{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OXTGFU6JOWUJBXLKNKM2HR5ZUN","short_pith_number":"pith:OXTGFU6J","schema_version":"1.0","canonical_sha256":"75e662d3c975a890dd6a6a99a3c7b9a343c1392c0808554f81f4b959d8b8b86e","source":{"kind":"arxiv","id":"2306.03398","version":2},"attestation_state":"computed","paper":{"title":"Minimum intrinsic dimension scaling for entropic optimal transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Austin J. Stromme","submitted_at":"2023-06-06T04:28:12Z","abstract_excerpt":"Motivated by the manifold hypothesis, which states that data with a high extrinsic dimension may yet have a low intrinsic dimension, we develop refined statistical bounds for entropic optimal transport that are sensitive to the intrinsic dimension of the data. Our bounds involve a robust notion of intrinsic dimension, measured at only a single distance scale depending on the regularization parameter, and show that it is only the minimum of these single-scale intrinsic dimensions which governs the rate of convergence. We call this the Minimum Intrinsic Dimension scaling (MID scaling) phenomenon"},"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":"2306.03398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2023-06-06T04:28:12Z","cross_cats_sorted":["cs.LG","math.PR","stat.TH"],"title_canon_sha256":"c93a217a085b90527fd1e68646e3a64f16bae3c6726e9da9308f4cc71fff3816","abstract_canon_sha256":"fe788857371944cc77214fd68473baec19ee6795fb21b1be6bbc5ce082bf0805"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:07.844932Z","signature_b64":"qUl3vBYrC57YJ8z/0fcmV/WV8BZcdteWNCndtPZDb1eMAyGG6Jrrm1+M4BxYm+iS2iiBipmtYV60u4ljGFQbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75e662d3c975a890dd6a6a99a3c7b9a343c1392c0808554f81f4b959d8b8b86e","last_reissued_at":"2026-07-05T06:44:07.844461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:07.844461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimum intrinsic dimension scaling for entropic optimal transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Austin J. Stromme","submitted_at":"2023-06-06T04:28:12Z","abstract_excerpt":"Motivated by the manifold hypothesis, which states that data with a high extrinsic dimension may yet have a low intrinsic dimension, we develop refined statistical bounds for entropic optimal transport that are sensitive to the intrinsic dimension of the data. Our bounds involve a robust notion of intrinsic dimension, measured at only a single distance scale depending on the regularization parameter, and show that it is only the minimum of these single-scale intrinsic dimensions which governs the rate of convergence. We call this the Minimum Intrinsic Dimension scaling (MID scaling) phenomenon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03398","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/2306.03398/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":"2306.03398","created_at":"2026-07-05T06:44:07.844523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03398v2","created_at":"2026-07-05T06:44:07.844523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03398","created_at":"2026-07-05T06:44:07.844523+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXTGFU6JOWUJ","created_at":"2026-07-05T06:44:07.844523+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXTGFU6JOWUJBXLK","created_at":"2026-07-05T06:44:07.844523+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXTGFU6J","created_at":"2026-07-05T06:44:07.844523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25947","citing_title":"Finite-sample bounds for regularized optimal transport","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27175","citing_title":"Polyak-Lojasiewicz Inequality for Quadratically Regularized Optimal Transport","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN","json":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN.json","graph_json":"https://pith.science/api/pith-number/OXTGFU6JOWUJBXLKNKM2HR5ZUN/graph.json","events_json":"https://pith.science/api/pith-number/OXTGFU6JOWUJBXLKNKM2HR5ZUN/events.json","paper":"https://pith.science/paper/OXTGFU6J"},"agent_actions":{"view_html":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN","download_json":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN.json","view_paper":"https://pith.science/paper/OXTGFU6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03398&json=true","fetch_graph":"https://pith.science/api/pith-number/OXTGFU6JOWUJBXLKNKM2HR5ZUN/graph.json","fetch_events":"https://pith.science/api/pith-number/OXTGFU6JOWUJBXLKNKM2HR5ZUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN/action/storage_attestation","attest_author":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN/action/author_attestation","sign_citation":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN/action/citation_signature","submit_replication":"https://pith.science/pith/OXTGFU6JOWUJBXLKNKM2HR5ZUN/action/replication_record"}},"created_at":"2026-07-05T06:44:07.844523+00:00","updated_at":"2026-07-05T06:44:07.844523+00:00"}