{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RRBXXTPDY5INPPHNYLABWHZL72","short_pith_number":"pith:RRBXXTPD","schema_version":"1.0","canonical_sha256":"8c437bcde3c750d7bcedc2c01b1f2bfeb4a52acc950911376f0f1ce2ed936e62","source":{"kind":"arxiv","id":"1611.02163","version":4},"attestation_state":"computed","paper":{"title":"Unrolled Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, David Pfau, Jascha Sohl-Dickstein, Luke Metz","submitted_at":"2016-11-07T16:42:09Z","abstract_excerpt":"We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of t"},"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":"1611.02163","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T16:42:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b81331f8b949e978c697e1719e209841bba52b4304affa7e16e35cb7b1145826","abstract_canon_sha256":"bc48e4f5d61d2ed5e148c2c16946d1f996f276e3f4b473c7f2ecb7899df9a550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:35.230729Z","signature_b64":"kwJ2QAFa8PcKjBEZrqxUJZ/cd425Gkqj6P1LQh4+xtVSdn1ojVQNyiD0Vk11kpNv081+N43tlrkGZHZ303tXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c437bcde3c750d7bcedc2c01b1f2bfeb4a52acc950911376f0f1ce2ed936e62","last_reissued_at":"2026-05-18T00:44:35.230066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:35.230066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unrolled Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, David Pfau, Jascha Sohl-Dickstein, Luke Metz","submitted_at":"2016-11-07T16:42:09Z","abstract_excerpt":"We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02163","kind":"arxiv","version":4},"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":"1611.02163","created_at":"2026-05-18T00:44:35.230179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02163v4","created_at":"2026-05-18T00:44:35.230179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02163","created_at":"2026-05-18T00:44:35.230179+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRBXXTPDY5IN","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRBXXTPDY5INPPHN","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRBXXTPD","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1710.10196","citing_title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04358","citing_title":"Intermediate Representations are Strong AI-Generated Image Detectors","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01361","citing_title":"Decision-Focused Learning via Tangent-Space Projection of Prediction Error","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12273","citing_title":"SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07724","citing_title":"Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72","json":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72.json","graph_json":"https://pith.science/api/pith-number/RRBXXTPDY5INPPHNYLABWHZL72/graph.json","events_json":"https://pith.science/api/pith-number/RRBXXTPDY5INPPHNYLABWHZL72/events.json","paper":"https://pith.science/paper/RRBXXTPD"},"agent_actions":{"view_html":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72","download_json":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72.json","view_paper":"https://pith.science/paper/RRBXXTPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02163&json=true","fetch_graph":"https://pith.science/api/pith-number/RRBXXTPDY5INPPHNYLABWHZL72/graph.json","fetch_events":"https://pith.science/api/pith-number/RRBXXTPDY5INPPHNYLABWHZL72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72/action/storage_attestation","attest_author":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72/action/author_attestation","sign_citation":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72/action/citation_signature","submit_replication":"https://pith.science/pith/RRBXXTPDY5INPPHNYLABWHZL72/action/replication_record"}},"created_at":"2026-05-18T00:44:35.230179+00:00","updated_at":"2026-05-18T00:44:35.230179+00:00"}