{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EJ5Z44DI7D3MGABLTUCFYYJWOQ","short_pith_number":"pith:EJ5Z44DI","schema_version":"1.0","canonical_sha256":"227b9e7068f8f6c3002b9d045c6136743f6f82e3b1f9e51ba55344b89b8dbfb8","source":{"kind":"arxiv","id":"2311.07548","version":4},"attestation_state":"computed","paper":{"title":"Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Hojin Kim, Romit Maulik, Shivam Barwey","submitted_at":"2023-11-13T18:37:07Z","abstract_excerpt":"Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations of data. The goal of this work is to introduce an interpretability enhancement procedure for GNNs, with application to unstructured mesh-based fluid dynamics modeling. Given a black-box baseline GNN model, the end result is an interpretable GNN model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task while retaining the predictive capability of"},"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":"2311.07548","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:37:07Z","cross_cats_sorted":["physics.comp-ph","physics.flu-dyn"],"title_canon_sha256":"d6297a5a49822b475cc0c87ba4228eb364257aff478a94a171164643d1de5253","abstract_canon_sha256":"da55549f14e8e43b8c42acf21a368647c972af9a945077c3b3be9fa4b8d5c537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:55.105391Z","signature_b64":"c04g8lf50yS8OiTtdaAjyVQk7ANOp3GpYKzinitTC+cxDa24CFUQgZVzJvbgSYpteEebdcS3ehgjCY6Lw/XpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"227b9e7068f8f6c3002b9d045c6136743f6f82e3b1f9e51ba55344b89b8dbfb8","last_reissued_at":"2026-07-05T09:24:55.105040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:55.105040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph","physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Hojin Kim, Romit Maulik, Shivam Barwey","submitted_at":"2023-11-13T18:37:07Z","abstract_excerpt":"Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations of data. The goal of this work is to introduce an interpretability enhancement procedure for GNNs, with application to unstructured mesh-based fluid dynamics modeling. Given a black-box baseline GNN model, the end result is an interpretable GNN model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task while retaining the predictive capability of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07548","kind":"arxiv","version":4},"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/2311.07548/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":"2311.07548","created_at":"2026-07-05T09:24:55.105094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07548v4","created_at":"2026-07-05T09:24:55.105094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07548","created_at":"2026-07-05T09:24:55.105094+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJ5Z44DI7D3M","created_at":"2026-07-05T09:24:55.105094+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJ5Z44DI7D3MGABL","created_at":"2026-07-05T09:24:55.105094+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJ5Z44DI","created_at":"2026-07-05T09:24:55.105094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07010","citing_title":"TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ","json":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ.json","graph_json":"https://pith.science/api/pith-number/EJ5Z44DI7D3MGABLTUCFYYJWOQ/graph.json","events_json":"https://pith.science/api/pith-number/EJ5Z44DI7D3MGABLTUCFYYJWOQ/events.json","paper":"https://pith.science/paper/EJ5Z44DI"},"agent_actions":{"view_html":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ","download_json":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ.json","view_paper":"https://pith.science/paper/EJ5Z44DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07548&json=true","fetch_graph":"https://pith.science/api/pith-number/EJ5Z44DI7D3MGABLTUCFYYJWOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EJ5Z44DI7D3MGABLTUCFYYJWOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ/action/storage_attestation","attest_author":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ/action/author_attestation","sign_citation":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ/action/citation_signature","submit_replication":"https://pith.science/pith/EJ5Z44DI7D3MGABLTUCFYYJWOQ/action/replication_record"}},"created_at":"2026-07-05T09:24:55.105094+00:00","updated_at":"2026-07-05T09:24:55.105094+00:00"}