{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MQTRPNHTB4Q4447SOZ6EXSWYTS","short_pith_number":"pith:MQTRPNHT","schema_version":"1.0","canonical_sha256":"642717b4f30f21ce73f2767c4bcad89ca57dedc4f3143e297e11702853b066f0","source":{"kind":"arxiv","id":"2010.10013","version":3},"attestation_state":"computed","paper":{"title":"Training Generative Adversarial Networks via stochastic Nash games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC"],"primary_cat":"cs.LG","authors_text":"Barbara Franci, Sergio Grammatico","submitted_at":"2020-10-17T09:07:40Z","abstract_excerpt":"Generative adversarial networks (GANs) are a class of generative models with two antagonistic neural networks: a generator and a discriminator. These two neural networks compete against each other through an adversarial process that can be modeled as a stochastic Nash equilibrium problem. Since the associated training process is challenging, it is fundamental to design reliable algorithms to compute an equilibrium. In this paper, we propose a stochastic relaxed forward-backward (SRFB) algorithm for GANs and we show convergence to an exact solution when an increasing number of data is available"},"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":"2010.10013","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T09:07:40Z","cross_cats_sorted":["cs.GT","math.OC"],"title_canon_sha256":"eaacb9c15edeff7a801e8dbfbff63893ad97c86792f9b49998ff2e8f5bd16cb9","abstract_canon_sha256":"4b79d7186fdbd942d1ca0d84ddf6a2433612df6f03d81acdb1512361a0c3ca2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:02.471506Z","signature_b64":"OiGseRJ6JZvA9Ztg25ZnXWLOJwq6Ctnl2kvvsZKuUZC0Aszh+PXbYmdPUsK9mViVbAymTmYUEViZ4tsMXkqEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"642717b4f30f21ce73f2767c4bcad89ca57dedc4f3143e297e11702853b066f0","last_reissued_at":"2026-07-05T02:42:02.471064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:02.471064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Generative Adversarial Networks via stochastic Nash games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC"],"primary_cat":"cs.LG","authors_text":"Barbara Franci, Sergio Grammatico","submitted_at":"2020-10-17T09:07:40Z","abstract_excerpt":"Generative adversarial networks (GANs) are a class of generative models with two antagonistic neural networks: a generator and a discriminator. These two neural networks compete against each other through an adversarial process that can be modeled as a stochastic Nash equilibrium problem. Since the associated training process is challenging, it is fundamental to design reliable algorithms to compute an equilibrium. In this paper, we propose a stochastic relaxed forward-backward (SRFB) algorithm for GANs and we show convergence to an exact solution when an increasing number of data is available"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10013","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.10013/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.10013","created_at":"2026-07-05T02:42:02.471118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.10013v3","created_at":"2026-07-05T02:42:02.471118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10013","created_at":"2026-07-05T02:42:02.471118+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQTRPNHTB4Q4","created_at":"2026-07-05T02:42:02.471118+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQTRPNHTB4Q4447S","created_at":"2026-07-05T02:42:02.471118+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQTRPNHT","created_at":"2026-07-05T02:42:02.471118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11318","citing_title":"Nested Annealed Training Scheme for Generative Adversarial Networks","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS","json":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS.json","graph_json":"https://pith.science/api/pith-number/MQTRPNHTB4Q4447SOZ6EXSWYTS/graph.json","events_json":"https://pith.science/api/pith-number/MQTRPNHTB4Q4447SOZ6EXSWYTS/events.json","paper":"https://pith.science/paper/MQTRPNHT"},"agent_actions":{"view_html":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS","download_json":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS.json","view_paper":"https://pith.science/paper/MQTRPNHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.10013&json=true","fetch_graph":"https://pith.science/api/pith-number/MQTRPNHTB4Q4447SOZ6EXSWYTS/graph.json","fetch_events":"https://pith.science/api/pith-number/MQTRPNHTB4Q4447SOZ6EXSWYTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS/action/storage_attestation","attest_author":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS/action/author_attestation","sign_citation":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS/action/citation_signature","submit_replication":"https://pith.science/pith/MQTRPNHTB4Q4447SOZ6EXSWYTS/action/replication_record"}},"created_at":"2026-07-05T02:42:02.471118+00:00","updated_at":"2026-07-05T02:42:02.471118+00:00"}