{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4AFLTIWZRBGL2KYGMB3MUGQOPF","short_pith_number":"pith:4AFLTIWZ","schema_version":"1.0","canonical_sha256":"e00ab9a2d9884cbd2b066076ca1a0e79583b19e25c59fe0d65c88aded7b3fbd8","source":{"kind":"arxiv","id":"1912.01865","version":2},"attestation_state":"computed","paper":{"title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaejun Yoo, Jung-Woo Ha, Youngjung Uh, Yunjey Choi","submitted_at":"2019-12-04T09:42:22Z","abstract_excerpt":"A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate our superiority in terms of visual quality, diversity, and scalability. To better ass"},"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":"1912.01865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T09:42:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b0b0c1ec147eaa5d62643a627d07165f036913516b2f009f2f32e06bb53e0224","abstract_canon_sha256":"ec4ceaea526182cf0ed9e75f3630fc8efd76a57699bf5751869458cd7bcedc81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:06.492970Z","signature_b64":"nvMV7mX62XkVc34/36wXGQtXLfinMSg/COjJNmYJmG/Np/8ejdamBga0iBZH3PAeWWR3OxnzGzrQ5X/4AuTuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e00ab9a2d9884cbd2b066076ca1a0e79583b19e25c59fe0d65c88aded7b3fbd8","last_reissued_at":"2026-07-05T00:58:06.492623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:06.492623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaejun Yoo, Jung-Woo Ha, Youngjung Uh, Yunjey Choi","submitted_at":"2019-12-04T09:42:22Z","abstract_excerpt":"A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate our superiority in terms of visual quality, diversity, and scalability. To better ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01865","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/1912.01865/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":"1912.01865","created_at":"2026-07-05T00:58:06.492684+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01865v2","created_at":"2026-07-05T00:58:06.492684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01865","created_at":"2026-07-05T00:58:06.492684+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AFLTIWZRBGL","created_at":"2026-07-05T00:58:06.492684+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AFLTIWZRBGL2KYG","created_at":"2026-07-05T00:58:06.492684+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AFLTIWZ","created_at":"2026-07-05T00:58:06.492684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20449","citing_title":"A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF","json":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF.json","graph_json":"https://pith.science/api/pith-number/4AFLTIWZRBGL2KYGMB3MUGQOPF/graph.json","events_json":"https://pith.science/api/pith-number/4AFLTIWZRBGL2KYGMB3MUGQOPF/events.json","paper":"https://pith.science/paper/4AFLTIWZ"},"agent_actions":{"view_html":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF","download_json":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF.json","view_paper":"https://pith.science/paper/4AFLTIWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01865&json=true","fetch_graph":"https://pith.science/api/pith-number/4AFLTIWZRBGL2KYGMB3MUGQOPF/graph.json","fetch_events":"https://pith.science/api/pith-number/4AFLTIWZRBGL2KYGMB3MUGQOPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF/action/storage_attestation","attest_author":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF/action/author_attestation","sign_citation":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF/action/citation_signature","submit_replication":"https://pith.science/pith/4AFLTIWZRBGL2KYGMB3MUGQOPF/action/replication_record"}},"created_at":"2026-07-05T00:58:06.492684+00:00","updated_at":"2026-07-05T00:58:06.492684+00:00"}