{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WN3QJGORUEYL7354ZTXRZV2SVE","short_pith_number":"pith:WN3QJGOR","schema_version":"1.0","canonical_sha256":"b3770499d1a130bfefbcccef1cd752a901a866d6906c6d8b03c8bb36b49029b3","source":{"kind":"arxiv","id":"2305.15618","version":2},"attestation_state":"computed","paper":{"title":"Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.app-ph"],"primary_cat":"cs.LG","authors_text":"Anudhyan Boral, Fei Sha, John Anderson, Leonardo Zepeda-N\\'u\\~nez, Ricardo Baptista, Yi-Fan Chen, Zhong Yi Wan","submitted_at":"2023-05-24T23:40:23Z","abstract_excerpt":"We introduce a two-stage probabilistic framework for statistical downscaling using unpaired data. Statistical downscaling seeks a probabilistic map to transform low-resolution data from a biased coarse-grained numerical scheme to high-resolution data that is consistent with a high-fidelity scheme. Our framework tackles the problem by composing two transformations: (i) a debiasing step via an optimal transport map, and (ii) an upsampling step achieved by a probabilistic diffusion model with a posteriori conditional sampling. This approach characterizes a conditional distribution without needing"},"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":"2305.15618","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T23:40:23Z","cross_cats_sorted":["physics.app-ph"],"title_canon_sha256":"91df91623d8c4e035293ad9780a95dddda0bf646da29b01b8b20dde1bd98aa33","abstract_canon_sha256":"3ebb72f0001ebfa8d25bc48c8438858545f72b80a1cf02970cdadc6f515ce767"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:10.755408Z","signature_b64":"9JuQRnmfa0Kx3L5jtA+Yr4Dr0Kiz+FfR84X/CdgUOYoBfdPTbvryFpvkx59EHukiq72W7mP/hKpBHHfvEzwlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3770499d1a130bfefbcccef1cd752a901a866d6906c6d8b03c8bb36b49029b3","last_reissued_at":"2026-07-05T07:07:10.754927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:10.754927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.app-ph"],"primary_cat":"cs.LG","authors_text":"Anudhyan Boral, Fei Sha, John Anderson, Leonardo Zepeda-N\\'u\\~nez, Ricardo Baptista, Yi-Fan Chen, Zhong Yi Wan","submitted_at":"2023-05-24T23:40:23Z","abstract_excerpt":"We introduce a two-stage probabilistic framework for statistical downscaling using unpaired data. Statistical downscaling seeks a probabilistic map to transform low-resolution data from a biased coarse-grained numerical scheme to high-resolution data that is consistent with a high-fidelity scheme. Our framework tackles the problem by composing two transformations: (i) a debiasing step via an optimal transport map, and (ii) an upsampling step achieved by a probabilistic diffusion model with a posteriori conditional sampling. This approach characterizes a conditional distribution without needing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15618","kind":"arxiv","version":2},"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/2305.15618/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":"2305.15618","created_at":"2026-07-05T07:07:10.754979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15618v2","created_at":"2026-07-05T07:07:10.754979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15618","created_at":"2026-07-05T07:07:10.754979+00:00"},{"alias_kind":"pith_short_12","alias_value":"WN3QJGORUEYL","created_at":"2026-07-05T07:07:10.754979+00:00"},{"alias_kind":"pith_short_16","alias_value":"WN3QJGORUEYL7354","created_at":"2026-07-05T07:07:10.754979+00:00"},{"alias_kind":"pith_short_8","alias_value":"WN3QJGOR","created_at":"2026-07-05T07:07:10.754979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03275","citing_title":"IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03341","citing_title":"Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fields","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE","json":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE.json","graph_json":"https://pith.science/api/pith-number/WN3QJGORUEYL7354ZTXRZV2SVE/graph.json","events_json":"https://pith.science/api/pith-number/WN3QJGORUEYL7354ZTXRZV2SVE/events.json","paper":"https://pith.science/paper/WN3QJGOR"},"agent_actions":{"view_html":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE","download_json":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE.json","view_paper":"https://pith.science/paper/WN3QJGOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15618&json=true","fetch_graph":"https://pith.science/api/pith-number/WN3QJGORUEYL7354ZTXRZV2SVE/graph.json","fetch_events":"https://pith.science/api/pith-number/WN3QJGORUEYL7354ZTXRZV2SVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE/action/storage_attestation","attest_author":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE/action/author_attestation","sign_citation":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE/action/citation_signature","submit_replication":"https://pith.science/pith/WN3QJGORUEYL7354ZTXRZV2SVE/action/replication_record"}},"created_at":"2026-07-05T07:07:10.754979+00:00","updated_at":"2026-07-05T07:07:10.754979+00:00"}