{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6RIB6MV3IVTEWJDN2F3IUR4A46","short_pith_number":"pith:6RIB6MV3","schema_version":"1.0","canonical_sha256":"f4501f32bb45664b246dd1768a4780e79f814e5d479df42c889ace987c936d14","source":{"kind":"arxiv","id":"1802.10172","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Herve Glotin, Randall Balestriero, Richard Baraniuk","submitted_at":"2018-02-27T21:27:01Z","abstract_excerpt":"Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks. However, their performance relies on the availability of a large set of labeled training data, which limits the breadth of their applicability. Hence, there is a need for new {\\em semi-supervised learning} methods for DNNs that can leverage both (a small amount of) labeled and unlabeled training data. In this paper, we develop a general loss function enabling DNNs of any topology to be trained in a semi-supervised manner without extra hyper-parameters. As opposed to current semi-superv"},"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":"1802.10172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T21:27:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63fc90549c38597008c5acf08a243499bb4991768991bcf1745486ed725ebff2","abstract_canon_sha256":"d0654705ca37cb0d64e97d0556d38fcc5278afe1fe8a4d2d7b1938d69f3b93d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:17.917115Z","signature_b64":"vOdysbblNWo9e6Tezb0XKp6VeKQ09DBa4QGDJHrwT3eVmmc6t+n09suBb1MykQR+7jfWx1IaEezFfSpw1lKfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4501f32bb45664b246dd1768a4780e79f814e5d479df42c889ace987c936d14","last_reissued_at":"2026-05-18T00:22:17.916519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:17.916519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Herve Glotin, Randall Balestriero, Richard Baraniuk","submitted_at":"2018-02-27T21:27:01Z","abstract_excerpt":"Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks. However, their performance relies on the availability of a large set of labeled training data, which limits the breadth of their applicability. Hence, there is a need for new {\\em semi-supervised learning} methods for DNNs that can leverage both (a small amount of) labeled and unlabeled training data. In this paper, we develop a general loss function enabling DNNs of any topology to be trained in a semi-supervised manner without extra hyper-parameters. As opposed to current semi-superv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10172","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":"1802.10172","created_at":"2026-05-18T00:22:17.916617+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10172v1","created_at":"2026-05-18T00:22:17.916617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10172","created_at":"2026-05-18T00:22:17.916617+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RIB6MV3IVTE","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RIB6MV3IVTEWJDN","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RIB6MV3","created_at":"2026-05-18T12:32:11.075285+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/6RIB6MV3IVTEWJDN2F3IUR4A46","json":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46.json","graph_json":"https://pith.science/api/pith-number/6RIB6MV3IVTEWJDN2F3IUR4A46/graph.json","events_json":"https://pith.science/api/pith-number/6RIB6MV3IVTEWJDN2F3IUR4A46/events.json","paper":"https://pith.science/paper/6RIB6MV3"},"agent_actions":{"view_html":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46","download_json":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46.json","view_paper":"https://pith.science/paper/6RIB6MV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10172&json=true","fetch_graph":"https://pith.science/api/pith-number/6RIB6MV3IVTEWJDN2F3IUR4A46/graph.json","fetch_events":"https://pith.science/api/pith-number/6RIB6MV3IVTEWJDN2F3IUR4A46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46/action/storage_attestation","attest_author":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46/action/author_attestation","sign_citation":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46/action/citation_signature","submit_replication":"https://pith.science/pith/6RIB6MV3IVTEWJDN2F3IUR4A46/action/replication_record"}},"created_at":"2026-05-18T00:22:17.916617+00:00","updated_at":"2026-05-18T00:22:17.916617+00:00"}