{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YRKUB3BSXKECPOOWVNYYGCWV4B","short_pith_number":"pith:YRKUB3BS","schema_version":"1.0","canonical_sha256":"c45540ec32ba8827b9d6ab71830ad5e076058cafce5e35b7197eea67fb47d1da","source":{"kind":"arxiv","id":"2207.02338","version":3},"attestation_state":"computed","paper":{"title":"Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anuj Karpatne, Arka Daw, Jie Bu, Paris Perdikaris, Sifan Wang","submitted_at":"2022-07-05T22:09:40Z","abstract_excerpt":"Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the \"failure modes\" of PINNs, although a thorough understanding of the connection between PINN failure modes and sampling strategies is missing. In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful \"propagation\" of solution from initial and"},"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":"2207.02338","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-05T22:09:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c542799bdc2fcebcb815b41351d93995614776b49dd02d82ceb55e4e4f564eb","abstract_canon_sha256":"65356d9b9c6967e35e540326b96f5d7b5a5ddce85b39e104c5b0f6689571f76d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:35.814067Z","signature_b64":"JzdZ8uShnViXsWgV02EIcj4JsMUfGMn2AwngoW+8Yp+7oY3ShK4IPcV+WFCwAC/Cg25tmkuRw0bPOJ725TKVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c45540ec32ba8827b9d6ab71830ad5e076058cafce5e35b7197eea67fb47d1da","last_reissued_at":"2026-07-05T06:18:35.813593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:35.813593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anuj Karpatne, Arka Daw, Jie Bu, Paris Perdikaris, Sifan Wang","submitted_at":"2022-07-05T22:09:40Z","abstract_excerpt":"Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the \"failure modes\" of PINNs, although a thorough understanding of the connection between PINN failure modes and sampling strategies is missing. In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful \"propagation\" of solution from initial and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02338","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/2207.02338/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":"2207.02338","created_at":"2026-07-05T06:18:35.813651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02338v3","created_at":"2026-07-05T06:18:35.813651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02338","created_at":"2026-07-05T06:18:35.813651+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRKUB3BSXKEC","created_at":"2026-07-05T06:18:35.813651+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRKUB3BSXKECPOOW","created_at":"2026-07-05T06:18:35.813651+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRKUB3BS","created_at":"2026-07-05T06:18:35.813651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06164","citing_title":"On the training of physics-informed neural operators for solving parametric partial differential equations","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2410.01990","citing_title":"Deep Learning Alternatives of the Kolmogorov Superposition Theorem","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23729","citing_title":"Integral regularization PINNs for evolution equations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16078","citing_title":"A numerical study into neural network surrogate model performance for uncertainty propagation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15254","citing_title":"Curriculum Learning of Physics-Informed Neural Networks based on Spatial Correlation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23528","citing_title":"When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04708","citing_title":"Differentiable Chemistry in PINNs for Solving Parameterized and Stiff Reaction Systems","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00863","citing_title":"Physics-informed neural networks for form-finding of unilateral membrane structures","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B","json":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B.json","graph_json":"https://pith.science/api/pith-number/YRKUB3BSXKECPOOWVNYYGCWV4B/graph.json","events_json":"https://pith.science/api/pith-number/YRKUB3BSXKECPOOWVNYYGCWV4B/events.json","paper":"https://pith.science/paper/YRKUB3BS"},"agent_actions":{"view_html":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B","download_json":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B.json","view_paper":"https://pith.science/paper/YRKUB3BS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02338&json=true","fetch_graph":"https://pith.science/api/pith-number/YRKUB3BSXKECPOOWVNYYGCWV4B/graph.json","fetch_events":"https://pith.science/api/pith-number/YRKUB3BSXKECPOOWVNYYGCWV4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B/action/storage_attestation","attest_author":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B/action/author_attestation","sign_citation":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B/action/citation_signature","submit_replication":"https://pith.science/pith/YRKUB3BSXKECPOOWVNYYGCWV4B/action/replication_record"}},"created_at":"2026-07-05T06:18:35.813651+00:00","updated_at":"2026-07-05T06:18:35.813651+00:00"}