{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:74LGOGVLHP2EADBRFALVCPS5OO","short_pith_number":"pith:74LGOGVL","schema_version":"1.0","canonical_sha256":"ff16671aab3bf4400c312817513e5d739440fd2b1abfa13fed38eae58d68952c","source":{"kind":"arxiv","id":"1910.12027","version":2},"attestation_state":"computed","paper":{"title":"Consistency Regularization for Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Augustus Odena, Han Zhang, Honglak Lee, Zizhao Zhang","submitted_at":"2019-10-26T09:06:03Z","abstract_excerpt":"Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization---a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of "},"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":"1910.12027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-26T09:06:03Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"f2e459af991210c2e091515cd2bc250bb39f767d7c3237cfee82d979126c1e99","abstract_canon_sha256":"c5f0186e2bc1f6301c325bffe90c0e8ad4ec990b405c8857234490f840e8ddb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:21.215493Z","signature_b64":"8/DQq10aVZVm7ibN9vuHDk720up1a5W7/i7ee5Ax8WY0BVa8X94+8NY7Ncjfnektt7pV8ZIn/ppoyvCT0NFpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff16671aab3bf4400c312817513e5d739440fd2b1abfa13fed38eae58d68952c","last_reissued_at":"2026-07-05T00:42:21.215035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:21.215035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Regularization for Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Augustus Odena, Han Zhang, Honglak Lee, Zizhao Zhang","submitted_at":"2019-10-26T09:06:03Z","abstract_excerpt":"Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization---a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12027","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/1910.12027/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":"1910.12027","created_at":"2026-07-05T00:42:21.215089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12027v2","created_at":"2026-07-05T00:42:21.215089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12027","created_at":"2026-07-05T00:42:21.215089+00:00"},{"alias_kind":"pith_short_12","alias_value":"74LGOGVLHP2E","created_at":"2026-07-05T00:42:21.215089+00:00"},{"alias_kind":"pith_short_16","alias_value":"74LGOGVLHP2EADBR","created_at":"2026-07-05T00:42:21.215089+00:00"},{"alias_kind":"pith_short_8","alias_value":"74LGOGVL","created_at":"2026-07-05T00:42:21.215089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06678","citing_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO","json":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO.json","graph_json":"https://pith.science/api/pith-number/74LGOGVLHP2EADBRFALVCPS5OO/graph.json","events_json":"https://pith.science/api/pith-number/74LGOGVLHP2EADBRFALVCPS5OO/events.json","paper":"https://pith.science/paper/74LGOGVL"},"agent_actions":{"view_html":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO","download_json":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO.json","view_paper":"https://pith.science/paper/74LGOGVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12027&json=true","fetch_graph":"https://pith.science/api/pith-number/74LGOGVLHP2EADBRFALVCPS5OO/graph.json","fetch_events":"https://pith.science/api/pith-number/74LGOGVLHP2EADBRFALVCPS5OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO/action/storage_attestation","attest_author":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO/action/author_attestation","sign_citation":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO/action/citation_signature","submit_replication":"https://pith.science/pith/74LGOGVLHP2EADBRFALVCPS5OO/action/replication_record"}},"created_at":"2026-07-05T00:42:21.215089+00:00","updated_at":"2026-07-05T00:42:21.215089+00:00"}