{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FVSTP72GMHJ42DMVC42L6SQR4O","short_pith_number":"pith:FVSTP72G","schema_version":"1.0","canonical_sha256":"2d6537ff4661d3cd0d951734bf4a11e3aaf6ad9fab2863d4eaf8371382b95310","source":{"kind":"arxiv","id":"1902.02934","version":1},"attestation_state":"computed","paper":{"title":"Mode Collapse and Regularity of Optimal Transportation Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongsheng An, Na Lei, Shing-Tung Yau, Xianfeng Gu, Xin Qi, Yang Guo, Zhongxuan Luo","submitted_at":"2019-02-08T04:30:38Z","abstract_excerpt":"This work builds the connection between the regularity theory of optimal transportation map, Monge-Amp\\`{e}re equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse.\n  According to the regularity theory of Monge-Amp\\`{e}re equation, if the support of the target measure is disconnected or just non-convex, the optimal transportation mapping is discontinuous. General DNNs can only approximate continuous mappings. This intrinsic conflict leads to the convergence difficulty and mode collapse in GANs.\n  We test our hypothesis"},"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":"1902.02934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T04:30:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"663c19c8cf5bd0c501a1427ad8b45a981f03543024ce08af571d134904f9ddfc","abstract_canon_sha256":"d4a38f54edf4944a24ea79486784de97d0cb20cb8a0e0307feb6f3ecd1415b8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:34.966031Z","signature_b64":"42ZeraA9L6ZYVFEKI3sGpljUknN26VsK8Q7fI1AAk7KeKo0u7tvUBcodMUoNtt6yT15y8sVY7XiDCmMOlMDkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d6537ff4661d3cd0d951734bf4a11e3aaf6ad9fab2863d4eaf8371382b95310","last_reissued_at":"2026-07-04T23:52:34.965500Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:34.965500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mode Collapse and Regularity of Optimal Transportation Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongsheng An, Na Lei, Shing-Tung Yau, Xianfeng Gu, Xin Qi, Yang Guo, Zhongxuan Luo","submitted_at":"2019-02-08T04:30:38Z","abstract_excerpt":"This work builds the connection between the regularity theory of optimal transportation map, Monge-Amp\\`{e}re equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse.\n  According to the regularity theory of Monge-Amp\\`{e}re equation, if the support of the target measure is disconnected or just non-convex, the optimal transportation mapping is discontinuous. General DNNs can only approximate continuous mappings. This intrinsic conflict leads to the convergence difficulty and mode collapse in GANs.\n  We test our hypothesis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02934","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/1902.02934/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":"1902.02934","created_at":"2026-07-04T23:52:34.965558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02934v1","created_at":"2026-07-04T23:52:34.965558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02934","created_at":"2026-07-04T23:52:34.965558+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVSTP72GMHJ4","created_at":"2026-07-04T23:52:34.965558+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVSTP72GMHJ42DMV","created_at":"2026-07-04T23:52:34.965558+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVSTP72G","created_at":"2026-07-04T23:52:34.965558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23429","citing_title":"DPOT: A DeepParticle method for Computation of Optimal Transport with convergence guarantee","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O","json":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O.json","graph_json":"https://pith.science/api/pith-number/FVSTP72GMHJ42DMVC42L6SQR4O/graph.json","events_json":"https://pith.science/api/pith-number/FVSTP72GMHJ42DMVC42L6SQR4O/events.json","paper":"https://pith.science/paper/FVSTP72G"},"agent_actions":{"view_html":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O","download_json":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O.json","view_paper":"https://pith.science/paper/FVSTP72G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02934&json=true","fetch_graph":"https://pith.science/api/pith-number/FVSTP72GMHJ42DMVC42L6SQR4O/graph.json","fetch_events":"https://pith.science/api/pith-number/FVSTP72GMHJ42DMVC42L6SQR4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O/action/storage_attestation","attest_author":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O/action/author_attestation","sign_citation":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O/action/citation_signature","submit_replication":"https://pith.science/pith/FVSTP72GMHJ42DMVC42L6SQR4O/action/replication_record"}},"created_at":"2026-07-04T23:52:34.965558+00:00","updated_at":"2026-07-04T23:52:34.965558+00:00"}