{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YY4DJDKX6GJIICQ5UMIIKIVIDT","short_pith_number":"pith:YY4DJDKX","schema_version":"1.0","canonical_sha256":"c638348d57f192840a1da3108522a81cff4b53a3857d2f0855f9291e76041462","source":{"kind":"arxiv","id":"2012.05942","version":2},"attestation_state":"computed","paper":{"title":"Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Chin-Wei Huang, Christos Tsirigotis, Ricky T. Q. Chen","submitted_at":"2020-12-10T19:36:34Z","abstract_excerpt":"Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient parameterization of invertible models inspired by the optimal transport (OT) theory. CP-Flows are the gradient map of a strongly convex neural potential function. The convexity implies invertibility and allows us to resort to convex optimization to solve the convex conjugate for efficient inversion. To enable maximum likelihood training, we derive a new gradient estimator of the log-determinant of the Jacobian, which inv"},"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":"2012.05942","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T19:36:34Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"dc01107c696b96919f674d29edc97ea9513604a7aa841b8ed96d5e67188ab646","abstract_canon_sha256":"8eedd00d041d7a610d6fba32acb3a0e7d82a937bc4fc5ec911d99cfc327d431e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:55.979542Z","signature_b64":"dCDJZeIEobBsBq6EH5MgB4j907ONehhRPUs6rVRqDw2OszMptfUh2pduZ7axpGvuiobTvXuStn0hx9xj6fWkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c638348d57f192840a1da3108522a81cff4b53a3857d2f0855f9291e76041462","last_reissued_at":"2026-07-05T02:17:55.979035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:55.979035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Chin-Wei Huang, Christos Tsirigotis, Ricky T. Q. Chen","submitted_at":"2020-12-10T19:36:34Z","abstract_excerpt":"Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient parameterization of invertible models inspired by the optimal transport (OT) theory. CP-Flows are the gradient map of a strongly convex neural potential function. The convexity implies invertibility and allows us to resort to convex optimization to solve the convex conjugate for efficient inversion. To enable maximum likelihood training, we derive a new gradient estimator of the log-determinant of the Jacobian, which inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05942","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/2012.05942/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":"2012.05942","created_at":"2026-07-05T02:17:55.979105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05942v2","created_at":"2026-07-05T02:17:55.979105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05942","created_at":"2026-07-05T02:17:55.979105+00:00"},{"alias_kind":"pith_short_12","alias_value":"YY4DJDKX6GJI","created_at":"2026-07-05T02:17:55.979105+00:00"},{"alias_kind":"pith_short_16","alias_value":"YY4DJDKX6GJIICQ5","created_at":"2026-07-05T02:17:55.979105+00:00"},{"alias_kind":"pith_short_8","alias_value":"YY4DJDKX","created_at":"2026-07-05T02:17:55.979105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30489","citing_title":"Factorizable Normalizing Flows for parameter-dependent density morphing","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2502.08534","citing_title":"Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04477","citing_title":"Universal Representation of Generalized Convex Functions and their Gradients","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14577","citing_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27351","citing_title":"Modeling isotropic polyconvex hyperelasticity by neural networks -- sufficient and necessary criteria for compressible and incompressible materials","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26942","citing_title":"Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT","json":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT.json","graph_json":"https://pith.science/api/pith-number/YY4DJDKX6GJIICQ5UMIIKIVIDT/graph.json","events_json":"https://pith.science/api/pith-number/YY4DJDKX6GJIICQ5UMIIKIVIDT/events.json","paper":"https://pith.science/paper/YY4DJDKX"},"agent_actions":{"view_html":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT","download_json":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT.json","view_paper":"https://pith.science/paper/YY4DJDKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05942&json=true","fetch_graph":"https://pith.science/api/pith-number/YY4DJDKX6GJIICQ5UMIIKIVIDT/graph.json","fetch_events":"https://pith.science/api/pith-number/YY4DJDKX6GJIICQ5UMIIKIVIDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT/action/storage_attestation","attest_author":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT/action/author_attestation","sign_citation":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT/action/citation_signature","submit_replication":"https://pith.science/pith/YY4DJDKX6GJIICQ5UMIIKIVIDT/action/replication_record"}},"created_at":"2026-07-05T02:17:55.979105+00:00","updated_at":"2026-07-05T02:17:55.979105+00:00"}