{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:E4TSHGPCFGVUVUIWRCD2VQGDJ2","short_pith_number":"pith:E4TSHGPC","canonical_record":{"source":{"id":"2003.03485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-07T01:56:20Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"a134ca4c27e49f81d72f760c4201ce7d598edec990ecca9c23d046cf4c9de232","abstract_canon_sha256":"26201da04c09f76f2fb8b3a3f189e55fb309433aa9f8feb44b6e922aef41479c"},"schema_version":"1.0"},"canonical_sha256":"27272399e229ab4ad1168887aac0c34e880760c485e704a9e33ce0b58ac7e632","source":{"kind":"arxiv","id":"2003.03485","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03485","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03485v1","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03485","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"E4TSHGPCFGVU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"E4TSHGPCFGVUVUIW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"E4TSHGPC","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:E4TSHGPCFGVUVUIWRCD2VQGDJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2003.03485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-07T01:56:20Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"a134ca4c27e49f81d72f760c4201ce7d598edec990ecca9c23d046cf4c9de232","abstract_canon_sha256":"26201da04c09f76f2fb8b3a3f189e55fb309433aa9f8feb44b6e922aef41479c"},"schema_version":"1.0"},"canonical_sha256":"27272399e229ab4ad1168887aac0c34e880760c485e704a9e33ce0b58ac7e632","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:21.493464Z","signature_b64":"qbvF8/fM6x9PLr2mJVSVejXimcA2Nb4s8RZnN1dyWT29ZoO8tpoaYYqzQerAIAKe73XFDaO3iVkT8lusLectCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27272399e229ab4ad1168887aac0c34e880760c485e704a9e33ce0b58ac7e632","last_reissued_at":"2026-05-17T23:39:21.492591Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:21.492591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.03485","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKDJvTZOikFT9QXWGYjChfaT35KOJDTvoG+Bu68Vq2YPY7H3WIh4vpotnlK/MsPhaNnYun/ZKHbgUSied8tyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:38:48.019607Z"},"content_sha256":"7930976b49f147b51738a0505cdda198d0493e00d651255b773fa17fc010d0f3","schema_version":"1.0","event_id":"sha256:7930976b49f147b51738a0505cdda198d0493e00d651255b773fa17fc010d0f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:E4TSHGPCFGVUVUIWRCD2VQGDJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks.","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Stuart, Anima Anandkumar, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Nikola Kovachki, Zongyi Li","submitted_at":"2020-03-07T01:56:20Z","abstract_excerpt":"The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces. The purpose of this work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators). The key innovation in our work is that a single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That message passing on graphs can faithfully approximate the required integral operators for the target PDE mappings without introducing discretization-dependent artifacts that break generalization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e5e6833e714884f08fc95423b8a07bb3df63a1f21c0311209370258b8fc6ed80"},"source":{"id":"2003.03485","kind":"arxiv","version":1},"verdict":{"id":"186e514a-8a15-49cb-8c39-1e283d135728","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T22:13:20.539096Z","strongest_claim":"A single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces.","one_line_summary":"Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That message passing on graphs can faithfully approximate the required integral operators for the target PDE mappings without introducing discretization-dependent artifacts that break generalization.","pith_extraction_headline":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks."},"references":{"count":141,"sample":[{"doi":"10.1137/07070111x","year":2009,"title":"Kolda and Brett W","work_id":"00b6411a-bd17-4725-9d1c-60a55cd201b5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Hsu and Sham M","work_id":"0bca2428-01fc-484e-8b9b-57e0ae50249b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1137/090752286","year":2011,"title":"Tensor-train decomposition","work_id":"880f1684-5487-419a-885a-823cf8b643c4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Fast adaptive interpolation of multi-dimensional arrays in tensor train format , isbn =","work_id":"c3ef5637-48d5-4929-a1d6-233d247e9e96","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Gorodetsky and Sertac Karaman and Youssef M","work_id":"e4c45c80-38b9-445a-83ba-205f1910fbc7","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":141,"snapshot_sha256":"f7789c609d414f0db2016e8242d8b48e843f3951c6aa40f44745ab3d709ebc3e","internal_anchors":16},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb2252c5ab474b3359f68b4c90dac6b7e167f0a9e5dcb53de459f27eb7ebdcdf"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"186e514a-8a15-49cb-8c39-1e283d135728"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pDS+izKV+r3ND6JpHZ6Sd4aQ3euTjnuwFxa/ekIstHnRO+QBmmP4qPcwcQR/k/5leAz97Va9YeIQZhtY2NSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:38:48.020278Z"},"content_sha256":"e308aa6e3da6af6fc34823510543d9bd504e0ddc8dc1018bf1d4505e604a4aeb","schema_version":"1.0","event_id":"sha256:e308aa6e3da6af6fc34823510543d9bd504e0ddc8dc1018bf1d4505e604a4aeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/bundle.json","state_url":"https://pith.science/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T02:38:48Z","links":{"resolver":"https://pith.science/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2","bundle":"https://pith.science/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/bundle.json","state":"https://pith.science