{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AOBDDKQ4BMULLZOILLJPFDXUCJ","short_pith_number":"pith:AOBDDKQ4","schema_version":"1.0","canonical_sha256":"038231aa1c0b28b5e5c85ad2f28ef4125e213f47cd370e9023ff6c7ec2906fda","source":{"kind":"arxiv","id":"2006.07057","version":3},"attestation_state":"computed","paper":{"title":"Linear Time Sinkhorn Divergences using Positive Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Marco Cuturi, Meyer Scetbon","submitted_at":"2020-06-12T10:21:40Z","abstract_excerpt":"Although Sinkhorn divergences are now routinely used in data sciences to compare probability distributions, the computational effort required to compute them remains expensive, growing in general quadratically in the size $n$ of the support of these distributions. Indeed, solving optimal transport (OT) with an entropic regularization requires computing a $n\\times n$ kernel matrix (the neg-exponential of a $n\\times n$ pairwise ground cost matrix) that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-\\log\\dotp{\\varphi(x)}{\\varphi(y)}$ where $\\varphi$"},"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":"2006.07057","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-12T10:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"452719c37c9eec31bb1f696dd829c5a46a10139cb7e7deffb14e6aa0d460a248","abstract_canon_sha256":"5c8e1704b36d877bf697eef7c46e36c145ac362d19a1de4ccf5ec7864797ed1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:01.779915Z","signature_b64":"NjZJiTC+kXvPOLcOGQw1t9OF+c64KkW85FxdMtRYvIF9+F7HBfkw86NNYqLF6FNIOHKZ25wP0feuvvOY5r90DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038231aa1c0b28b5e5c85ad2f28ef4125e213f47cd370e9023ff6c7ec2906fda","last_reissued_at":"2026-07-05T01:46:01.779394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:01.779394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Time Sinkhorn Divergences using Positive Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Marco Cuturi, Meyer Scetbon","submitted_at":"2020-06-12T10:21:40Z","abstract_excerpt":"Although Sinkhorn divergences are now routinely used in data sciences to compare probability distributions, the computational effort required to compute them remains expensive, growing in general quadratically in the size $n$ of the support of these distributions. Indeed, solving optimal transport (OT) with an entropic regularization requires computing a $n\\times n$ kernel matrix (the neg-exponential of a $n\\times n$ pairwise ground cost matrix) that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-\\log\\dotp{\\varphi(x)}{\\varphi(y)}$ where $\\varphi$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07057","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/2006.07057/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":"2006.07057","created_at":"2026-07-05T01:46:01.779448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07057v3","created_at":"2026-07-05T01:46:01.779448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07057","created_at":"2026-07-05T01:46:01.779448+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOBDDKQ4BMUL","created_at":"2026-07-05T01:46:01.779448+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOBDDKQ4BMULLZOI","created_at":"2026-07-05T01:46:01.779448+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOBDDKQ4","created_at":"2026-07-05T01:46:01.779448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ","json":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ.json","graph_json":"https://pith.science/api/pith-number/AOBDDKQ4BMULLZOILLJPFDXUCJ/graph.json","events_json":"https://pith.science/api/pith-number/AOBDDKQ4BMULLZOILLJPFDXUCJ/events.json","paper":"https://pith.science/paper/AOBDDKQ4"},"agent_actions":{"view_html":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ","download_json":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ.json","view_paper":"https://pith.science/paper/AOBDDKQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07057&json=true","fetch_graph":"https://pith.science/api/pith-number/AOBDDKQ4BMULLZOILLJPFDXUCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AOBDDKQ4BMULLZOILLJPFDXUCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ/action/storage_attestation","attest_author":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ/action/author_attestation","sign_citation":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ/action/citation_signature","submit_replication":"https://pith.science/pith/AOBDDKQ4BMULLZOILLJPFDXUCJ/action/replication_record"}},"created_at":"2026-07-05T01:46:01.779448+00:00","updated_at":"2026-07-05T01:46:01.779448+00:00"}