{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TKDFJDPZAERW5UFHYALADONHVR","short_pith_number":"pith:TKDFJDPZ","schema_version":"1.0","canonical_sha256":"9a86548df901236ed0a7c01601b9a7ac68142ba41f0453d0d3e7e34af4ad850d","source":{"kind":"arxiv","id":"2002.07501","version":1},"attestation_state":"computed","paper":{"title":"A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Zhang, Jun Zhu, Shuyu Cheng, Yueru Li, Ziyu Wang","submitted_at":"2020-02-18T11:40:26Z","abstract_excerpt":"Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior."},"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":"2002.07501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-18T11:40:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd35f6dccb1590e476e45ee86019d4dc2a7a687ab496cdd9320f4374d2b5a37e","abstract_canon_sha256":"ce6e495237b5d499e45d8c07fbd7ca4b6a1269f2ec6989b4c5b7933d6b46f6d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:02.790352Z","signature_b64":"n9AHCfpQya7NluKg6guDjYy18SqBpHHDNZwfC/mPu/28sTHU43IpSK2+EomW4ov/G+HYn23tlVEGuWrirhs2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a86548df901236ed0a7c01601b9a7ac68142ba41f0453d0d3e7e34af4ad850d","last_reissued_at":"2026-07-05T00:42:02.789537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:02.789537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Zhang, Jun Zhu, Shuyu Cheng, Yueru Li, Ziyu Wang","submitted_at":"2020-02-18T11:40:26Z","abstract_excerpt":"Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07501","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/2002.07501/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":"2002.07501","created_at":"2026-07-05T00:42:02.789601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07501v1","created_at":"2026-07-05T00:42:02.789601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07501","created_at":"2026-07-05T00:42:02.789601+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKDFJDPZAERW","created_at":"2026-07-05T00:42:02.789601+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKDFJDPZAERW5UFH","created_at":"2026-07-05T00:42:02.789601+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKDFJDPZ","created_at":"2026-07-05T00:42:02.789601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR","json":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR.json","graph_json":"https://pith.science/api/pith-number/TKDFJDPZAERW5UFHYALADONHVR/graph.json","events_json":"https://pith.science/api/pith-number/TKDFJDPZAERW5UFHYALADONHVR/events.json","paper":"https://pith.science/paper/TKDFJDPZ"},"agent_actions":{"view_html":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR","download_json":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR.json","view_paper":"https://pith.science/paper/TKDFJDPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07501&json=true","fetch_graph":"https://pith.science/api/pith-number/TKDFJDPZAERW5UFHYALADONHVR/graph.json","fetch_events":"https://pith.science/api/pith-number/TKDFJDPZAERW5UFHYALADONHVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR/action/storage_attestation","attest_author":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR/action/author_attestation","sign_citation":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR/action/citation_signature","submit_replication":"https://pith.science/pith/TKDFJDPZAERW5UFHYALADONHVR/action/replication_record"}},"created_at":"2026-07-05T00:42:02.789601+00:00","updated_at":"2026-07-05T00:42:02.789601+00:00"}