{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YXKE2IUG7USDACY276ZPADLVDX","short_pith_number":"pith:YXKE2IUG","schema_version":"1.0","canonical_sha256":"c5d44d2286fd24300b1affb2f00d751dc4128d6542322ae068704c0b5e402ef0","source":{"kind":"arxiv","id":"1911.13060","version":2},"attestation_state":"computed","paper":{"title":"Orthogonal Wasserstein GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan M\\\"uller, Michael Weinmann, Reinhard Klein","submitted_at":"2019-11-29T11:20:12Z","abstract_excerpt":"Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved convergence behaviour and improved image quality. However, Wasserstein-GANs require the discriminator to be Lipschitz continuous. In current state-of-the-art Wasserstein-GANs this constraint is enforced via gradient norm regularization. In this paper, we demonstrate that this regularization does not encourage a broad distribution of spectral-values in the discriminator weights, hence "},"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":"1911.13060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-29T11:20:12Z","cross_cats_sorted":["eess.IV","stat.ML"],"title_canon_sha256":"a4f33c3759e9d46787513ec622eddc37ad7a1f81a09d6d84612fca301484f62d","abstract_canon_sha256":"5720fc9ca42de042b2adf62879c64cd1e049eebf623ebed2c22018a1818ade6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:12.441945Z","signature_b64":"QTfd6HXSl7KYIawaB5ew1sL7BMvfmOsPCh3LnYaB0+OfbQYz/hAKrzIaPKo//+f9O0sTPXZgmZpFkUYrqHFACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5d44d2286fd24300b1affb2f00d751dc4128d6542322ae068704c0b5e402ef0","last_reissued_at":"2026-07-05T00:26:12.441542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:12.441542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orthogonal Wasserstein GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan M\\\"uller, Michael Weinmann, Reinhard Klein","submitted_at":"2019-11-29T11:20:12Z","abstract_excerpt":"Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved convergence behaviour and improved image quality. However, Wasserstein-GANs require the discriminator to be Lipschitz continuous. In current state-of-the-art Wasserstein-GANs this constraint is enforced via gradient norm regularization. In this paper, we demonstrate that this regularization does not encourage a broad distribution of spectral-values in the discriminator weights, hence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.13060","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/1911.13060/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":"1911.13060","created_at":"2026-07-05T00:26:12.441607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.13060v2","created_at":"2026-07-05T00:26:12.441607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.13060","created_at":"2026-07-05T00:26:12.441607+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXKE2IUG7USD","created_at":"2026-07-05T00:26:12.441607+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXKE2IUG7USDACY2","created_at":"2026-07-05T00:26:12.441607+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXKE2IUG","created_at":"2026-07-05T00:26:12.441607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15174","citing_title":"Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX","json":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX.json","graph_json":"https://pith.science/api/pith-number/YXKE2IUG7USDACY276ZPADLVDX/graph.json","events_json":"https://pith.science/api/pith-number/YXKE2IUG7USDACY276ZPADLVDX/events.json","paper":"https://pith.science/paper/YXKE2IUG"},"agent_actions":{"view_html":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX","download_json":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX.json","view_paper":"https://pith.science/paper/YXKE2IUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.13060&json=true","fetch_graph":"https://pith.science/api/pith-number/YXKE2IUG7USDACY276ZPADLVDX/graph.json","fetch_events":"https://pith.science/api/pith-number/YXKE2IUG7USDACY276ZPADLVDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX/action/storage_attestation","attest_author":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX/action/author_attestation","sign_citation":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX/action/citation_signature","submit_replication":"https://pith.science/pith/YXKE2IUG7USDACY276ZPADLVDX/action/replication_record"}},"created_at":"2026-07-05T00:26:12.441607+00:00","updated_at":"2026-07-05T00:26:12.441607+00:00"}