{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RQXRTRV75SMHZXYCUWNKJWOE3F","short_pith_number":"pith:RQXRTRV7","schema_version":"1.0","canonical_sha256":"8c2f19c6bfec987cdf02a59aa4d9c4d95de188df35e3eea2e96cc3d76f53afc6","source":{"kind":"arxiv","id":"2410.02628","version":5},"attestation_state":"computed","paper":{"title":"Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Anastasis Kratsios, Arip Asadulaev, Dmitry Baranchuk, Evgeny Burnaev, Mikhail Persiianov, Nikita Andreev, Nikita Starodubcev","submitted_at":"2024-10-03T16:12:59Z","abstract_excerpt":"Learning conditional distributions $\\pi^*(\\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \\sim \\pi^*$. However, acquiring paired data samples is often challenging, especially in problems such as domain translation. This necessitates the development of $\\textit{semi-supervised}$ models that utilize both limited paired data and additional unpaired i.i.d. samples $x \\sim \\pi^*_x$ and $y \\sim \\pi^*_y$ from the marginal distributions. The usage of such combined data is complex and often relies on heuristic approaches. "},"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":"2410.02628","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T16:12:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"888d3ad8e888bb25ad5df0b651189a09f31c47d912b7340f12e7c5f7e32f0ffd","abstract_canon_sha256":"1c9625f266458bef53a20d2b00cd0733e6422c5def1dab25c74f0d55ddbd055a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:11.798732Z","signature_b64":"agTljZz44QfaFMmbLOBKFr5ilMwXPYwkmb4k3IQPLAgbGfEGEbYRTUEwLuloj8Q2IlKe6C326tVyetyrn7C0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c2f19c6bfec987cdf02a59aa4d9c4d95de188df35e3eea2e96cc3d76f53afc6","last_reissued_at":"2026-06-05T01:15:11.798220Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:11.798220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Anastasis Kratsios, Arip Asadulaev, Dmitry Baranchuk, Evgeny Burnaev, Mikhail Persiianov, Nikita Andreev, Nikita Starodubcev","submitted_at":"2024-10-03T16:12:59Z","abstract_excerpt":"Learning conditional distributions $\\pi^*(\\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \\sim \\pi^*$. However, acquiring paired data samples is often challenging, especially in problems such as domain translation. This necessitates the development of $\\textit{semi-supervised}$ models that utilize both limited paired data and additional unpaired i.i.d. samples $x \\sim \\pi^*_x$ and $y \\sim \\pi^*_y$ from the marginal distributions. The usage of such combined data is complex and often relies on heuristic approaches. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02628","kind":"arxiv","version":5},"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/2410.02628/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":"2410.02628","created_at":"2026-06-05T01:15:11.798279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02628v5","created_at":"2026-06-05T01:15:11.798279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02628","created_at":"2026-06-05T01:15:11.798279+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQXRTRV75SMH","created_at":"2026-06-05T01:15:11.798279+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQXRTRV75SMHZXYC","created_at":"2026-06-05T01:15:11.798279+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQXRTRV7","created_at":"2026-06-05T01:15:11.798279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21094","citing_title":"UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03803","citing_title":"Well-Posedness and Efficient Algorithms for Inverse Optimal Transport with Bregman Regularization","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F","json":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F.json","graph_json":"https://pith.science/api/pith-number/RQXRTRV75SMHZXYCUWNKJWOE3F/graph.json","events_json":"https://pith.science/api/pith-number/RQXRTRV75SMHZXYCUWNKJWOE3F/events.json","paper":"https://pith.science/paper/RQXRTRV7"},"agent_actions":{"view_html":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F","download_json":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F.json","view_paper":"https://pith.science/paper/RQXRTRV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02628&json=true","fetch_graph":"https://pith.science/api/pith-number/RQXRTRV75SMHZXYCUWNKJWOE3F/graph.json","fetch_events":"https://pith.science/api/pith-number/RQXRTRV75SMHZXYCUWNKJWOE3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F/action/storage_attestation","attest_author":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F/action/author_attestation","sign_citation":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F/action/citation_signature","submit_replication":"https://pith.science/pith/RQXRTRV75SMHZXYCUWNKJWOE3F/action/replication_record"}},"created_at":"2026-06-05T01:15:11.798279+00:00","updated_at":"2026-06-05T01:15:11.798279+00:00"}