{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6HXNZPTAY7ECNGPPSCFC22Y2IV","short_pith_number":"pith:6HXNZPTA","schema_version":"1.0","canonical_sha256":"f1eedcbe60c7c82699ef908a2d6b1a455ee7f825ce59d71828fb40f4d61a38ad","source":{"kind":"arxiv","id":"1807.00734","version":3},"attestation_state":"computed","paper":{"title":"The relativistic discriminator: a key element missing from standard GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau","submitted_at":"2018-07-02T15:11:23Z","abstract_excerpt":"In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also simultaneously decrease the probability that real data is real because 1) this would account for a priori knowledge that half of the data in the mini-batch is fake, 2) this would be observed with divergence minimization, and 3) in optimal settings, SGAN would be equivalent to integral probability metric (IPM) GANs.\n  We show that this property can be induced by using "},"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":"1807.00734","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T15:11:23Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"aa5298d664b09699793c740c08b66547a377de89714ed6533eb9131f1ec48c24","abstract_canon_sha256":"38b6e1bc7e7d3519a0dbe0bdfd37700a9070c9947306aa38685563df5355b97e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:11.265879Z","signature_b64":"VQPGoNFzkSmKcRTB8xnbzTzSdZM/XUbdF/vPm5Sw9TVVi6t5YP1w96S2xEPLmhu4aGdp+AqQwi60+jLvz37dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1eedcbe60c7c82699ef908a2d6b1a455ee7f825ce59d71828fb40f4d61a38ad","last_reissued_at":"2026-05-18T00:06:11.265114Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:11.265114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The relativistic discriminator: a key element missing from standard GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau","submitted_at":"2018-07-02T15:11:23Z","abstract_excerpt":"In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also simultaneously decrease the probability that real data is real because 1) this would account for a priori knowledge that half of the data in the mini-batch is fake, 2) this would be observed with divergence minimization, and 3) in optimal settings, SGAN would be equivalent to integral probability metric (IPM) GANs.\n  We show that this property can be induced by using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00734","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":"1807.00734","created_at":"2026-05-18T00:06:11.265244+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00734v3","created_at":"2026-05-18T00:06:11.265244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00734","created_at":"2026-05-18T00:06:11.265244+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HXNZPTAY7EC","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HXNZPTAY7ECNGPP","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HXNZPTA","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.09909","citing_title":"Deep Exemplar-based Video Colorization","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07863","citing_title":"Diving Deeper into Underwater Image Enhancement: A Survey","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01273","citing_title":"Learning Stratigraphically Consistent Relative Geologic Time from 3D Seismic Data via Sinusoidal Mapping","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2508.14950","citing_title":"Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26342","citing_title":"Which Face and Whose Identity? Solving the Dual Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01273","citing_title":"Learning Stratigraphically Consistent Relative Geologic Time from 3D Seismic Data via Sinusoidal Mapping","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01273","citing_title":"Learning Stratigraphically Consistent Relative Geologic Time from 3D Seismic Data via Sinusoidal Mapping","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11521","citing_title":"Continuous Adversarial Flow Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20130","citing_title":"Pairing Regularization for Mitigating Many-to-One Collapse in GANs","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV","json":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV.json","graph_json":"https://pith.science/api/pith-number/6HXNZPTAY7ECNGPPSCFC22Y2IV/graph.json","events_json":"https://pith.science/api/pith-number/6HXNZPTAY7ECNGPPSCFC22Y2IV/events.json","paper":"https://pith.science/paper/6HXNZPTA"},"agent_actions":{"view_html":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV","download_json":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV.json","view_paper":"https://pith.science/paper/6HXNZPTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00734&json=true","fetch_graph":"https://pith.science/api/pith-number/6HXNZPTAY7ECNGPPSCFC22Y2IV/graph.json","fetch_events":"https://pith.science/api/pith-number/6HXNZPTAY7ECNGPPSCFC22Y2IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV/action/storage_attestation","attest_author":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV/action/author_attestation","sign_citation":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV/action/citation_signature","submit_replication":"https://pith.science/pith/6HXNZPTAY7ECNGPPSCFC22Y2IV/action/replication_record"}},"created_at":"2026-05-18T00:06:11.265244+00:00","updated_at":"2026-05-18T00:06:11.265244+00:00"}