{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RDHSWXEJUSEVADPSHFSOBHRG33","short_pith_number":"pith:RDHSWXEJ","schema_version":"1.0","canonical_sha256":"88cf2b5c89a489500df23964e09e26defa900da65cf61028aaf6412ae5ed9653","source":{"kind":"arxiv","id":"2605.13912","version":1},"attestation_state":"computed","paper":{"title":"ViT-K: A Few-Shot Learning Model for Coupled Fluid-Porous Media Flows with Interface Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ViT-K learns stable long-term predictions for coupled fluid-porous flows from few examples by linearizing dynamics with a Koopman operator.","cross_cats":["cs.NA","physics.flu-dyn"],"primary_cat":"math.NA","authors_text":"Changxin Qiu, Menghui Xu, Mengjia Chen, Zhiping Mao","submitted_at":"2026-05-13T08:27:17Z","abstract_excerpt":"The numerical simulation of interaction between free flow and porous media, governed by coupled Stokes/Navier--Stokes--Darcy flows, is critical for understanding fluid filtration and physiological transport, yet it is hindered by the high computational cost of resolving interface heterogeneities and the instability of long-term predictions. While deep learning offers surrogate modeling potential, existing frameworks often suffer from exponential error accumulation and poor convergence in multi-physics regimes. To address these limitations, we propose ViT-K, a novel few-shot learning model desi"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-13T08:27:17Z","cross_cats_sorted":["cs.NA","physics.flu-dyn"],"title_canon_sha256":"38a52c4292a02e333ce0698a536996354c7cea96067294381ecc14b490ebd614","abstract_canon_sha256":"2e27b288dfb0f1ebc78fe0167d647b1f1cc015b1275804a587eec12dcdb029a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:18.802150Z","signature_b64":"QaHufw4cKuJGc6EfOGgOGSo+C1wQHcJ690VlDTfrJjC1BSJd81IOM//Ye2h0xvqQa4Z1kM2FAR4pNfEJeORkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88cf2b5c89a489500df23964e09e26defa900da65cf61028aaf6412ae5ed9653","last_reissued_at":"2026-05-17T23:39:18.801424Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:18.801424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViT-K: A Few-Shot Learning Model for Coupled Fluid-Porous Media Flows with Interface Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ViT-K learns stable long-term predictions for coupled fluid-porous flows from few examples by linearizing dynamics with a Koopman operator.","cross_cats":["cs.NA","physics.flu-dyn"],"primary_cat":"math.NA","authors_text":"Changxin Qiu, Menghui Xu, Mengjia Chen, Zhiping Mao","submitted_at":"2026-05-13T08:27:17Z","abstract_excerpt":"The numerical simulation of interaction between free flow and porous media, governed by coupled Stokes/Navier--Stokes--Darcy flows, is critical for understanding fluid filtration and physiological transport, yet it is hindered by the high computational cost of resolving interface heterogeneities and the instability of long-term predictions. While deep learning offers surrogate modeling potential, existing frameworks often suffer from exponential error accumulation and poor convergence in multi-physics regimes. To address these limitations, we propose ViT-K, a novel few-shot learning model desi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By lifting nonlinear dynamics into a globally linear observable space, the ViT-K model provides stability by design, ensuring that prediction errors grow linearly rather than exponentially over time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Koopman operator can be learned effectively from sparse data to linearize the full coupled Stokes/Navier-Stokes-Darcy system including interface conditions without losing essential nonlinear physics or requiring extensive hyperparameter tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ViT-K uses Vision Transformers and Koopman operators to learn stable long-term spatiotemporal dynamics of coupled fluid-porous media flows from sparse data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ViT-K learns stable long-term predictions for coupled fluid-porous flows from few examples by linearizing dynamics with a Koopman operator.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"52516da8fea9676c4973cf8d46c0121d380c43f2a8f40e234f5195db37825439"},"source":{"id":"2605.13912","kind":"arxiv","version":1},"verdict":{"id":"3f47fbc8-4713-49e1-944b-ef8eb0848bd6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:55:15.665863Z","strongest_claim":"By lifting nonlinear dynamics into a globally linear observable space, the ViT-K model provides stability by design, ensuring that prediction errors grow linearly rather than exponentially over time.","one_line_summary":"ViT-K uses Vision Transformers and Koopman operators to learn stable long-term spatiotemporal dynamics of coupled fluid-porous media flows from sparse data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Koopman operator can be learned effectively from sparse data to linearize the full coupled Stokes/Navier-Stokes-Darcy system including interface conditions without losing essential nonlinear physics or requiring extensive hyperparameter tuning.","pith_extraction_headline":"ViT-K learns stable long-term predictions for coupled fluid-porous flows from few examples by linearizing dynamics with a Koopman operator."},"references":{"count":53,"sample":[{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"9c5780d0-d7c4-4f73-a274-a7b00c883750","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Journal of Hydrology , volume=","work_id":"6c117c05-8d3f-4e44-973b-b8b67e40c043","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Domain decomposition methods for the coupling of surface and groundwater flows , author=. 2004 , type=","work_id":"bf898650-88b3-428e-a936-0cdd6e8b139b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"Computational issues related to iterative coupling of subsurface and channel flows , author=. Calcolo , volume=. 2007 , publisher=","work_id":"f021d6f3-1e3d-4df1-adfb-2c989b893d5d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Transport in porous media , volume=","work_id":"bb26416c-b1e2-4b8c-98a0-888a8b787447","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"94b5753312f5955db8a3e3b1b68f265e3c57da8f157c943740716283c0795d46","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":"2605.13912","created_at":"2026-05-17T23:39:18.801554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13912v1","created_at":"2026-05-17T23:39:18.801554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13912","created_at":"2026-05-17T23:39:18.801554+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDHSWXEJUSEV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDHSWXEJUSEVADPS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDHSWXEJ","created_at":"2026-05-18T12:33:37.589309+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/RDHSWXEJUSEVADPSHFSOBHRG33","json":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33.json","graph_json":"https://pith.science/api/pith-number/RDHSWXEJUSEVADPSHFSOBHRG33/graph.json","events_json":"https://pith.science/api/pith-number/RDHSWXEJUSEVADPSHFSOBHRG33/events.json","paper":"https://pith.science/paper/RDHSWXEJ"},"agent_actions":{"view_html":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33","download_json":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33.json","view_paper":"https://pith.science/paper/RDHSWXEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13912&json=true","fetch_graph":"https://pith.science/api/pith-number/RDHSWXEJUSEVADPSHFSOBHRG33/graph.json","fetch_events":"https://pith.science/api/pith-number/RDHSWXEJUSEVADPSHFSOBHRG33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33/action/storage_attestation","attest_author":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33/action/author_attestation","sign_citation":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33/action/citation_signature","submit_replication":"https://pith.science/pith/RDHSWXEJUSEVADPSHFSOBHRG33/action/replication_record"}},"created_at":"2026-05-17T23:39:18.801554+00:00","updated_at":"2026-05-17T23:39:18.801554+00:00"}