{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T6Z3H6MY6BUUJCSEFRVEE3MGSB","short_pith_number":"pith:T6Z3H6MY","schema_version":"1.0","canonical_sha256":"9fb3b3f998f069448a442c6a426d86905e2f72189bfb45d6a6721cd250d8e36e","source":{"kind":"arxiv","id":"2004.03355","version":3},"attestation_state":"computed","paper":{"title":"Inclusive GAN: Improving Data and Minority Coverage in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jitendra Malik, Ke Li, Larry Davis, Mario Fritz, Ning Yu, Peng Zhou","submitted_at":"2020-04-07T13:31:33Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods "},"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":"2004.03355","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-07T13:31:33Z","cross_cats_sorted":[],"title_canon_sha256":"e15064fe19542dbb61fd77f5df6b4e1fe08fcaa46311d10981663e295dd960a8","abstract_canon_sha256":"0d622345926d3eccb9d27f80015870090784b5986224ad46b44916322d275c4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:04.853142Z","signature_b64":"1MDTa48bdPUwh9n3VV2cj9IiZ7nxfnHV4gIBjkOH/JUL2Uie+NxM1q3953hnGHIWL2Yj+1hdLLVEScvP7m16BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fb3b3f998f069448a442c6a426d86905e2f72189bfb45d6a6721cd250d8e36e","last_reissued_at":"2026-07-05T01:29:04.852656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:04.852656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inclusive GAN: Improving Data and Minority Coverage in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jitendra Malik, Ke Li, Larry Davis, Mario Fritz, Ning Yu, Peng Zhou","submitted_at":"2020-04-07T13:31:33Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03355","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/2004.03355/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":"2004.03355","created_at":"2026-07-05T01:29:04.852713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03355v3","created_at":"2026-07-05T01:29:04.852713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03355","created_at":"2026-07-05T01:29:04.852713+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6Z3H6MY6BUU","created_at":"2026-07-05T01:29:04.852713+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6Z3H6MY6BUUJCSE","created_at":"2026-07-05T01:29:04.852713+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6Z3H6MY","created_at":"2026-07-05T01:29:04.852713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB","json":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB.json","graph_json":"https://pith.science/api/pith-number/T6Z3H6MY6BUUJCSEFRVEE3MGSB/graph.json","events_json":"https://pith.science/api/pith-number/T6Z3H6MY6BUUJCSEFRVEE3MGSB/events.json","paper":"https://pith.science/paper/T6Z3H6MY"},"agent_actions":{"view_html":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB","download_json":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB.json","view_paper":"https://pith.science/paper/T6Z3H6MY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03355&json=true","fetch_graph":"https://pith.science/api/pith-number/T6Z3H6MY6BUUJCSEFRVEE3MGSB/graph.json","fetch_events":"https://pith.science/api/pith-number/T6Z3H6MY6BUUJCSEFRVEE3MGSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB/action/storage_attestation","attest_author":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB/action/author_attestation","sign_citation":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB/action/citation_signature","submit_replication":"https://pith.science/pith/T6Z3H6MY6BUUJCSEFRVEE3MGSB/action/replication_record"}},"created_at":"2026-07-05T01:29:04.852713+00:00","updated_at":"2026-07-05T01:29:04.852713+00:00"}