{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UL6QURAJ3QN54FUS3XVAHAKJLI","short_pith_number":"pith:UL6QURAJ","schema_version":"1.0","canonical_sha256":"a2fd0a4409dc1bde1692ddea0381495a121ef452bc13508b2ac551d7b4d3bd8f","source":{"kind":"arxiv","id":"2311.01404","version":4},"attestation_state":"computed","paper":{"title":"Normalizing flows as approximations of optimal transport maps via linear-control neural ODEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alessandro Scagliotti, Sara Farinelli","submitted_at":"2023-11-02T17:17:03Z","abstract_excerpt":"In this paper, we consider the problem of recovering the $W_2$-optimal transport map T between absolutely continuous measures $\\mu,\\nu\\in\\mathcal{P}(\\mathbb{R}^n)$ as the flow of a linear-control neural ODE, where the control depends only on the time variable and takes values in a finite-dimensional space. We first show that, under suitable assumptions on $\\mu,\\nu$ and on the controlled vector fields governing the neural ODE, the optimal transport map is contained in the $C^0_c$-closure of the flows generated by the system. Then, we tackle the problem under the assumption that only discrete ap"},"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":"2311.01404","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-02T17:17:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48e41cede035fcc6d57273703546c3dc53c676b647d6d9af10514ceea6da3c55","abstract_canon_sha256":"45e1c1d5827855f0d35e043f991a2ce52358533ceb7c3643404af1bd54832cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:23.771919Z","signature_b64":"rXREs/eJVfT3vhdQDWmWrkzU83R98xy/uvxcsDTe++/2r38gmguOVW8v9RG2zKt3m+9NdXVLiTXEeBtKAgQiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2fd0a4409dc1bde1692ddea0381495a121ef452bc13508b2ac551d7b4d3bd8f","last_reissued_at":"2026-07-05T09:43:23.771448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:23.771448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalizing flows as approximations of optimal transport maps via linear-control neural ODEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alessandro Scagliotti, Sara Farinelli","submitted_at":"2023-11-02T17:17:03Z","abstract_excerpt":"In this paper, we consider the problem of recovering the $W_2$-optimal transport map T between absolutely continuous measures $\\mu,\\nu\\in\\mathcal{P}(\\mathbb{R}^n)$ as the flow of a linear-control neural ODE, where the control depends only on the time variable and takes values in a finite-dimensional space. We first show that, under suitable assumptions on $\\mu,\\nu$ and on the controlled vector fields governing the neural ODE, the optimal transport map is contained in the $C^0_c$-closure of the flows generated by the system. Then, we tackle the problem under the assumption that only discrete ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01404","kind":"arxiv","version":4},"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/2311.01404/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":"2311.01404","created_at":"2026-07-05T09:43:23.771515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01404v4","created_at":"2026-07-05T09:43:23.771515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01404","created_at":"2026-07-05T09:43:23.771515+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL6QURAJ3QN5","created_at":"2026-07-05T09:43:23.771515+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL6QURAJ3QN54FUS","created_at":"2026-07-05T09:43:23.771515+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL6QURAJ","created_at":"2026-07-05T09:43:23.771515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19366","citing_title":"Constructive approximate transport maps with normalizing flows","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI","json":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI.json","graph_json":"https://pith.science/api/pith-number/UL6QURAJ3QN54FUS3XVAHAKJLI/graph.json","events_json":"https://pith.science/api/pith-number/UL6QURAJ3QN54FUS3XVAHAKJLI/events.json","paper":"https://pith.science/paper/UL6QURAJ"},"agent_actions":{"view_html":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI","download_json":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI.json","view_paper":"https://pith.science/paper/UL6QURAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01404&json=true","fetch_graph":"https://pith.science/api/pith-number/UL6QURAJ3QN54FUS3XVAHAKJLI/graph.json","fetch_events":"https://pith.science/api/pith-number/UL6QURAJ3QN54FUS3XVAHAKJLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI/action/storage_attestation","attest_author":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI/action/author_attestation","sign_citation":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI/action/citation_signature","submit_replication":"https://pith.science/pith/UL6QURAJ3QN54FUS3XVAHAKJLI/action/replication_record"}},"created_at":"2026-07-05T09:43:23.771515+00:00","updated_at":"2026-07-05T09:43:23.771515+00:00"}