{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SNKKLGTU7FAQIAFQYOBWOGYI64","short_pith_number":"pith:SNKKLGTU","schema_version":"1.0","canonical_sha256":"9354a59a74f9410400b0c383671b08f700e35c11a1877a51d4aa580c7ea60690","source":{"kind":"arxiv","id":"2112.02424","version":3},"attestation_state":"computed","paper":{"title":"Variational Wasserstein gradient flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Jiaojiao Fan, Qinsheng Zhang, Yongxin Chen","submitted_at":"2021-12-04T20:27:31Z","abstract_excerpt":"Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions. A recent trend is to use the well-known JKO scheme in combination with input convex neural networks to numerically implement the proximal step. The most challenging step, in this setup, is to evaluate functions involving density explicitly, such as entropy, in terms of samples. This paper builds on the recent works with a slight but crucial difference: we propose to utilize a variational formulation of the objective function formulated as maximization over a"},"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":"2112.02424","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-04T20:27:31Z","cross_cats_sorted":[],"title_canon_sha256":"85a8fc145bc5c9ed5097f9a9e99eb5b174497d64dd76671fcfa7e4460828ae67","abstract_canon_sha256":"1e640f7adee0f236898841e4fc886b3a89132eed8df52b779feb7e46f8594765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:57.681423Z","signature_b64":"SsRo5RX+rzXpBldC5/L+wc3J2GQ+OvUsjX3vU3zyJ+lsXUqJsuXrFRanbFLFMXCVot/YEhDfdrBYRL2+gXIQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9354a59a74f9410400b0c383671b08f700e35c11a1877a51d4aa580c7ea60690","last_reissued_at":"2026-07-05T04:42:57.680920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:57.680920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Wasserstein gradient flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amirhossein Taghvaei, Jiaojiao Fan, Qinsheng Zhang, Yongxin Chen","submitted_at":"2021-12-04T20:27:31Z","abstract_excerpt":"Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions. A recent trend is to use the well-known JKO scheme in combination with input convex neural networks to numerically implement the proximal step. The most challenging step, in this setup, is to evaluate functions involving density explicitly, such as entropy, in terms of samples. This paper builds on the recent works with a slight but crucial difference: we propose to utilize a variational formulation of the objective function formulated as maximization over a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02424","kind":"arxiv","version":3},"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/2112.02424/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":"2112.02424","created_at":"2026-07-05T04:42:57.680977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02424v3","created_at":"2026-07-05T04:42:57.680977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02424","created_at":"2026-07-05T04:42:57.680977+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNKKLGTU7FAQ","created_at":"2026-07-05T04:42:57.680977+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNKKLGTU7FAQIAFQ","created_at":"2026-07-05T04:42:57.680977+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNKKLGTU","created_at":"2026-07-05T04:42:57.680977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11755","citing_title":"One-Step Generative Modeling via Wasserstein Gradient Flows","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11755","citing_title":"One-Step Generative Modeling via Wasserstein Gradient Flows","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64","json":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64.json","graph_json":"https://pith.science/api/pith-number/SNKKLGTU7FAQIAFQYOBWOGYI64/graph.json","events_json":"https://pith.science/api/pith-number/SNKKLGTU7FAQIAFQYOBWOGYI64/events.json","paper":"https://pith.science/paper/SNKKLGTU"},"agent_actions":{"view_html":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64","download_json":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64.json","view_paper":"https://pith.science/paper/SNKKLGTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02424&json=true","fetch_graph":"https://pith.science/api/pith-number/SNKKLGTU7FAQIAFQYOBWOGYI64/graph.json","fetch_events":"https://pith.science/api/pith-number/SNKKLGTU7FAQIAFQYOBWOGYI64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64/action/storage_attestation","attest_author":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64/action/author_attestation","sign_citation":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64/action/citation_signature","submit_replication":"https://pith.science/pith/SNKKLGTU7FAQIAFQYOBWOGYI64/action/replication_record"}},"created_at":"2026-07-05T04:42:57.680977+00:00","updated_at":"2026-07-05T04:42:57.680977+00:00"}