{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3Z66EMZ4DN6DGMWPXATBRWGB2T","short_pith_number":"pith:3Z66EMZ4","schema_version":"1.0","canonical_sha256":"de7de2333c1b7c3332cfb82618d8c1d4d27e0e543ceb4242546c54b37eeb312d","source":{"kind":"arxiv","id":"2001.04536","version":1},"attestation_state":"computed","paper":{"title":"Understanding and mitigating gradient pathologies in physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Paris Perdikaris, Sifan Wang, Yujun Teng","submitted_at":"2020-01-13T21:23:49Z","abstract_excerpt":"The widespread use of neural networks across different scientific domains often involves constraining them to satisfy certain symmetries, conservation laws, or other domain knowledge. Such constraints are often imposed as soft penalties during model training and effectively act as domain-specific regularizers of the empirical risk loss. Physics-informed neural networks is an example of this philosophy in which the outputs of deep neural networks are constrained to approximately satisfy a given set of partial differential equations. In this work we review recent advances in scientific machine l"},"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":"2001.04536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-13T21:23:49Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"f0b2e0996295edb209d4dca261b6f316a6139349646b58ede172fb9aaba8e4ce","abstract_canon_sha256":"9440e9ab7b0d7789428a0b4000835f7d94067a657d31df260f1b8bb0d4e59eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:26.616313Z","signature_b64":"V/xvDvfyq2lt75AVcPLQtMMDJI0XDiZlndTMY6JFde/ua4Z5GyGj2encU9ohyKtm2jiqlPiR4ZTTc3jWAkdkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de7de2333c1b7c3332cfb82618d8c1d4d27e0e543ceb4242546c54b37eeb312d","last_reissued_at":"2026-07-05T00:33:26.615799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:26.615799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding and mitigating gradient pathologies in physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Paris Perdikaris, Sifan Wang, Yujun Teng","submitted_at":"2020-01-13T21:23:49Z","abstract_excerpt":"The widespread use of neural networks across different scientific domains often involves constraining them to satisfy certain symmetries, conservation laws, or other domain knowledge. Such constraints are often imposed as soft penalties during model training and effectively act as domain-specific regularizers of the empirical risk loss. Physics-informed neural networks is an example of this philosophy in which the outputs of deep neural networks are constrained to approximately satisfy a given set of partial differential equations. In this work we review recent advances in scientific machine l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04536","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/2001.04536/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":"2001.04536","created_at":"2026-07-05T00:33:26.615858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04536v1","created_at":"2026-07-05T00:33:26.615858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04536","created_at":"2026-07-05T00:33:26.615858+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z66EMZ4DN6D","created_at":"2026-07-05T00:33:26.615858+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z66EMZ4DN6DGMWP","created_at":"2026-07-05T00:33:26.615858+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z66EMZ4","created_at":"2026-07-05T00:33:26.615858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.13222","citing_title":"Bayesian Reasoning for Physics Informed Neural Networks","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22338","citing_title":"Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19856","citing_title":"StableGrad: Backward Scale Control without Batch Normalization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12344","citing_title":"FEDONet : Fourier-Embedded DeepONet for Spectrally Accurate Operator Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2001.04385","citing_title":"Universal Differential Equations for Scientific Machine Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15046","citing_title":"Quantum-Enhanced Convergence of Physics-Informed Neural Networks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22862","citing_title":"Physics-Informed Neural Networks for Solving Two-Flavor Neutrino Oscillations in Vacuum and Matter Environments for Atmospheric and Reactor Neutrinos","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23625","citing_title":"Physics informed operator learning of parameter dependent spectra","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22862","citing_title":"Physics-Informed Neural Networks for Solving Two-Flavor Neutrino Oscillations in Vacuum and Matter Environments for Atmospheric and Reactor Neutrinos","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T","json":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T.json","graph_json":"https://pith.science/api/pith-number/3Z66EMZ4DN6DGMWPXATBRWGB2T/graph.json","events_json":"https://pith.science/api/pith-number/3Z66EMZ4DN6DGMWPXATBRWGB2T/events.json","paper":"https://pith.science/paper/3Z66EMZ4"},"agent_actions":{"view_html":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T","download_json":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T.json","view_paper":"https://pith.science/paper/3Z66EMZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04536&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z66EMZ4DN6DGMWPXATBRWGB2T/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z66EMZ4DN6DGMWPXATBRWGB2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T/action/storage_attestation","attest_author":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T/action/author_attestation","sign_citation":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T/action/citation_signature","submit_replication":"https://pith.science/pith/3Z66EMZ4DN6DGMWPXATBRWGB2T/action/replication_record"}},"created_at":"2026-07-05T00:33:26.615858+00:00","updated_at":"2026-07-05T00:33:26.615858+00:00"}