{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B2P5ANX27Z4TPYZU4FW6R2YOIC","short_pith_number":"pith:B2P5ANX2","schema_version":"1.0","canonical_sha256":"0e9fd036fafe7937e334e16de8eb0e408d19b4331090291b6a653d068c52bd1b","source":{"kind":"arxiv","id":"2202.00273","version":2},"attestation_state":"computed","paper":{"title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andreas Geiger, Axel Sauer, Katja Schwarz","submitted_at":"2022-02-01T08:22:34Z","abstract_excerpt":"Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN's performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected G"},"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":"2202.00273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-01T08:22:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5caf856fb77b9c1d5f7b170026961097844a641afddb8ca02da13ddf7b682612","abstract_canon_sha256":"9606b37fe9231e36d8143289d1798ec5f8c890b66a67813311263f9579685cff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:32.937754Z","signature_b64":"UCOX+7sziSHdWHBCInBkAztdtJ3lzT/AAfq/bJWT908eCLJhyw9NAmEap5jopqH4Bf9+7CcSZqlm+Q6QHRiJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e9fd036fafe7937e334e16de8eb0e408d19b4331090291b6a653d068c52bd1b","last_reissued_at":"2026-07-05T04:20:32.937242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:32.937242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andreas Geiger, Axel Sauer, Katja Schwarz","submitted_at":"2022-02-01T08:22:34Z","abstract_excerpt":"Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN's performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00273","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/2202.00273/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":"2202.00273","created_at":"2026-07-05T04:20:32.937302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00273v2","created_at":"2026-07-05T04:20:32.937302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00273","created_at":"2026-07-05T04:20:32.937302+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2P5ANX27Z4T","created_at":"2026-07-05T04:20:32.937302+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2P5ANX27Z4TPYZU","created_at":"2026-07-05T04:20:32.937302+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2P5ANX2","created_at":"2026-07-05T04:20:32.937302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC","json":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC.json","graph_json":"https://pith.science/api/pith-number/B2P5ANX27Z4TPYZU4FW6R2YOIC/graph.json","events_json":"https://pith.science/api/pith-number/B2P5ANX27Z4TPYZU4FW6R2YOIC/events.json","paper":"https://pith.science/paper/B2P5ANX2"},"agent_actions":{"view_html":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC","download_json":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC.json","view_paper":"https://pith.science/paper/B2P5ANX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00273&json=true","fetch_graph":"https://pith.science/api/pith-number/B2P5ANX27Z4TPYZU4FW6R2YOIC/graph.json","fetch_events":"https://pith.science/api/pith-number/B2P5ANX27Z4TPYZU4FW6R2YOIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC/action/storage_attestation","attest_author":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC/action/author_attestation","sign_citation":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC/action/citation_signature","submit_replication":"https://pith.science/pith/B2P5ANX27Z4TPYZU4FW6R2YOIC/action/replication_record"}},"created_at":"2026-07-05T04:20:32.937302+00:00","updated_at":"2026-07-05T04:20:32.937302+00:00"}