{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FN662YCQRJ4RUJHA2BYIH4EC6V","short_pith_number":"pith:FN662YCQ","schema_version":"1.0","canonical_sha256":"2b7ded60508a791a24e0d07083f082f5641f1ecac698d6eb737baaa6144b4add","source":{"kind":"arxiv","id":"2509.24935","version":2},"attestation_state":"computed","paper":{"title":"Scalable GANs with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jae-Pil Heo, MinKyu Lee, Sangeek Hyun","submitted_at":"2025-09-29T15:36:15Z","abstract_excerpt":"Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigate the scalability of Generative Adversarial Networks (GANs) through two design choices that have proven to be effective in other types of generative models: training in a compact Variational Autoencoder latent space and adopting purely transformer-based generators and discriminators. Training in latent space enables efficient computation while preserving perceptual fidelity, and this efficiency pairs naturally with plain transformers, whose performance s"},"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":"2509.24935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-29T15:36:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a66341a2be47a5402e4bf96642577f2231017261d4259338ea469bef260dfce0","abstract_canon_sha256":"bc269413b89da9c7b5d3019103f25813c68b9bab6bcc4814d467415ea7e12091"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:51.320656Z","signature_b64":"/kG7cmUq3CMpPw34yA0nTiOSVQhaE/iS9B2pQ8gpRtyGfJWMzE0433hzQ3larEykD/n70jN6BErqEiyB7jTSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b7ded60508a791a24e0d07083f082f5641f1ecac698d6eb737baaa6144b4add","last_reissued_at":"2026-05-27T01:04:51.319958Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:51.319958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable GANs with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jae-Pil Heo, MinKyu Lee, Sangeek Hyun","submitted_at":"2025-09-29T15:36:15Z","abstract_excerpt":"Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigate the scalability of Generative Adversarial Networks (GANs) through two design choices that have proven to be effective in other types of generative models: training in a compact Variational Autoencoder latent space and adopting purely transformer-based generators and discriminators. Training in latent space enables efficient computation while preserving perceptual fidelity, and this efficiency pairs naturally with plain transformers, whose performance s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24935","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.24935/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":"2509.24935","created_at":"2026-05-27T01:04:51.320059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24935v2","created_at":"2026-05-27T01:04:51.320059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24935","created_at":"2026-05-27T01:04:51.320059+00:00"},{"alias_kind":"pith_short_12","alias_value":"FN662YCQRJ4R","created_at":"2026-05-27T01:04:51.320059+00:00"},{"alias_kind":"pith_short_16","alias_value":"FN662YCQRJ4RUJHA","created_at":"2026-05-27T01:04:51.320059+00:00"},{"alias_kind":"pith_short_8","alias_value":"FN662YCQ","created_at":"2026-05-27T01:04:51.320059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.11521","citing_title":"Continuous Adversarial Flow Models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V","json":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V.json","graph_json":"https://pith.science/api/pith-number/FN662YCQRJ4RUJHA2BYIH4EC6V/graph.json","events_json":"https://pith.science/api/pith-number/FN662YCQRJ4RUJHA2BYIH4EC6V/events.json","paper":"https://pith.science/paper/FN662YCQ"},"agent_actions":{"view_html":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V","download_json":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V.json","view_paper":"https://pith.science/paper/FN662YCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24935&json=true","fetch_graph":"https://pith.science/api/pith-number/FN662YCQRJ4RUJHA2BYIH4EC6V/graph.json","fetch_events":"https://pith.science/api/pith-number/FN662YCQRJ4RUJHA2BYIH4EC6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V/action/storage_attestation","attest_author":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V/action/author_attestation","sign_citation":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V/action/citation_signature","submit_replication":"https://pith.science/pith/FN662YCQRJ4RUJHA2BYIH4EC6V/action/replication_record"}},"created_at":"2026-05-27T01:04:51.320059+00:00","updated_at":"2026-05-27T01:04:51.320059+00:00"}