{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TBARESWI6UTMLUZETHIQIOVYJL","short_pith_number":"pith:TBARESWI","schema_version":"1.0","canonical_sha256":"9841124ac8f526c5d32499d1043ab84acd670473cbac0d033a1880a655feda81","source":{"kind":"arxiv","id":"2505.17308","version":1},"attestation_state":"computed","paper":{"title":"Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Markus Heinonen, Niklas Wahlstr\\\"om, Philipp Pilar","submitted_at":"2025-05-22T21:58:40Z","abstract_excerpt":"Physics-informed neural networks (PINNs) have proven an effective tool for solving differential equations, in particular when considering non-standard or ill-posed settings. When inferring solutions and parameters of the differential equation from data, uncertainty estimates are preferable to point estimates, as they give an idea about the accuracy of the solution. In this work, we consider the inverse problem and employ repulsive ensembles of PINNs (RE-PINN) for obtaining such estimates. The repulsion is implemented by adding a particular repulsive term to the loss function, which has the pro"},"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":"2505.17308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-22T21:58:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"939bf1be31b913f67bef9630bef7ad9309463c4ecbcf0a40c483949e3f32a9f3","abstract_canon_sha256":"165724fd7460f309922851583d4efc6378046a74da936e57b2dec92a10c50730"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:24.182370Z","signature_b64":"bbx9Tt54u8TWPX+bFnG1GbiN3x4I/3EPwIUd0tYicOW3BffO6+UchtGJQ2FDGSplQ8xt6G1tIkGHST9aGsD9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9841124ac8f526c5d32499d1043ab84acd670473cbac0d033a1880a655feda81","last_reissued_at":"2026-07-05T11:08:24.181993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:24.181993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Markus Heinonen, Niklas Wahlstr\\\"om, Philipp Pilar","submitted_at":"2025-05-22T21:58:40Z","abstract_excerpt":"Physics-informed neural networks (PINNs) have proven an effective tool for solving differential equations, in particular when considering non-standard or ill-posed settings. When inferring solutions and parameters of the differential equation from data, uncertainty estimates are preferable to point estimates, as they give an idea about the accuracy of the solution. In this work, we consider the inverse problem and employ repulsive ensembles of PINNs (RE-PINN) for obtaining such estimates. The repulsion is implemented by adding a particular repulsive term to the loss function, which has the pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17308","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/2505.17308/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":"2505.17308","created_at":"2026-07-05T11:08:24.182056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17308v1","created_at":"2026-07-05T11:08:24.182056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17308","created_at":"2026-07-05T11:08:24.182056+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBARESWI6UTM","created_at":"2026-07-05T11:08:24.182056+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBARESWI6UTMLUZE","created_at":"2026-07-05T11:08:24.182056+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBARESWI","created_at":"2026-07-05T11:08:24.182056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07060","citing_title":"Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07060","citing_title":"Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17156","citing_title":"Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL","json":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL.json","graph_json":"https://pith.science/api/pith-number/TBARESWI6UTMLUZETHIQIOVYJL/graph.json","events_json":"https://pith.science/api/pith-number/TBARESWI6UTMLUZETHIQIOVYJL/events.json","paper":"https://pith.science/paper/TBARESWI"},"agent_actions":{"view_html":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL","download_json":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL.json","view_paper":"https://pith.science/paper/TBARESWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17308&json=true","fetch_graph":"https://pith.science/api/pith-number/TBARESWI6UTMLUZETHIQIOVYJL/graph.json","fetch_events":"https://pith.science/api/pith-number/TBARESWI6UTMLUZETHIQIOVYJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL/action/storage_attestation","attest_author":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL/action/author_attestation","sign_citation":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL/action/citation_signature","submit_replication":"https://pith.science/pith/TBARESWI6UTMLUZETHIQIOVYJL/action/replication_record"}},"created_at":"2026-07-05T11:08:24.182056+00:00","updated_at":"2026-07-05T11:08:24.182056+00:00"}