{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GKDQFJHHEPEF3NDXIGSLXOCFOT","short_pith_number":"pith:GKDQFJHH","schema_version":"1.0","canonical_sha256":"328702a4e723c85db47741a4bbb84574e1251c2117bc2d51bd2f548715218387","source":{"kind":"arxiv","id":"1907.09607","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Linwei Wang, Prashnna Kumar Gyawali, Sandesh Ghimire, Zhiyuan Li","submitted_at":"2019-07-22T22:19:04Z","abstract_excerpt":"The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In thi"},"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":"1907.09607","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-22T22:19:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0784ca8124152ebe7b425df83a4df562350a36ff837ed2585af80e584da960ed","abstract_canon_sha256":"74777276a1a2b5da113e624f6f290dda3a746a7ee497b7295318cca22f1168cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:52.761078Z","signature_b64":"LerK0VhnyaageICcDt3aKS6GAeHsFdRrGQenqaHvcdeRMATBwISaZUv28H6P4dwRZbfvR13/nCUHFuzZ8DX3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"328702a4e723c85db47741a4bbb84574e1251c2117bc2d51bd2f548715218387","last_reissued_at":"2026-05-17T23:39:52.760555Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:52.760555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Linwei Wang, Prashnna Kumar Gyawali, Sandesh Ghimire, Zhiyuan Li","submitted_at":"2019-07-22T22:19:04Z","abstract_excerpt":"The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09607","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":"1907.09607","created_at":"2026-05-17T23:39:52.760621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09607v1","created_at":"2026-05-17T23:39:52.760621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09607","created_at":"2026-05-17T23:39:52.760621+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKDQFJHHEPEF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKDQFJHHEPEF3NDX","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKDQFJHH","created_at":"2026-05-18T12:33:18.533446+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/GKDQFJHHEPEF3NDXIGSLXOCFOT","json":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT.json","graph_json":"https://pith.science/api/pith-number/GKDQFJHHEPEF3NDXIGSLXOCFOT/graph.json","events_json":"https://pith.science/api/pith-number/GKDQFJHHEPEF3NDXIGSLXOCFOT/events.json","paper":"https://pith.science/paper/GKDQFJHH"},"agent_actions":{"view_html":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT","download_json":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT.json","view_paper":"https://pith.science/paper/GKDQFJHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09607&json=true","fetch_graph":"https://pith.science/api/pith-number/GKDQFJHHEPEF3NDXIGSLXOCFOT/graph.json","fetch_events":"https://pith.science/api/pith-number/GKDQFJHHEPEF3NDXIGSLXOCFOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT/action/storage_attestation","attest_author":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT/action/author_attestation","sign_citation":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT/action/citation_signature","submit_replication":"https://pith.science/pith/GKDQFJHHEPEF3NDXIGSLXOCFOT/action/replication_record"}},"created_at":"2026-05-17T23:39:52.760621+00:00","updated_at":"2026-05-17T23:39:52.760621+00:00"}