{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AJ3FOJTHMW5IIKDTJBCPALFOOQ","short_pith_number":"pith:AJ3FOJTH","schema_version":"1.0","canonical_sha256":"027657266765ba8428734844f02cae7432846144248b1988ad8aa0691100f648","source":{"kind":"arxiv","id":"1705.09783","version":3},"attestation_state":"computed","paper":{"title":"Good Semi-supervised Learning that Requires a Bad GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Yang, Ruslan Salakhutdinov, William W. Cohen, Zhilin Yang, Zihang Dai","submitted_at":"2017-05-27T07:53:53Z","abstract_excerpt":"Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time. Theoretically, we show that given the discriminator objective, good semisupervised learning indeed requires a bad generator, and propose the definition of a preferred generator. Empirically, we derive a novel formulation based on our analysis that substantially improves over"},"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":"1705.09783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-27T07:53:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2b7c54ef4756134fe7d3d5808a1b7790666e9329015394dd0783219f31d9c38","abstract_canon_sha256":"f4754a96c3db275690bcb13aee261bf1cef23115e26e02a6c337898b49b92cd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:23.715571Z","signature_b64":"9iL6QdubSpKLGCfdwoChl+1//piaEhNMgtPfuW8J5r9FNYUnvSUndm4WtGL3KNyW2/CJfMl117C2eW10V3v7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027657266765ba8428734844f02cae7432846144248b1988ad8aa0691100f648","last_reissued_at":"2026-05-18T00:31:23.715149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:23.715149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good Semi-supervised Learning that Requires a Bad GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Yang, Ruslan Salakhutdinov, William W. Cohen, Zhilin Yang, Zihang Dai","submitted_at":"2017-05-27T07:53:53Z","abstract_excerpt":"Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time. Theoretically, we show that given the discriminator objective, good semisupervised learning indeed requires a bad generator, and propose the definition of a preferred generator. Empirically, we derive a novel formulation based on our analysis that substantially improves over"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09783","kind":"arxiv","version":3},"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":"1705.09783","created_at":"2026-05-18T00:31:23.715211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09783v3","created_at":"2026-05-18T00:31:23.715211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09783","created_at":"2026-05-18T00:31:23.715211+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ3FOJTHMW5I","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ3FOJTHMW5IIKDT","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ3FOJTH","created_at":"2026-05-18T12:31:05.417338+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/AJ3FOJTHMW5IIKDTJBCPALFOOQ","json":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ.json","graph_json":"https://pith.science/api/pith-number/AJ3FOJTHMW5IIKDTJBCPALFOOQ/graph.json","events_json":"https://pith.science/api/pith-number/AJ3FOJTHMW5IIKDTJBCPALFOOQ/events.json","paper":"https://pith.science/paper/AJ3FOJTH"},"agent_actions":{"view_html":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ","download_json":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ.json","view_paper":"https://pith.science/paper/AJ3FOJTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09783&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ3FOJTHMW5IIKDTJBCPALFOOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ3FOJTHMW5IIKDTJBCPALFOOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ/action/storage_attestation","attest_author":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ/action/author_attestation","sign_citation":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ/action/citation_signature","submit_replication":"https://pith.science/pith/AJ3FOJTHMW5IIKDTJBCPALFOOQ/action/replication_record"}},"created_at":"2026-05-18T00:31:23.715211+00:00","updated_at":"2026-05-18T00:31:23.715211+00:00"}