{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:53ZGDHU7V4J46BW7OGD2E45YNI","short_pith_number":"pith:53ZGDHU7","schema_version":"1.0","canonical_sha256":"eef2619e9faf13cf06df7187a273b86a0c10a3cf19481891177ab519b45b92e0","source":{"kind":"arxiv","id":"1705.08850","version":2},"attestation_state":"computed","paper":{"title":"Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Kumar, Prasanna Sattigeri, P. Thomas Fletcher","submitted_at":"2017-05-24T16:35:37Z","abstract_excerpt":"Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while also predicting the class label. Motivated by the ability of the GANs generator to capture the data manifold well, we propose to estimate the tangent space to the data manifold using GANs and employ it to inject invariances into the classifier. In the process, we propose enhancements over existing methods for learning the inverse mapping (i.e., the encoder) whi"},"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":"1705.08850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T16:35:37Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"6fd350bb27b3f4d704b75360683e961cba1c1e7c798f3fe345addabad304c144","abstract_canon_sha256":"234390727539477edfa0a1540afe85a41550f741dbf2e3da7c77b092554ea283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:37.846684Z","signature_b64":"fpiJMpzU2n+EvQks1w9YHaHiSlqm4tdoo+zsZJiaXlfxrv+4+77P/mxUHjbvBTNFw5ATGWQiGWEyh+hfIey4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef2619e9faf13cf06df7187a273b86a0c10a3cf19481891177ab519b45b92e0","last_reissued_at":"2026-05-18T00:13:37.846010Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:37.846010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Kumar, Prasanna Sattigeri, P. Thomas Fletcher","submitted_at":"2017-05-24T16:35:37Z","abstract_excerpt":"Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while also predicting the class label. Motivated by the ability of the GANs generator to capture the data manifold well, we propose to estimate the tangent space to the data manifold using GANs and employ it to inject invariances into the classifier. In the process, we propose enhancements over existing methods for learning the inverse mapping (i.e., the encoder) whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08850","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":"1705.08850","created_at":"2026-05-18T00:13:37.846101+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08850v2","created_at":"2026-05-18T00:13:37.846101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08850","created_at":"2026-05-18T00:13:37.846101+00:00"},{"alias_kind":"pith_short_12","alias_value":"53ZGDHU7V4J4","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"53ZGDHU7V4J46BW7","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"53ZGDHU7","created_at":"2026-05-18T12:31:00.734936+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/53ZGDHU7V4J46BW7OGD2E45YNI","json":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI.json","graph_json":"https://pith.science/api/pith-number/53ZGDHU7V4J46BW7OGD2E45YNI/graph.json","events_json":"https://pith.science/api/pith-number/53ZGDHU7V4J46BW7OGD2E45YNI/events.json","paper":"https://pith.science/paper/53ZGDHU7"},"agent_actions":{"view_html":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI","download_json":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI.json","view_paper":"https://pith.science/paper/53ZGDHU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08850&json=true","fetch_graph":"https://pith.science/api/pith-number/53ZGDHU7V4J46BW7OGD2E45YNI/graph.json","fetch_events":"https://pith.science/api/pith-number/53ZGDHU7V4J46BW7OGD2E45YNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI/action/storage_attestation","attest_author":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI/action/author_attestation","sign_citation":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI/action/citation_signature","submit_replication":"https://pith.science/pith/53ZGDHU7V4J46BW7OGD2E45YNI/action/replication_record"}},"created_at":"2026-05-18T00:13:37.846101+00:00","updated_at":"2026-05-18T00:13:37.846101+00:00"}