{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OVJUM7RENCJ52HZBDSUOLDYISW","short_pith_number":"pith:OVJUM7RE","schema_version":"1.0","canonical_sha256":"7553467e246893dd1f211ca8e58f08959447a56237d837d3a818e1a8fa5b544c","source":{"kind":"arxiv","id":"1703.00573","version":5},"attestation_state":"computed","paper":{"title":"Generalization and Equilibrium in Generative Adversarial Nets (GANs)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rong Ge, Sanjeev Arora, Tengyu Ma, Yingyu Liang, Yi Zhang","submitted_at":"2017-03-02T01:14:03Z","abstract_excerpt":"We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is also shown that an approximate pure equilibrium exists in the discriminator/generator game for a special class of generators with natural training objectives when generator capacity and training set sizes are moderate.\n  This existence of equilibrium inspires MIX+GAN protocol, 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":"1703.00573","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T01:14:03Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"3b5672a95b7acba93422adaf5982577b8a72d406f2d95f20b98c1742e4724ed4","abstract_canon_sha256":"aa24e77e27e57c8ade648fc51fa53534e4bac04286827fa080ed573bc6df97d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:46.188899Z","signature_b64":"/uoTPL9nn/eeSD97CcwS79yRsJEtQh5ahtySCXwLGxLJ3fgJHN8p54HULcIpW96vGguJyl3SdaQrYGQs2yo4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7553467e246893dd1f211ca8e58f08959447a56237d837d3a818e1a8fa5b544c","last_reissued_at":"2026-05-18T00:38:46.188261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:46.188261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization and Equilibrium in Generative Adversarial Nets (GANs)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rong Ge, Sanjeev Arora, Tengyu Ma, Yingyu Liang, Yi Zhang","submitted_at":"2017-03-02T01:14:03Z","abstract_excerpt":"We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is also shown that an approximate pure equilibrium exists in the discriminator/generator game for a special class of generators with natural training objectives when generator capacity and training set sizes are moderate.\n  This existence of equilibrium inspires MIX+GAN protocol, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00573","kind":"arxiv","version":5},"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":"1703.00573","created_at":"2026-05-18T00:38:46.188373+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00573v5","created_at":"2026-05-18T00:38:46.188373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00573","created_at":"2026-05-18T00:38:46.188373+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVJUM7RENCJ5","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVJUM7RENCJ52HZB","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVJUM7RE","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1801.01401","citing_title":"Demystifying MMD GANs","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW","json":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW.json","graph_json":"https://pith.science/api/pith-number/OVJUM7RENCJ52HZBDSUOLDYISW/graph.json","events_json":"https://pith.science/api/pith-number/OVJUM7RENCJ52HZBDSUOLDYISW/events.json","paper":"https://pith.science/paper/OVJUM7RE"},"agent_actions":{"view_html":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW","download_json":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW.json","view_paper":"https://pith.science/paper/OVJUM7RE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00573&json=true","fetch_graph":"https://pith.science/api/pith-number/OVJUM7RENCJ52HZBDSUOLDYISW/graph.json","fetch_events":"https://pith.science/api/pith-number/OVJUM7RENCJ52HZBDSUOLDYISW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW/action/storage_attestation","attest_author":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW/action/author_attestation","sign_citation":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW/action/citation_signature","submit_replication":"https://pith.science/pith/OVJUM7RENCJ52HZBDSUOLDYISW/action/replication_record"}},"created_at":"2026-05-18T00:38:46.188373+00:00","updated_at":"2026-05-18T00:38:46.188373+00:00"}