{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:T65UGPBAQVQ6RDZY53XBYVRUUO","short_pith_number":"pith:T65UGPBA","schema_version":"1.0","canonical_sha256":"9fbb433c208561e88f38eeee1c5634a3a2f8ef3d7ab858fc438e21e5b5b8161d","source":{"kind":"arxiv","id":"1711.07476","version":2},"attestation_state":"computed","paper":{"title":"Virtual Adversarial Ladder Networks For Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel E. Worrall, Gabriel J. Brostow, Saki Shinoda","submitted_at":"2017-11-20T11:10:40Z","abstract_excerpt":"Semi-supervised learning (SSL) partially circumvents the high cost of labeling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn from the same distribution. This paper offers a novel interpretation of two deep learning-based SSL approaches, ladder networks and virtual adversarial training (VAT), as applying distributional smoothing to their respective latent spaces. We propose a class of models that fuse these approaches. We achieve near-supervised accuracy with high consistency on the MNIST dataset using just 5 labels per class: our best mode"},"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":"1711.07476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-20T11:10:40Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"8e237e5007ea83e608700a895b96e5a49e00fecc6d8a8699793f544a60c91aff","abstract_canon_sha256":"33467640611ebdf8433f01618b7fa009b8d707dd6dbedd592b6c5c6b1aac7dd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:10.218206Z","signature_b64":"AQ+vmMyYSICB5r9E/pds6azi/aPF58kgDAnTRgxxgt+J+a5z2gMPCRIJ3rUvCwNW8627deqwVE7C3+HhgPCoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fbb433c208561e88f38eeee1c5634a3a2f8ef3d7ab858fc438e21e5b5b8161d","last_reissued_at":"2026-05-18T00:28:10.217403Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:10.217403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Virtual Adversarial Ladder Networks For Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel E. Worrall, Gabriel J. Brostow, Saki Shinoda","submitted_at":"2017-11-20T11:10:40Z","abstract_excerpt":"Semi-supervised learning (SSL) partially circumvents the high cost of labeling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn from the same distribution. This paper offers a novel interpretation of two deep learning-based SSL approaches, ladder networks and virtual adversarial training (VAT), as applying distributional smoothing to their respective latent spaces. We propose a class of models that fuse these approaches. We achieve near-supervised accuracy with high consistency on the MNIST dataset using just 5 labels per class: our best mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07476","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":"1711.07476","created_at":"2026-05-18T00:28:10.217513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07476v2","created_at":"2026-05-18T00:28:10.217513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07476","created_at":"2026-05-18T00:28:10.217513+00:00"},{"alias_kind":"pith_short_12","alias_value":"T65UGPBAQVQ6","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"T65UGPBAQVQ6RDZY","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"T65UGPBA","created_at":"2026-05-18T12:31:43.269735+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/T65UGPBAQVQ6RDZY53XBYVRUUO","json":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO.json","graph_json":"https://pith.science/api/pith-number/T65UGPBAQVQ6RDZY53XBYVRUUO/graph.json","events_json":"https://pith.science/api/pith-number/T65UGPBAQVQ6RDZY53XBYVRUUO/events.json","paper":"https://pith.science/paper/T65UGPBA"},"agent_actions":{"view_html":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO","download_json":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO.json","view_paper":"https://pith.science/paper/T65UGPBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07476&json=true","fetch_graph":"https://pith.science/api/pith-number/T65UGPBAQVQ6RDZY53XBYVRUUO/graph.json","fetch_events":"https://pith.science/api/pith-number/T65UGPBAQVQ6RDZY53XBYVRUUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO/action/storage_attestation","attest_author":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO/action/author_attestation","sign_citation":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO/action/citation_signature","submit_replication":"https://pith.science/pith/T65UGPBAQVQ6RDZY53XBYVRUUO/action/replication_record"}},"created_at":"2026-05-18T00:28:10.217513+00:00","updated_at":"2026-05-18T00:28:10.217513+00:00"}