{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:536RJEIFETMLEN5KTXMSLFRU4D","short_pith_number":"pith:536RJEIF","schema_version":"1.0","canonical_sha256":"eefd14910524d8b237aa9dd9259634e0c452d8f402f0742c05b262cd2cb99bf1","source":{"kind":"arxiv","id":"1712.02505","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning with IPM-based GANs: an Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tom Sercu, Youssef Mroueh","submitted_at":"2017-12-07T06:27:28Z","abstract_excerpt":"We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning. IPM-based GANs like Wasserstein GAN, Fisher GAN and Sobolev GAN have desirable properties in terms of theoretical understanding, training stability, and a meaningful loss. In this work we investigate how the design of the critic (or discriminator) influences the performance in semi-supervised learning. We distill three key take-aways which are important for good SSL performance: (1) the K+1 formulation, (2"},"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":"1712.02505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-07T06:27:28Z","cross_cats_sorted":[],"title_canon_sha256":"cb3cce8ea91b8d2055c65b733c899f8298553ac9fdc4dc5f76c30b92d5d0c983","abstract_canon_sha256":"6c700ac71cc66d1e015042b79037dd5bcf442a2ab8db6608f4a3dc64de1a1a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:33.818879Z","signature_b64":"FLls+g/kgCHiEtExq6fWt3KTcoUssB2cl2HAzyQ8R/LqYZDRW1jvEwdgzu4t3QFnucZfoknNVe5x9kVmD9HRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eefd14910524d8b237aa9dd9259634e0c452d8f402f0742c05b262cd2cb99bf1","last_reissued_at":"2026-05-18T00:28:33.818112Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:33.818112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning with IPM-based GANs: an Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tom Sercu, Youssef Mroueh","submitted_at":"2017-12-07T06:27:28Z","abstract_excerpt":"We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning. IPM-based GANs like Wasserstein GAN, Fisher GAN and Sobolev GAN have desirable properties in terms of theoretical understanding, training stability, and a meaningful loss. In this work we investigate how the design of the critic (or discriminator) influences the performance in semi-supervised learning. We distill three key take-aways which are important for good SSL performance: (1) the K+1 formulation, (2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02505","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":"1712.02505","created_at":"2026-05-18T00:28:33.818235+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.02505v1","created_at":"2026-05-18T00:28:33.818235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02505","created_at":"2026-05-18T00:28:33.818235+00:00"},{"alias_kind":"pith_short_12","alias_value":"536RJEIFETML","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"536RJEIFETMLEN5K","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"536RJEIF","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/536RJEIFETMLEN5KTXMSLFRU4D","json":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D.json","graph_json":"https://pith.science/api/pith-number/536RJEIFETMLEN5KTXMSLFRU4D/graph.json","events_json":"https://pith.science/api/pith-number/536RJEIFETMLEN5KTXMSLFRU4D/events.json","paper":"https://pith.science/paper/536RJEIF"},"agent_actions":{"view_html":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D","download_json":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D.json","view_paper":"https://pith.science/paper/536RJEIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.02505&json=true","fetch_graph":"https://pith.science/api/pith-number/536RJEIFETMLEN5KTXMSLFRU4D/graph.json","fetch_events":"https://pith.science/api/pith-number/536RJEIFETMLEN5KTXMSLFRU4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D/action/storage_attestation","attest_author":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D/action/author_attestation","sign_citation":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D/action/citation_signature","submit_replication":"https://pith.science/pith/536RJEIFETMLEN5KTXMSLFRU4D/action/replication_record"}},"created_at":"2026-05-18T00:28:33.818235+00:00","updated_at":"2026-05-18T00:28:33.818235+00:00"}