{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SF3SH3OARIQ7MMIDTFBQQNOT5S","short_pith_number":"pith:SF3SH3OA","schema_version":"1.0","canonical_sha256":"917723edc08a21f6310399430835d3ecb79ac0d3c77bea67b42e6384fe651be6","source":{"kind":"arxiv","id":"2002.04185","version":1},"attestation_state":"computed","paper":{"title":"Smoothness and Stability in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Casey Chu, Kenji Fukumizu, Kentaro Minami","submitted_at":"2020-02-11T03:08:28Z","abstract_excerpt":"Generative adversarial networks, or GANs, commonly display unstable behavior during training. In this work, we develop a principled theoretical framework for understanding the stability of various types of GANs. In particular, we derive conditions that guarantee eventual stationarity of the generator when it is trained with gradient descent, conditions that must be satisfied by the divergence that is minimized by the GAN and the generator's architecture. We find that existing GAN variants satisfy some, but not all, of these conditions. Using tools from convex analysis, optimal transport, and r"},"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":"2002.04185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-11T03:08:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"325ee06fc87f58624b6562bafb2914b9ca831ea5efa7084b95c2ad10349af18f","abstract_canon_sha256":"eb03ea49242e073a26850212354e73a5addb75f238d69004960830bced6b94ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:42.959998Z","signature_b64":"ix72cwbFzp3yX+lpBk9/7LD2wNqeNTJVAQSaFdnoVjXn7YrIpDZqFl2piJntW1DJW4nWfUWYFOEmWFgDOr0OCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917723edc08a21f6310399430835d3ecb79ac0d3c77bea67b42e6384fe651be6","last_reissued_at":"2026-07-05T00:39:42.959575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:42.959575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smoothness and Stability in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Casey Chu, Kenji Fukumizu, Kentaro Minami","submitted_at":"2020-02-11T03:08:28Z","abstract_excerpt":"Generative adversarial networks, or GANs, commonly display unstable behavior during training. In this work, we develop a principled theoretical framework for understanding the stability of various types of GANs. In particular, we derive conditions that guarantee eventual stationarity of the generator when it is trained with gradient descent, conditions that must be satisfied by the divergence that is minimized by the GAN and the generator's architecture. We find that existing GAN variants satisfy some, but not all, of these conditions. Using tools from convex analysis, optimal transport, and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04185","kind":"arxiv","version":1},"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/2002.04185/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":"2002.04185","created_at":"2026-07-05T00:39:42.959637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04185v1","created_at":"2026-07-05T00:39:42.959637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04185","created_at":"2026-07-05T00:39:42.959637+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF3SH3OARIQ7","created_at":"2026-07-05T00:39:42.959637+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF3SH3OARIQ7MMID","created_at":"2026-07-05T00:39:42.959637+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF3SH3OA","created_at":"2026-07-05T00:39:42.959637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S","json":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S.json","graph_json":"https://pith.science/api/pith-number/SF3SH3OARIQ7MMIDTFBQQNOT5S/graph.json","events_json":"https://pith.science/api/pith-number/SF3SH3OARIQ7MMIDTFBQQNOT5S/events.json","paper":"https://pith.science/paper/SF3SH3OA"},"agent_actions":{"view_html":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S","download_json":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S.json","view_paper":"https://pith.science/paper/SF3SH3OA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04185&json=true","fetch_graph":"https://pith.science/api/pith-number/SF3SH3OARIQ7MMIDTFBQQNOT5S/graph.json","fetch_events":"https://pith.science/api/pith-number/SF3SH3OARIQ7MMIDTFBQQNOT5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S/action/storage_attestation","attest_author":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S/action/author_attestation","sign_citation":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S/action/citation_signature","submit_replication":"https://pith.science/pith/SF3SH3OARIQ7MMIDTFBQQNOT5S/action/replication_record"}},"created_at":"2026-07-05T00:39:42.959637+00:00","updated_at":"2026-07-05T00:39:42.959637+00:00"}