43abe5b43c74eb333ea476122f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:21.926714Z","signature_b64":"J9bjzMgQWYMmAzjJ15V6F/RMi3oTE+MyfUtFZnc4H1I2D+xLwWYxHUtPkhhorldGNF4pWvclUPt//D1T0AmaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fdac1c14e02695231983e22550eb3a3c9bbab6bd822a6542a1d3e9fc0691d50","last_reissued_at":"2026-07-05T02:05:21.926210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:21.926210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher C Holmes, Matthew Willetts, Stephen J Roberts","submitted_at":"2019-01-24T18:24:39Z","abstract_excerpt":"In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the case that some classes of data are found only in the unlabelled dataset -- perhaps the labelling process was biased -- so we do not have any labelled examples to train on for some classes. We call this learning regime $\\textit{semi-unsupervised learning}$, an extreme case of semi-supervised learning, where some classes have no labelled exemplars in the train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08560","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1901.08560/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":"1901.08560","created_at":"2026-07-05T02:05:21.926265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08560v3","created_at":"2026-07-05T02:05:21.926265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08560","created_at":"2026-07-05T02:05:21.926265+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7NMDQKOAJUV","created_at":"2026-07-05T02:05:21.926265+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7NMDQKOAJUVEMMY","created_at":"2026-07-05T02:05:21.926265+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7NMDQKO","created_at":"2026-07-05T02:05:21.926265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03015","citing_title":"Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP","json":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP.json","graph_json":"https://pith.science/api/pith-number/F7NMDQKOAJUVEMMYHYRFKDVTUP/graph.json","events_json":"https://pith.science/api/pith-number/F7NMDQKOAJUVEMMYHYRFKDVTUP/events.json","paper":"https://pith.science/paper/F7NMDQKO"},"agent_actions":{"view_html":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP","download_json":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP.json","view_paper":"https://pith.science/paper/F7NMDQKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08560&json=true","fetch_graph":"https://pith.science/api/pith-number/F7NMDQKOAJUVEMMYHYRFKDVTUP/graph.json","fetch_events":"https://pith.science/api/pith-number/F7NMDQKOAJUVEMMYHYRFKDVTUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP/action/storage_attestation","attest_author":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP/action/author_attestation","sign_citation":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP/action/citation_signature","submit_replication":"https://pith.science/pith/F7NMDQKOAJUVEMMYHYRFKDVTUP/action/replication_record"}},"created_at":"2026-07-05T02:05:21.926265+00:00","updated_at":"2026-07-05T02:05:21.926265+00:00"}