{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GCHB6OGVESZLJFYABLYKXFIXIR","short_pith_number":"pith:GCHB6OGV","schema_version":"1.0","canonical_sha256":"308e1f38d524b2b497000af0ab9517446b27212ec741ea92b1d7a050a5384c53","source":{"kind":"arxiv","id":"2308.08468","version":1},"attestation_state":"computed","paper":{"title":"An Expert's Guide to Training Physics-informed Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Hanwen Wang, Paris Perdikaris, Shyam Sankaran, Sifan Wang","submitted_at":"2023-08-16T16:19:25Z","abstract_excerpt":"Physics-informed neural networks (PINNs) have been popularized as a deep learning framework that can seamlessly synthesize observational data and partial differential equation (PDE) constraints. Their practical effectiveness however can be hampered by training pathologies, but also oftentimes by poor choices made by users who lack deep learning expertise. In this paper we present a series of best practices that can significantly improve the training efficiency and overall accuracy of PINNs. We also put forth a series of challenging benchmark problems that highlight some of the most prominent d"},"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":"2308.08468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-16T16:19:25Z","cross_cats_sorted":["cs.NA","math.NA","physics.comp-ph"],"title_canon_sha256":"a6afc55a9f8929d30ba09d2d993296acd86d83c51dbb1de9fc36ff2ba8e49049","abstract_canon_sha256":"bb83dbed83e122a0a2420b72d430ba71598a990d1b244036d6ac334dfc7c0c39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:59.534489Z","signature_b64":"MIcyGL+Kr7rdKsO4d+TV3p2D29wW0WFxDCNxLTZOCTGEfT+VXzaf236gP3cJUDrePFZMqsuuzycf5JKaBdVCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"308e1f38d524b2b497000af0ab9517446b27212ec741ea92b1d7a050a5384c53","last_reissued_at":"2026-07-05T06:41:59.534003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:59.534003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Expert's Guide to Training Physics-informed Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Hanwen Wang, Paris Perdikaris, Shyam Sankaran, Sifan Wang","submitted_at":"2023-08-16T16:19:25Z","abstract_excerpt":"Physics-informed neural networks (PINNs) have been popularized as a deep learning framework that can seamlessly synthesize observational data and partial differential equation (PDE) constraints. Their practical effectiveness however can be hampered by training pathologies, but also oftentimes by poor choices made by users who lack deep learning expertise. In this paper we present a series of best practices that can significantly improve the training efficiency and overall accuracy of PINNs. We also put forth a series of challenging benchmark problems that highlight some of the most prominent d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08468","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/2308.08468/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":"2308.08468","created_at":"2026-07-05T06:41:59.534063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08468v1","created_at":"2026-07-05T06:41:59.534063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08468","created_at":"2026-07-05T06:41:59.534063+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCHB6OGVESZL","created_at":"2026-07-05T06:41:59.534063+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCHB6OGVESZLJFYA","created_at":"2026-07-05T06:41:59.534063+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCHB6OGV","created_at":"2026-07-05T06:41:59.534063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22566","citing_title":"A Deep Learning Approach to Describing the Plasma Sheath","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21945","citing_title":"Beyond Data-Driven: How Physics-Informed Neural Networks are Reshaping Multi-Physics Design and Discovery","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20417","citing_title":"Neural network surrogates with uncertainty quantification for inverse problems in partial differential equations","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18386","citing_title":"Reconstructing Galactic Gravitational Potentials from Stellar Kinematics with Physics-Informed Neural Networks","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09949","citing_title":"Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07146","citing_title":"Decision-Aware Evaluation of Physics-Informed Surrogates","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03838","citing_title":"Uncovering Turbulent Dynamics in Stenotic Flows from 4D-flow MRI Measurements via Resolvent Analysis and Data Assimilation","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04018","citing_title":"The Coercivity Gap in Neural PDE Solvers: Parameter Escape and Functional Convergence","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29702","citing_title":"Verified residual-specific explicit derivative kernels for physics-informed learning and discretized PDE adjoints","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30936","citing_title":"Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00056","citing_title":"Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24774","citing_title":"Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04018","citing_title":"The Coercivity Gap in Neural PDE Solvers: Parameter Escape and Functional Convergence","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25057","citing_title":"Random Neural Network Expressivity for Non-Linear Partial Differential Equations","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31106","citing_title":"Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26059","citing_title":"A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2410.01990","citing_title":"Deep Learning Alternatives of the Kolmogorov Superposition Theorem","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08453","citing_title":"Hard-constrained Physics-informed Neural Networks for Interface Problems","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02571","citing_title":"Gaussian Process Regression of Steering Vectors With Physics-Aware Deep Composite Kernels for Augmented Listening","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17776","citing_title":"Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11316","citing_title":"Error whitening: Why Gauss-Newton outperforms Newton","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08408","citing_title":"AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10136","citing_title":"Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23528","citing_title":"When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22566","citing_title":"A Deep Learning Approach to Describing the Plasma Sheath","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR","json":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR.json","graph_json":"https://pith.science/api/pith-number/GCHB6OGVESZLJFYABLYKXFIXIR/graph.json","events_json":"https://pith.science/api/pith-number/GCHB6OGVESZLJFYABLYKXFIXIR/events.json","paper":"https://pith.science/paper/GCHB6OGV"},"agent_actions":{"view_html":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR","download_json":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR.json","view_paper":"https://pith.science/paper/GCHB6OGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/GCHB6OGVESZLJFYABLYKXFIXIR/graph.json","fetch_events":"https://pith.science/api/pith-number/GCHB6OGVESZLJFYABLYKXFIXIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR/action/storage_attestation","attest_author":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR/action/author_attestation","sign_citation":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR/action/citation_signature","submit_replication":"https://pith.science/pith/GCHB6OGVESZLJFYABLYKXFIXIR/action/replication_record"}},"created_at":"2026-07-05T06:41:59.534063+00:00","updated_at":"2026-07-05T06:41:59.534063+00:00"}