{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MUI3ZCDS6DUYLF4OTOWGWB6J6","short_pith_number":"pith:4MUI3ZCD","schema_version":"1.0","canonical_sha256":"e3288de44397874c2cbc74dd63583e4f94b094f43333327b1d881ada14d57767","source":{"kind":"arxiv","id":"2310.19809","version":3},"attestation_state":"computed","paper":{"title":"MgNO: Efficient Parameterization of Linear Operators via Multigrid","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Xinliang Liu","submitted_at":"2023-10-16T13:01:35Z","abstract_excerpt":"In this work, we propose a concise neural operator architecture for operator learning. Drawing an analogy with a conventional fully connected neural network, we define the neural operator as follows: the output of the $i$-th neuron in a nonlinear operator layer is defined by $O_i(u) = \\sigma\\left( \\sum_j W_{ij} u + B_{ij}\\right)$. Here, $ W_{ij}$ denotes the bounded linear operator connecting $j$-th input neuron to $i$-th output neuron, and the bias $ B_{ij}$ takes the form of a function rather than a scalar. Given its new universal approximation property, the efficient parameterization of the"},"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":"2310.19809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T13:01:35Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"33d1f34eb2f249088cfd6b9500ed4d9021d96599b3d747863c426f1a1702a8db","abstract_canon_sha256":"1c4843cd49c2c6623906f75f73b8f05f623a544079bdfc6992852efe4c8c8c77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:44.119483Z","signature_b64":"9YaKre1Xms32qACnAdZbeXtNbKXurnGkZpZDHnCpId9ETqVLT7oJJeOIjKk7NBt7L/8qdaH1NiIldDaNcAjLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3288de44397874c2cbc74dd63583e4f94b094f43333327b1d881ada14d57767","last_reissued_at":"2026-07-05T08:36:44.119014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:44.119014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MgNO: Efficient Parameterization of Linear Operators via Multigrid","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Xinliang Liu","submitted_at":"2023-10-16T13:01:35Z","abstract_excerpt":"In this work, we propose a concise neural operator architecture for operator learning. Drawing an analogy with a conventional fully connected neural network, we define the neural operator as follows: the output of the $i$-th neuron in a nonlinear operator layer is defined by $O_i(u) = \\sigma\\left( \\sum_j W_{ij} u + B_{ij}\\right)$. Here, $ W_{ij}$ denotes the bounded linear operator connecting $j$-th input neuron to $i$-th output neuron, and the bias $ B_{ij}$ takes the form of a function rather than a scalar. Given its new universal approximation property, the efficient parameterization of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19809","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/2310.19809/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":"2310.19809","created_at":"2026-07-05T08:36:44.119066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19809v3","created_at":"2026-07-05T08:36:44.119066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19809","created_at":"2026-07-05T08:36:44.119066+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MUI3ZCDS6DU","created_at":"2026-07-05T08:36:44.119066+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MUI3ZCDS6DUYLF4","created_at":"2026-07-05T08:36:44.119066+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MUI3ZCD","created_at":"2026-07-05T08:36:44.119066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24876","citing_title":"IV-Net: A neural network for elliptic PDEs with random and highly varying coefficients","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16344","citing_title":"Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14546","citing_title":"Discovering Physical Directions in Weight Space: Composing Neural PDE Experts","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08935","citing_title":"PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6","json":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6.json","graph_json":"https://pith.science/api/pith-number/4MUI3ZCDS6DUYLF4OTOWGWB6J6/graph.json","events_json":"https://pith.science/api/pith-number/4MUI3ZCDS6DUYLF4OTOWGWB6J6/events.json","paper":"https://pith.science/paper/4MUI3ZCD"},"agent_actions":{"view_html":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6","download_json":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6.json","view_paper":"https://pith.science/paper/4MUI3ZCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19809&json=true","fetch_graph":"https://pith.science/api/pith-number/4MUI3ZCDS6DUYLF4OTOWGWB6J6/graph.json","fetch_events":"https://pith.science/api/pith-number/4MUI3ZCDS6DUYLF4OTOWGWB6J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6/action/storage_attestation","attest_author":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6/action/author_attestation","sign_citation":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6/action/citation_signature","submit_replication":"https://pith.science/pith/4MUI3ZCDS6DUYLF4OTOWGWB6J6/action/replication_record"}},"created_at":"2026-07-05T08:36:44.119066+00:00","updated_at":"2026-07-05T08:36:44.119066+00:00"}