{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AO2G6CF6FDBB7PLXAV523TTG3A","short_pith_number":"pith:AO2G6CF6","schema_version":"1.0","canonical_sha256":"03b46f08be28c21fbd77057badce66d80767299c6db2be7002034cff8bf97c55","source":{"kind":"arxiv","id":"1802.05637","version":2},"attestation_state":"computed","paper":{"title":"cGANs with Projection Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masanori Koyama, Takeru Miyato","submitted_at":"2018-02-15T16:19:21Z","abstract_excerpt":"We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the curren"},"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":"1802.05637","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-15T16:19:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"56cbd8c04eff1aa350fdae946e6ea61f7f58d10c7a0a97497edd8c4274fbf52b","abstract_canon_sha256":"6d4dc9c5e6be6abd2bd00b9dfa93430daad6dd5102198805ee40cd2f4069e240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:03.055093Z","signature_b64":"lPAhei5Az2Jx5a3d8xzGaQAbyMaehwB6oS6LzjpSSU/oCq1To/3To+HtwhgoNwnZoxn5Vho2kCDjXUQmF0XOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b46f08be28c21fbd77057badce66d80767299c6db2be7002034cff8bf97c55","last_reissued_at":"2026-05-18T00:08:03.054588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:03.054588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"cGANs with Projection Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masanori Koyama, Takeru Miyato","submitted_at":"2018-02-15T16:19:21Z","abstract_excerpt":"We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the curren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05637","kind":"arxiv","version":2},"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":"1802.05637","created_at":"2026-05-18T00:08:03.054664+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05637v2","created_at":"2026-05-18T00:08:03.054664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05637","created_at":"2026-05-18T00:08:03.054664+00:00"},{"alias_kind":"pith_short_12","alias_value":"AO2G6CF6FDBB","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AO2G6CF6FDBB7PLX","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AO2G6CF6","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.19162","citing_title":"The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2512.05335","citing_title":"State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A","json":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A.json","graph_json":"https://pith.science/api/pith-number/AO2G6CF6FDBB7PLXAV523TTG3A/graph.json","events_json":"https://pith.science/api/pith-number/AO2G6CF6FDBB7PLXAV523TTG3A/events.json","paper":"https://pith.science/paper/AO2G6CF6"},"agent_actions":{"view_html":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A","download_json":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A.json","view_paper":"https://pith.science/paper/AO2G6CF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05637&json=true","fetch_graph":"https://pith.science/api/pith-number/AO2G6CF6FDBB7PLXAV523TTG3A/graph.json","fetch_events":"https://pith.science/api/pith-number/AO2G6CF6FDBB7PLXAV523TTG3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A/action/storage_attestation","attest_author":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A/action/author_attestation","sign_citation":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A/action/citation_signature","submit_replication":"https://pith.science/pith/AO2G6CF6FDBB7PLXAV523TTG3A/action/replication_record"}},"created_at":"2026-05-18T00:08:03.054664+00:00","updated_at":"2026-05-18T00:08:03.054664+00:00"}