{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GZNJQ2JNZV2ILO66X6DRUNNRVD","short_pith_number":"pith:GZNJQ2JN","schema_version":"1.0","canonical_sha256":"365a98692dcd7485bbdebf871a35b1a8fecd8d22fdfec36862d86c3c52c2cb5a","source":{"kind":"arxiv","id":"2208.01565","version":1},"attestation_state":"computed","paper":{"title":"Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Emilia Magnani, Lorenzo Rosasco, Nicholas Kr\\\"amer, Philipp Hennig, Runa Eschenhagen","submitted_at":"2022-08-02T16:10:27Z","abstract_excerpt":"Neural operators are a type of deep architecture that learns to solve (i.e. learns the nonlinear solution operator of) partial differential equations (PDEs). The current state of the art for these models does not provide explicit uncertainty quantification. This is arguably even more of a problem for this kind of tasks than elsewhere in machine learning, because the dynamical systems typically described by PDEs often exhibit subtle, multiscale structure that makes errors hard to spot by humans. In this work, we first provide a mathematically detailed Bayesian formulation of the ''shallow'' (li"},"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":"2208.01565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-02T16:10:27Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"5ce98c8a7a58f3c0fd3c47e3be2f1a9a454b0a10252df29dbad3a67b16d88f6c","abstract_canon_sha256":"dd11e6c44b547465d01baa7bb7165087d762a93e839fca3fbab938e306f86905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:35.071372Z","signature_b64":"QdC2BRwRKjlcNgsaj7Y1rziPfPmDo9FCReudfuK2kTDiuTs1zV9Xzqn6M2SooItmK8o2OqMOrQvK0G4NrUlcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"365a98692dcd7485bbdebf871a35b1a8fecd8d22fdfec36862d86c3c52c2cb5a","last_reissued_at":"2026-07-05T04:45:35.070867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:35.070867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Emilia Magnani, Lorenzo Rosasco, Nicholas Kr\\\"amer, Philipp Hennig, Runa Eschenhagen","submitted_at":"2022-08-02T16:10:27Z","abstract_excerpt":"Neural operators are a type of deep architecture that learns to solve (i.e. learns the nonlinear solution operator of) partial differential equations (PDEs). The current state of the art for these models does not provide explicit uncertainty quantification. This is arguably even more of a problem for this kind of tasks than elsewhere in machine learning, because the dynamical systems typically described by PDEs often exhibit subtle, multiscale structure that makes errors hard to spot by humans. In this work, we first provide a mathematically detailed Bayesian formulation of the ''shallow'' (li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01565","kind":"arxiv","version":1},"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/2208.01565/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":"2208.01565","created_at":"2026-07-05T04:45:35.070932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01565v1","created_at":"2026-07-05T04:45:35.070932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01565","created_at":"2026-07-05T04:45:35.070932+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZNJQ2JNZV2I","created_at":"2026-07-05T04:45:35.070932+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZNJQ2JNZV2ILO66","created_at":"2026-07-05T04:45:35.070932+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZNJQ2JN","created_at":"2026-07-05T04:45:35.070932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22946","citing_title":"Neural Operator Processes for Probabilistic Operator Learning under Partial Observations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17513","citing_title":"Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08654","citing_title":"Operator learning for the 2D incompressible Navier-Stokes equations: a conformal prediction approach in the data-scarce regime","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD","json":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD.json","graph_json":"https://pith.science/api/pith-number/GZNJQ2JNZV2ILO66X6DRUNNRVD/graph.json","events_json":"https://pith.science/api/pith-number/GZNJQ2JNZV2ILO66X6DRUNNRVD/events.json","paper":"https://pith.science/paper/GZNJQ2JN"},"agent_actions":{"view_html":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD","download_json":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD.json","view_paper":"https://pith.science/paper/GZNJQ2JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01565&json=true","fetch_graph":"https://pith.science/api/pith-number/GZNJQ2JNZV2ILO66X6DRUNNRVD/graph.json","fetch_events":"https://pith.science/api/pith-number/GZNJQ2JNZV2ILO66X6DRUNNRVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD/action/storage_attestation","attest_author":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD/action/author_attestation","sign_citation":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD/action/citation_signature","submit_replication":"https://pith.science/pith/GZNJQ2JNZV2ILO66X6DRUNNRVD/action/replication_record"}},"created_at":"2026-07-05T04:45:35.070932+00:00","updated_at":"2026-07-05T04:45:35.070932+00:00"}