{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MCD27ZBZCLBUEUMBQDTX6G6H2X","short_pith_number":"pith:MCD27ZBZ","schema_version":"1.0","canonical_sha256":"6087afe43912c342518180e77f1bc7d5cd2685448c84a03f3a473d4ccad9bebb","source":{"kind":"arxiv","id":"2602.20070","version":3},"attestation_state":"computed","paper":{"title":"Generative Modeling via Kernelized Stochastic Interpolants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Etienne Lempereur, Florentin Coeurdoux, Nathana\\\"el Cuvelle-Magar, St\\'ephane Mallat","submitted_at":"2026-02-23T17:26:09Z","abstract_excerpt":"We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\\hat b_t(x) = \\nabla\\phi(x)^\\top\\eta_t$, where $\\eta_t \\in \\mathbb{R}^P$ solves a $P\\times P$ system computable from data, with $P$ independent of the data dimension $d$. Since estimates are inexact, the diffusion coefficient $D_t$ affects sample quality; the optimal $D_t^*$ from Girsanov diverges at $t=0$, but this poses no difficulty and we develop an integrator that handles it seamlessly. The framework acco"},"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":"2602.20070","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-23T17:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"99edb4f55a906fa822fee72c792ebcf125bd09acc1bdfcc74b2ef62e3d66a1e7","abstract_canon_sha256":"5ad821cfa223d3e0f26ae1be3c679f491283479440f46bb3eaf0abc177e2f80b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:28.577397Z","signature_b64":"0+qkRCf4CxQo9Qug8rUrk7BvnJPggyy3mY7p8vIupY8fGmjygEuW3SXF19aVd0RME0zPU0CFZE7SZMAzSYCUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6087afe43912c342518180e77f1bc7d5cd2685448c84a03f3a473d4ccad9bebb","last_reissued_at":"2026-06-23T03:14:28.576863Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:28.576863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling via Kernelized Stochastic Interpolants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Etienne Lempereur, Florentin Coeurdoux, Nathana\\\"el Cuvelle-Magar, St\\'ephane Mallat","submitted_at":"2026-02-23T17:26:09Z","abstract_excerpt":"We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\\hat b_t(x) = \\nabla\\phi(x)^\\top\\eta_t$, where $\\eta_t \\in \\mathbb{R}^P$ solves a $P\\times P$ system computable from data, with $P$ independent of the data dimension $d$. Since estimates are inexact, the diffusion coefficient $D_t$ affects sample quality; the optimal $D_t^*$ from Girsanov diverges at $t=0$, but this poses no difficulty and we develop an integrator that handles it seamlessly. The framework acco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.20070","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/2602.20070/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":"2602.20070","created_at":"2026-06-23T03:14:28.576919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.20070v3","created_at":"2026-06-23T03:14:28.576919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.20070","created_at":"2026-06-23T03:14:28.576919+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCD27ZBZCLBU","created_at":"2026-06-23T03:14:28.576919+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCD27ZBZCLBUEUMB","created_at":"2026-06-23T03:14:28.576919+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCD27ZBZ","created_at":"2026-06-23T03:14:28.576919+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/MCD27ZBZCLBUEUMBQDTX6G6H2X","json":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X.json","graph_json":"https://pith.science/api/pith-number/MCD27ZBZCLBUEUMBQDTX6G6H2X/graph.json","events_json":"https://pith.science/api/pith-number/MCD27ZBZCLBUEUMBQDTX6G6H2X/events.json","paper":"https://pith.science/paper/MCD27ZBZ"},"agent_actions":{"view_html":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X","download_json":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X.json","view_paper":"https://pith.science/paper/MCD27ZBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.20070&json=true","fetch_graph":"https://pith.science/api/pith-number/MCD27ZBZCLBUEUMBQDTX6G6H2X/graph.json","fetch_events":"https://pith.science/api/pith-number/MCD27ZBZCLBUEUMBQDTX6G6H2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X/action/storage_attestation","attest_author":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X/action/author_attestation","sign_citation":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X/action/citation_signature","submit_replication":"https://pith.science/pith/MCD27ZBZCLBUEUMBQDTX6G6H2X/action/replication_record"}},"created_at":"2026-06-23T03:14:28.576919+00:00","updated_at":"2026-06-23T03:14:28.576919+00:00"}