{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RGIOAGJGLYMSZSHJIVEHQL6V7K","short_pith_number":"pith:RGIOAGJG","schema_version":"1.0","canonical_sha256":"8990e019265e192cc8e94548782fd5fa80d38f384fb56dc5e3750482f22d44e9","source":{"kind":"arxiv","id":"1809.05957","version":1},"attestation_state":"computed","paper":{"title":"A Deep Generative Model for Semi-Supervised Classification with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edouard Mehlman, Jeffrey Regier, Maxime Langevin, Michael I. Jordan, Nir Yosef, Romain Lopez","submitted_at":"2018-09-16T21:04:47Z","abstract_excerpt":"Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for label noise. Additionally, the derivation of M-VAE gives new theoretical insights into the popular M1+M2 semi-supervised model."},"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":"1809.05957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-16T21:04:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"492e09c45b6e4d6967d6e772d4d35c5bda733a0102f7214ab37d85cc3d523e68","abstract_canon_sha256":"80e55e66d6ded694af37cfc67357b918ecd58bb6caf17a3c8cb84db94a8fc212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:36.029491Z","signature_b64":"86rPX8R7fpXJSXQ4VBsSNum/WvH4Ovp92VdNItlSYcR+U822o+SADD8gfsdelgKAzcbqbEqP8osOg0Ew8KcjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8990e019265e192cc8e94548782fd5fa80d38f384fb56dc5e3750482f22d44e9","last_reissued_at":"2026-05-18T00:05:36.029095Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:36.029095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Generative Model for Semi-Supervised Classification with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edouard Mehlman, Jeffrey Regier, Maxime Langevin, Michael I. Jordan, Nir Yosef, Romain Lopez","submitted_at":"2018-09-16T21:04:47Z","abstract_excerpt":"Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for label noise. Additionally, the derivation of M-VAE gives new theoretical insights into the popular M1+M2 semi-supervised model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05957","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":"1809.05957","created_at":"2026-05-18T00:05:36.029163+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05957v1","created_at":"2026-05-18T00:05:36.029163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05957","created_at":"2026-05-18T00:05:36.029163+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGIOAGJGLYMS","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGIOAGJGLYMSZSHJ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGIOAGJG","created_at":"2026-05-18T12:32:50.500415+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/RGIOAGJGLYMSZSHJIVEHQL6V7K","json":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K.json","graph_json":"https://pith.science/api/pith-number/RGIOAGJGLYMSZSHJIVEHQL6V7K/graph.json","events_json":"https://pith.science/api/pith-number/RGIOAGJGLYMSZSHJIVEHQL6V7K/events.json","paper":"https://pith.science/paper/RGIOAGJG"},"agent_actions":{"view_html":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K","download_json":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K.json","view_paper":"https://pith.science/paper/RGIOAGJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05957&json=true","fetch_graph":"https://pith.science/api/pith-number/RGIOAGJGLYMSZSHJIVEHQL6V7K/graph.json","fetch_events":"https://pith.science/api/pith-number/RGIOAGJGLYMSZSHJIVEHQL6V7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K/action/storage_attestation","attest_author":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K/action/author_attestation","sign_citation":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K/action/citation_signature","submit_replication":"https://pith.science/pith/RGIOAGJGLYMSZSHJIVEHQL6V7K/action/replication_record"}},"created_at":"2026-05-18T00:05:36.029163+00:00","updated_at":"2026-05-18T00:05:36.029163+00:00"}