{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JMCZRMPPQPYEFXH6S2X2ULJWBT","short_pith_number":"pith:JMCZRMPP","schema_version":"1.0","canonical_sha256":"4b0598b1ef83f042dcfe96afaa2d360ccd2e5d9f9097e753fe45d28c57362578","source":{"kind":"arxiv","id":"1908.03015","version":2},"attestation_state":"computed","paper":{"title":"Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominik Gei{\\ss}ler, Felix Berkhahn, Nikhil Shetty, Richard Keys, Wajih Ouertani","submitted_at":"2019-08-08T11:07:22Z","abstract_excerpt":"We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also the classification performance. Vice versa, every label not only improves classification, but also unsupervised tasks. The proposed architecture is simple: A classification layer is connected to the topmost encoder layer, and then combined with the resampled latent layer for the decoder. The usual evidence lower bound (ELBO) loss is supplemented with a supe"},"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":"1908.03015","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-08T11:07:22Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"c714a1e13a5fa009cc6156d1540bd4c0beb9f8bb223730377efa886e4ac1960e","abstract_canon_sha256":"19d7f3891dd317e7e80777c6bc9c93bf24b640e802224c2efeaefb1050d75e9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:09.962088Z","signature_b64":"ps3dR2gQSkKZ/Ouu+tUZQENBULG5GM+sJM8wo2UDrobFlbnYyWdvcJOmBuB7su1rG1b4g9SlJ3//kLmGSxdEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0598b1ef83f042dcfe96afaa2d360ccd2e5d9f9097e753fe45d28c57362578","last_reissued_at":"2026-07-05T00:19:09.961686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:09.961686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominik Gei{\\ss}ler, Felix Berkhahn, Nikhil Shetty, Richard Keys, Wajih Ouertani","submitted_at":"2019-08-08T11:07:22Z","abstract_excerpt":"We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also the classification performance. Vice versa, every label not only improves classification, but also unsupervised tasks. The proposed architecture is simple: A classification layer is connected to the topmost encoder layer, and then combined with the resampled latent layer for the decoder. The usual evidence lower bound (ELBO) loss is supplemented with a supe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03015","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.03015/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":"1908.03015","created_at":"2026-07-05T00:19:09.961745+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03015v2","created_at":"2026-07-05T00:19:09.961745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03015","created_at":"2026-07-05T00:19:09.961745+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMCZRMPPQPYE","created_at":"2026-07-05T00:19:09.961745+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMCZRMPPQPYEFXH6","created_at":"2026-07-05T00:19:09.961745+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMCZRMPP","created_at":"2026-07-05T00:19:09.961745+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/JMCZRMPPQPYEFXH6S2X2ULJWBT","json":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT.json","graph_json":"https://pith.science/api/pith-number/JMCZRMPPQPYEFXH6S2X2ULJWBT/graph.json","events_json":"https://pith.science/api/pith-number/JMCZRMPPQPYEFXH6S2X2ULJWBT/events.json","paper":"https://pith.science/paper/JMCZRMPP"},"agent_actions":{"view_html":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT","download_json":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT.json","view_paper":"https://pith.science/paper/JMCZRMPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03015&json=true","fetch_graph":"https://pith.science/api/pith-number/JMCZRMPPQPYEFXH6S2X2ULJWBT/graph.json","fetch_events":"https://pith.science/api/pith-number/JMCZRMPPQPYEFXH6S2X2ULJWBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT/action/storage_attestation","attest_author":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT/action/author_attestation","sign_citation":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT/action/citation_signature","submit_replication":"https://pith.science/pith/JMCZRMPPQPYEFXH6S2X2ULJWBT/action/replication_record"}},"created_at":"2026-07-05T00:19:09.961745+00:00","updated_at":"2026-07-05T00:19:09.961745+00:00"}