{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WW5FNND644KXUJ7ST4DUB3VMKW","short_pith_number":"pith:WW5FNND6","schema_version":"1.0","canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","source":{"kind":"arxiv","id":"1711.04313","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning via New Deep Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Herve G. Glotin, Randall Balestriero, Richard G. Baraniuk, Vincent Roger","submitted_at":"2017-11-12T15:42:24Z","abstract_excerpt":"We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching $99.14\\%$ of test set accuracy while using $5$ labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture."},"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":"1711.04313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T15:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ff6f4ed6b66d65f4515430833a1fcd9858ab1388257e3a8b92ba3b26ef64e28","abstract_canon_sha256":"f2d57d7cda1e2280241b1a7dc34fb9bb6c8184faf50d3bc80e93fceaf27cd5e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:39.441519Z","signature_b64":"GztWv1E6LylxNMhvlpVZLoEyZgnkb2zqDr9cDoNrM2ZnahclYGO6awqbImWp8JO83liY6LqnNsvbwevsvSAyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ba56b47ee7157a27f29f0740eeac55a5e70d47285434a508e2bfb1f27515fb","last_reissued_at":"2026-05-18T00:30:39.440770Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:39.440770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning via New Deep Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Herve G. Glotin, Randall Balestriero, Richard G. Baraniuk, Vincent Roger","submitted_at":"2017-11-12T15:42:24Z","abstract_excerpt":"We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching $99.14\\%$ of test set accuracy while using $5$ labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04313","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":"1711.04313","created_at":"2026-05-18T00:30:39.440895+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04313v1","created_at":"2026-05-18T00:30:39.440895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04313","created_at":"2026-05-18T00:30:39.440895+00:00"},{"alias_kind":"pith_short_12","alias_value":"WW5FNND644KX","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WW5FNND644KXUJ7S","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WW5FNND6","created_at":"2026-05-18T12:31:53.515858+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/WW5FNND644KXUJ7ST4DUB3VMKW","json":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW.json","graph_json":"https://pith.science/api/pith-number/WW5FNND644KXUJ7ST4DUB3VMKW/graph.json","events_json":"https://pith.science/api/pith-number/WW5FNND644KXUJ7ST4DUB3VMKW/events.json","paper":"https://pith.science/paper/WW5FNND6"},"agent_actions":{"view_html":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW","download_json":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW.json","view_paper":"https://pith.science/paper/WW5FNND6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04313&json=true","fetch_graph":"https://pith.science/api/pith-number/WW5FNND644KXUJ7ST4DUB3VMKW/graph.json","fetch_events":"https://pith.science/api/pith-number/WW5FNND644KXUJ7ST4DUB3VMKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/action/storage_attestation","attest_author":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/action/author_attestation","sign_citation":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/action/citation_signature","submit_replication":"https://pith.science/pith/WW5FNND644KXUJ7ST4DUB3VMKW/action/replication_record"}},"created_at":"2026-05-18T00:30:39.440895+00:00","updated_at":"2026-05-18T00:30:39.440895+00:00"}