{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CDVOLSSMXMGMLZ75Y2JEXOC7JU","short_pith_number":"pith:CDVOLSSM","schema_version":"1.0","canonical_sha256":"10eae5ca4cbb0cc5e7fdc6924bb85f4d281bc50f503944e692a18f9da7d30504","source":{"kind":"arxiv","id":"2509.01629","version":3},"attestation_state":"computed","paper":{"title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Jiawei Xu, Yifan Chen","submitted_at":"2025-09-01T17:16:34Z","abstract_excerpt":"We study the design of interpolation schedules in flow and diffusion-based generative models from both statistical and numerical perspectives. Within the stochastic interpolants framework, we first show that scalar interpolation schedules are statistically equivalent under the Kullback--Leibler divergence in path space, after optimal a posteriori tuning of the diffusion coefficient. This equivalence motivates focusing on numerical properties of the drift field rather than purely statistical criteria. We propose minimizing the averaged squared Lipschitzness of the drift as a principled criterio"},"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":"2509.01629","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-01T17:16:34Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"b6db21b9a14d5835a0765957ad8c9f0f3553dd144989ec183b4b2a2e83deaddb","abstract_canon_sha256":"60328a654d7908b74086ffd7622bacec6e307fe08e3cb524658328443aab7a4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:54.312122Z","signature_b64":"wzrNhi/TYDCENDpcVAhiUMya6eFRg+uXWYz/G0EG/ieUaoGledj3/32+cnPAX84v1v84rHYeNzQK1IWbOGyBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10eae5ca4cbb0cc5e7fdc6924bb85f4d281bc50f503944e692a18f9da7d30504","last_reissued_at":"2026-05-20T00:02:54.311281Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:54.311281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Jiawei Xu, Yifan Chen","submitted_at":"2025-09-01T17:16:34Z","abstract_excerpt":"We study the design of interpolation schedules in flow and diffusion-based generative models from both statistical and numerical perspectives. Within the stochastic interpolants framework, we first show that scalar interpolation schedules are statistically equivalent under the Kullback--Leibler divergence in path space, after optimal a posteriori tuning of the diffusion coefficient. This equivalence motivates focusing on numerical properties of the drift field rather than purely statistical criteria. We propose minimizing the averaged squared Lipschitzness of the drift as a principled criterio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01629","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/2509.01629/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":"2509.01629","created_at":"2026-05-20T00:02:54.311427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01629v3","created_at":"2026-05-20T00:02:54.311427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01629","created_at":"2026-05-20T00:02:54.311427+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDVOLSSMXMGM","created_at":"2026-05-20T00:02:54.311427+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDVOLSSMXMGMLZ75","created_at":"2026-05-20T00:02:54.311427+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDVOLSSM","created_at":"2026-05-20T00:02:54.311427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.21911","citing_title":"Noise Schedule Design for Diffusion Models: An Optimal Control Perspective","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10989","citing_title":"Variational Optimality of F\\\"ollmer Processes in Generative Diffusions","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08392","citing_title":"Geometry-Aware Discretization Error of Diffusion Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU","json":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU.json","graph_json":"https://pith.science/api/pith-number/CDVOLSSMXMGMLZ75Y2JEXOC7JU/graph.json","events_json":"https://pith.science/api/pith-number/CDVOLSSMXMGMLZ75Y2JEXOC7JU/events.json","paper":"https://pith.science/paper/CDVOLSSM"},"agent_actions":{"view_html":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU","download_json":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU.json","view_paper":"https://pith.science/paper/CDVOLSSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01629&json=true","fetch_graph":"https://pith.science/api/pith-number/CDVOLSSMXMGMLZ75Y2JEXOC7JU/graph.json","fetch_events":"https://pith.science/api/pith-number/CDVOLSSMXMGMLZ75Y2JEXOC7JU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU/action/storage_attestation","attest_author":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU/action/author_attestation","sign_citation":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU/action/citation_signature","submit_replication":"https://pith.science/pith/CDVOLSSMXMGMLZ75Y2JEXOC7JU/action/replication_record"}},"created_at":"2026-05-20T00:02:54.311427+00:00","updated_at":"2026-05-20T00:02:54.311427+00:00"}