{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4UUZAFJWOES453RQ2FL5HL5H5V","short_pith_number":"pith:4UUZAFJW","schema_version":"1.0","canonical_sha256":"e5299015367125ceee30d157d3afa7ed4e037f32bd4094966c4aa419667c0149","source":{"kind":"arxiv","id":"2306.11895","version":2},"attestation_state":"computed","paper":{"title":"Learning Elastic Costs to Shape Monge Displacements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aram-Alexandre Pooladian, Eug\\`ene Ndiaye, Jonathan Niles-Weed, Marco Cuturi, Michal Klein, Pierre Ablin","submitted_at":"2023-06-20T21:17:32Z","abstract_excerpt":"Given a source and a target probability measure supported on $\\mathbb{R}^d$, the Monge problem asks to find the most efficient way to map one distribution to the other. This efficiency is quantified by defining a \\textit{cost} function between source and target data. Such a cost is often set by default in the machine learning literature to the squared-Euclidean distance, $\\ell^2_2(\\mathbf{x},\\mathbf{y})=\\tfrac12|\\mathbf{x}-\\mathbf{y}|_2^2$. Recently, Cuturi et. al '23 highlighted the benefits of using elastic costs, defined through a regularizer $\\tau$ as $c(\\mathbf{x},\\mathbf{y})=\\ell^2_2(\\ma"},"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":"2306.11895","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-20T21:17:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f86d16218d02d5c89e1ddb10fce7c841689f9da77d2caf15438f3135bf431f2","abstract_canon_sha256":"83353ff167547eeb59392d69e32779145050d5385e7446e58d0b30e8d24c0b25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:20.557687Z","signature_b64":"hqPnsqVdPuz76CxKD4Uk1KxItuGCSGJ2IW65u4bEl9QMXzOKXNYJc22hS9aTltPJowyfuQpyo+0drD5DTD0iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5299015367125ceee30d157d3afa7ed4e037f32bd4094966c4aa419667c0149","last_reissued_at":"2026-07-05T08:22:20.557267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:20.557267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Elastic Costs to Shape Monge Displacements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aram-Alexandre Pooladian, Eug\\`ene Ndiaye, Jonathan Niles-Weed, Marco Cuturi, Michal Klein, Pierre Ablin","submitted_at":"2023-06-20T21:17:32Z","abstract_excerpt":"Given a source and a target probability measure supported on $\\mathbb{R}^d$, the Monge problem asks to find the most efficient way to map one distribution to the other. This efficiency is quantified by defining a \\textit{cost} function between source and target data. Such a cost is often set by default in the machine learning literature to the squared-Euclidean distance, $\\ell^2_2(\\mathbf{x},\\mathbf{y})=\\tfrac12|\\mathbf{x}-\\mathbf{y}|_2^2$. Recently, Cuturi et. al '23 highlighted the benefits of using elastic costs, defined through a regularizer $\\tau$ as $c(\\mathbf{x},\\mathbf{y})=\\ell^2_2(\\ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11895","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/2306.11895/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":"2306.11895","created_at":"2026-07-05T08:22:20.557322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11895v2","created_at":"2026-07-05T08:22:20.557322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11895","created_at":"2026-07-05T08:22:20.557322+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UUZAFJWOES4","created_at":"2026-07-05T08:22:20.557322+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UUZAFJWOES453RQ","created_at":"2026-07-05T08:22:20.557322+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UUZAFJW","created_at":"2026-07-05T08:22:20.557322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.08066","citing_title":"Wasserstein distances and divergences of order $p$ by quantum channels","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26326","citing_title":"Strong Kantorovich duality for quantum optimal transport with generic cost and optimal couplings on quantum bits","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V","json":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V.json","graph_json":"https://pith.science/api/pith-number/4UUZAFJWOES453RQ2FL5HL5H5V/graph.json","events_json":"https://pith.science/api/pith-number/4UUZAFJWOES453RQ2FL5HL5H5V/events.json","paper":"https://pith.science/paper/4UUZAFJW"},"agent_actions":{"view_html":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V","download_json":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V.json","view_paper":"https://pith.science/paper/4UUZAFJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11895&json=true","fetch_graph":"https://pith.science/api/pith-number/4UUZAFJWOES453RQ2FL5HL5H5V/graph.json","fetch_events":"https://pith.science/api/pith-number/4UUZAFJWOES453RQ2FL5HL5H5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V/action/storage_attestation","attest_author":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V/action/author_attestation","sign_citation":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V/action/citation_signature","submit_replication":"https://pith.science/pith/4UUZAFJWOES453RQ2FL5HL5H5V/action/replication_record"}},"created_at":"2026-07-05T08:22:20.557322+00:00","updated_at":"2026-07-05T08:22:20.557322+00:00"}