/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4TSHGPCFGVUVUIWRCD2VQGDJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:E4TSHGPCFGVUVUIWRCD2VQGDJ2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"26201da04c09f76f2fb8b3a3f189e55fb309433aa9f8feb44b6e922aef41479c","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-07T01:56:20Z","title_canon_sha256":"a134ca4c27e49f81d72f760c4201ce7d598edec990ecca9c23d046cf4c9de232"},"schema_version":"1.0","source":{"id":"2003.03485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03485","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03485v1","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03485","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"E4TSHGPCFGVU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"E4TSHGPCFGVUVUIW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"E4TSHGPC","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e308aa6e3da6af6fc34823510543d9bd504e0ddc8dc1018bf1d4505e604a4aeb","target":"graph","created_at":"2026-05-17T23:39:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"A single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That message passing on graphs can faithfully approximate the required integral operators for the target PDE mappings without introducing discretization-dependent artifacts that break generalization."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks."}],"snapshot_sha256":"e5e6833e714884f08fc95423b8a07bb3df63a1f21c0311209370258b8fc6ed80"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb2252c5ab474b3359f68b4c90dac6b7e167f0a9e5dcb53de459f27eb7ebdcdf"},"paper":{"abstract_excerpt":"The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces. The purpose of this work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators). The key innovation in our work is that a single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces","authors_text":"Andrew Stuart, Anima Anandkumar, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Nikola Kovachki, Zongyi Li","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-07T01:56:20Z","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations"},"references":{"count":141,"internal_anchors":16,"resolved_work":141,"sample":[{"cited_arxiv_id":"","doi":"10.1137/07070111x","is_internal_anchor":false,"ref_index":1,"title":"Kolda and Brett W","work_id":"00b6411a-bd17-4725-9d1c-60a55cd201b5","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Hsu and Sham M","work_id":"0bca2428-01fc-484e-8b9b-57e0ae50249b","year":2012},{"cited_arxiv_id":"","doi":"10.1137/090752286","is_internal_anchor":false,"ref_index":3,"title":"Tensor-train decomposition","work_id":"880f1684-5487-419a-885a-823cf8b643c4","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Fast adaptive interpolation of multi-dimensional arrays in tensor train format , isbn =","work_id":"c3ef5637-48d5-4929-a1d6-233d247e9e96","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Gorodetsky and Sertac Karaman and Youssef M","work_id":"e4c45c80-38b9-445a-83ba-205f1910fbc7","year":2016}],"snapshot_sha256":"f7789c609d414f0db2016e8242d8b48e843f3951c6aa40f44745ab3d709ebc3e"},"source":{"id":"2003.03485","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T22:13:20.539096Z","id":"186e514a-8a15-49cb-8c39-1e283d135728","model_set":{"reader":"grok-4.3"},"one_line_summary":"Graph Kernel Networks learn PDE solution operators that generalize across discretization methods and grid resolutions using graph-based kernel integration.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single set of network parameters can describe mappings between infinite-dimensional spaces and their finite approximations using graph kernel networks.","strongest_claim":"A single set of network parameters, within a carefully designed network architecture, may be used to describe mappings between infinite-dimensional spaces and between different finite-dimensional approximations of those spaces.","weakest_assumption":"That message passing on graphs can faithfully approximate the required integral operators for the target PDE mappings without introducing discretization-dependent artifacts that break generalization."}},"verdict_id":"186e514a-8a15-49cb-8c39-1e283d135728"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7930976b49f147b51738a0505cdda198d0493e00d651255b773fa17fc010d0f3","target":"record","created_at":"2026-05-17T23:39:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"26201da04c09f76f2fb8b3a3f189e55fb309433aa9f8feb44b6e922aef41479c","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-07T01:56:20Z","title_canon_sha256":"a134ca4c27e49f81d72f760c4201ce7d598edec990ecca9c23d046cf4c9de232"},"schema_version":"1.0","source":{"id":"2003.03485","kind":"arxiv","version":1}},"canonical_sha256":"27272399e229ab4ad1168887aac0c34e880760c485e704a9e33ce0b58ac7e632","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27272399e229ab4ad1168887aac0c34e880760c485e704a9e33ce0b58ac7e632","first_computed_at":"2026-05-17T23:39:21.492591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:21.492591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qbvF8/fM6x9PLr2mJVSVejXimcA2Nb4s8RZnN1dyWT29ZoO8tpoaYYqzQerAIAKe73XFDaO3iVkT8lusLectCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:21.493464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7930976b49f147b51738a0505cdda198d0493e00d651255b773fa17fc010d0f3","sha256:e308aa6e3da6af6fc34823510543d9bd504e0ddc8dc1018bf1d4505e604a4aeb"],"state_sha256":"84940dd7e68bd1a1fa3692e8653360ff57e9e89e38a9966a8ef74147c342f38c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNAC4ER8JecAiyHj8s/7O4SrkUtJRyr+XIjkJRtWFHUr57K3OzxxXf6Ln/nNZZBs6Q25J4eNVXJeibVZvm63Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:38:48.024847Z","bundle_sha256":"cfe96d68f694000765225ac92477fd3523151f4de51a60174f1f5ae8807a200b"}}