{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QRSTELTZYZZOWB3PBLNQ4TAEUY","short_pith_number":"pith:QRSTELTZ","schema_version":"1.0","canonical_sha256":"8465322e79c672eb076f0adb0e4c04a632ab30150dc97017e817f88fbbe9c3f6","source":{"kind":"arxiv","id":"2509.02971","version":2},"attestation_state":"computed","paper":{"title":"Scale-Adaptive Generative Flows for Multiscale Scientific Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Yifan Chen","submitted_at":"2025-09-03T03:17:49Z","abstract_excerpt":"Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem within the flow matching and stochastic interpolants framework, through the principled design of noise distributions and interpolation schedules. Working in function space ensures that the generative model remains well defined as the resolution is refined; the Lipschitz regularity of the drift is important to both this function-space well-posedness and the integration cost at fixed resolution. The central observatio"},"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":"2509.02971","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-03T03:17:49Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.PR"],"title_canon_sha256":"19ec8f23971875010b9800fcf52a6f6d541be7b46f3414148123c06ce9ea40b6","abstract_canon_sha256":"1e86a39449f95d6264510bd58f4204fd78ef53b3c9bb45052a2b271cbf5143fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:15.769980Z","signature_b64":"Ba7Yp4YpTAShN5Fz0ZhIC1hK7r/zr44X1OrKAoMrodS09TG8H89p6D2PbenYrjby5MApVt2VNzx/qGyOv3ZJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8465322e79c672eb076f0adb0e4c04a632ab30150dc97017e817f88fbbe9c3f6","last_reissued_at":"2026-06-05T01:15:15.769102Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:15.769102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-Adaptive Generative Flows for Multiscale Scientific Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Yifan Chen","submitted_at":"2025-09-03T03:17:49Z","abstract_excerpt":"Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem within the flow matching and stochastic interpolants framework, through the principled design of noise distributions and interpolation schedules. Working in function space ensures that the generative model remains well defined as the resolution is refined; the Lipschitz regularity of the drift is important to both this function-space well-posedness and the integration cost at fixed resolution. The central observatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02971","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/2509.02971/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":"2509.02971","created_at":"2026-06-05T01:15:15.769219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02971v2","created_at":"2026-06-05T01:15:15.769219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02971","created_at":"2026-06-05T01:15:15.769219+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRSTELTZYZZO","created_at":"2026-06-05T01:15:15.769219+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRSTELTZYZZOWB3P","created_at":"2026-06-05T01:15:15.769219+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRSTELTZ","created_at":"2026-06-05T01:15:15.769219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2602.10989","citing_title":"Variational Optimality of F\\\"ollmer Processes in Generative Diffusions","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12597","citing_title":"The critical slowing down in diffusion models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12597","citing_title":"The critical slowing down in diffusion models","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10687","citing_title":"The finite expression method for turbulent dynamics with high-order moment recovery","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20775","citing_title":"Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY","json":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY.json","graph_json":"https://pith.science/api/pith-number/QRSTELTZYZZOWB3PBLNQ4TAEUY/graph.json","events_json":"https://pith.science/api/pith-number/QRSTELTZYZZOWB3PBLNQ4TAEUY/events.json","paper":"https://pith.science/paper/QRSTELTZ"},"agent_actions":{"view_html":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY","download_json":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY.json","view_paper":"https://pith.science/paper/QRSTELTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02971&json=true","fetch_graph":"https://pith.science/api/pith-number/QRSTELTZYZZOWB3PBLNQ4TAEUY/graph.json","fetch_events":"https://pith.science/api/pith-number/QRSTELTZYZZOWB3PBLNQ4TAEUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY/action/storage_attestation","attest_author":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY/action/author_attestation","sign_citation":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY/action/citation_signature","submit_replication":"https://pith.science/pith/QRSTELTZYZZOWB3PBLNQ4TAEUY/action/replication_record"}},"created_at":"2026-06-05T01:15:15.769219+00:00","updated_at":"2026-06-05T01:15:15.769219+00:00"}