{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:I65C2IN3Q6DKH3OLTM4IXOQ2FM","short_pith_number":"pith:I65C2IN3","schema_version":"1.0","canonical_sha256":"47ba2d21bb8786a3edcb9b388bba1a2b3f2d6fd98f6ff1db23ec4c528b01fac8","source":{"kind":"arxiv","id":"1704.02906","version":3},"attestation_state":"computed","paper":{"title":"Multi-Agent Diverse Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arnab Ghosh, Philip H. S. Torr, Puneet K. Dokania, Vinay Namboodiri, Viveka Kulharia","submitted_at":"2017-04-10T15:26:23Z","abstract_excerpt":"We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different generators capture diverse high probability modes, the discriminator of MAD-GAN is designed such that along with finding the real and fake samples, it is also required to identify the generator that generated the given fake sample. Intuitively, to succeed in this task, the discriminat"},"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":"1704.02906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:26:23Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","stat.ML"],"title_canon_sha256":"1828d83212f2e58fb0ed94a79b526ea0044243b740730942fd66aad63f61ff72","abstract_canon_sha256":"6714c6f1ca975462a3c168481ed55b6aa770112ccd8b1ef12d5603dc07a23556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:47.812766Z","signature_b64":"1BTcxzngjd/5U+Z5McD2QsSncNN+15PmpBRYn0r4gTbCiLigVwFJ56QgnUXBHPxRoShOn/coG+bW3WcU16rOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47ba2d21bb8786a3edcb9b388bba1a2b3f2d6fd98f6ff1db23ec4c528b01fac8","last_reissued_at":"2026-05-18T00:10:47.812116Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:47.812116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Diverse Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arnab Ghosh, Philip H. S. Torr, Puneet K. Dokania, Vinay Namboodiri, Viveka Kulharia","submitted_at":"2017-04-10T15:26:23Z","abstract_excerpt":"We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different generators capture diverse high probability modes, the discriminator of MAD-GAN is designed such that along with finding the real and fake samples, it is also required to identify the generator that generated the given fake sample. Intuitively, to succeed in this task, the discriminat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02906","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":"1704.02906","created_at":"2026-05-18T00:10:47.812211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02906v3","created_at":"2026-05-18T00:10:47.812211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02906","created_at":"2026-05-18T00:10:47.812211+00:00"},{"alias_kind":"pith_short_12","alias_value":"I65C2IN3Q6DK","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"I65C2IN3Q6DKH3OL","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"I65C2IN3","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1710.10196","citing_title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM","json":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM.json","graph_json":"https://pith.science/api/pith-number/I65C2IN3Q6DKH3OLTM4IXOQ2FM/graph.json","events_json":"https://pith.science/api/pith-number/I65C2IN3Q6DKH3OLTM4IXOQ2FM/events.json","paper":"https://pith.science/paper/I65C2IN3"},"agent_actions":{"view_html":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM","download_json":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM.json","view_paper":"https://pith.science/paper/I65C2IN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02906&json=true","fetch_graph":"https://pith.science/api/pith-number/I65C2IN3Q6DKH3OLTM4IXOQ2FM/graph.json","fetch_events":"https://pith.science/api/pith-number/I65C2IN3Q6DKH3OLTM4IXOQ2FM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM/action/storage_attestation","attest_author":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM/action/author_attestation","sign_citation":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM/action/citation_signature","submit_replication":"https://pith.science/pith/I65C2IN3Q6DKH3OLTM4IXOQ2FM/action/replication_record"}},"created_at":"2026-05-18T00:10:47.812211+00:00","updated_at":"2026-05-18T00:10:47.812211+00:00"}