{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4HGNU6BPGWDK6CMU57SCDHB2LK","short_pith_number":"pith:4HGNU6BP","schema_version":"1.0","canonical_sha256":"e1ccda782f3586af0994efe4219c3a5ab3c53a237cce28d2768b0df9f3f5a97f","source":{"kind":"arxiv","id":"1910.12958","version":3},"attestation_state":"computed","paper":{"title":"Sinkhorn Divergences for Unbalanced Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alain Trouv\\'e, Fran\\c{c}ois-Xavier Vialard, Gabriel Peyr\\'e, Jean Feydy, Thibault S\\'ejourn\\'e","submitted_at":"2019-10-28T20:40:37Z","abstract_excerpt":"Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been studied in depth: unbalanced transport, which is robust to the presence of outliers and can be used when distributions don't have the same total mass; entropy-regularized transport, which is robust to sampling noise and lends itself to fast computations using the Sinkhorn algorithm. This paper combines both lines of work to put robust optimal transport on so"},"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":"1910.12958","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-28T20:40:37Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"70857554d22503530295c4edc3a1f38d35eeda4dfab78638a4f37e208a09a23e","abstract_canon_sha256":"d4b1f589e60cb7d137dcdc391edc2b42a58b2b520e11f7d16b35c72d51da71f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:02.858546Z","signature_b64":"oxrxEh1ZeNGU2VlANOPJhhNEqCTMQa9mN70JZZU/WGYSkoKmpZb+aKMRolu/JSImUgTNH46T8T4JoxRv5vrZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1ccda782f3586af0994efe4219c3a5ab3c53a237cce28d2768b0df9f3f5a97f","last_reissued_at":"2026-07-05T05:33:02.857987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:02.857987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sinkhorn Divergences for Unbalanced Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alain Trouv\\'e, Fran\\c{c}ois-Xavier Vialard, Gabriel Peyr\\'e, Jean Feydy, Thibault S\\'ejourn\\'e","submitted_at":"2019-10-28T20:40:37Z","abstract_excerpt":"Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been studied in depth: unbalanced transport, which is robust to the presence of outliers and can be used when distributions don't have the same total mass; entropy-regularized transport, which is robust to sampling noise and lends itself to fast computations using the Sinkhorn algorithm. This paper combines both lines of work to put robust optimal transport on so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12958","kind":"arxiv","version":3},"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/1910.12958/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":"1910.12958","created_at":"2026-07-05T05:33:02.858051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12958v3","created_at":"2026-07-05T05:33:02.858051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12958","created_at":"2026-07-05T05:33:02.858051+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HGNU6BPGWDK","created_at":"2026-07-05T05:33:02.858051+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HGNU6BPGWDK6CMU","created_at":"2026-07-05T05:33:02.858051+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HGNU6BP","created_at":"2026-07-05T05:33:02.858051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24987","citing_title":"Sample complexity of unbalanced entropic OT","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18729","citing_title":"TimeLAVA: Learning-Agnostic Valuation for Time Series Data","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00665","citing_title":"Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18729","citing_title":"TimeLAVA: Learning-Agnostic Valuation for Time Series Data","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28973","citing_title":"Sharp $O(1/k)$ convergence rate for the Sinkhorn algorithm via a local analysis","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27948","citing_title":"RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18389","citing_title":"Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00844","citing_title":"Multivariate Time Series Data Imputation via Distributionally Robust Regularization","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19981","citing_title":"Debiasing optimal transport: classical and entropic","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK","json":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK.json","graph_json":"https://pith.science/api/pith-number/4HGNU6BPGWDK6CMU57SCDHB2LK/graph.json","events_json":"https://pith.science/api/pith-number/4HGNU6BPGWDK6CMU57SCDHB2LK/events.json","paper":"https://pith.science/paper/4HGNU6BP"},"agent_actions":{"view_html":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK","download_json":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK.json","view_paper":"https://pith.science/paper/4HGNU6BP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12958&json=true","fetch_graph":"https://pith.science/api/pith-number/4HGNU6BPGWDK6CMU57SCDHB2LK/graph.json","fetch_events":"https://pith.science/api/pith-number/4HGNU6BPGWDK6CMU57SCDHB2LK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK/action/storage_attestation","attest_author":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK/action/author_attestation","sign_citation":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK/action/citation_signature","submit_replication":"https://pith.science/pith/4HGNU6BPGWDK6CMU57SCDHB2LK/action/replication_record"}},"created_at":"2026-07-05T05:33:02.858051+00:00","updated_at":"2026-07-05T05:33:02.858051+00:00"}