{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NKDWF7DI25MAJOMZ2DFFUNZORM","short_pith_number":"pith:NKDWF7DI","schema_version":"1.0","canonical_sha256":"6a8762fc68d75804b999d0ca5a372e8b0998e7489e9b17e2cdce27089edb5540","source":{"kind":"arxiv","id":"2203.07404","version":1},"attestation_state":"computed","paper":{"title":"Respecting causality is all you need for training physics-informed neural networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","nlin.CD","physics.flu-dyn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Paris Perdikaris, Shyam Sankaran, Sifan Wang","submitted_at":"2022-03-14T18:08:18Z","abstract_excerpt":"While the popularity of physics-informed neural networks (PINNs) is steadily rising, to this date PINNs have not been successful in simulating dynamical systems whose solution exhibits multi-scale, chaotic or turbulent behavior. In this work we attribute this shortcoming to the inability of existing PINNs formulations to respect the spatio-temporal causal structure that is inherent to the evolution of physical systems. We argue that this is a fundamental limitation and a key source of error that can ultimately steer PINN models to converge towards erroneous solutions. We address this pathology"},"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":"2203.07404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-14T18:08:18Z","cross_cats_sorted":["cs.NA","math.NA","nlin.CD","physics.flu-dyn","stat.ML"],"title_canon_sha256":"c639ae94ccf8421d91c501ee96275cca537380f4ec5e194d055de35a6fd335c0","abstract_canon_sha256":"f905c36368d689348ff38291292971a7002d5b5c16e6f2ce9f47393da9f5889e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:04.199619Z","signature_b64":"PjfyfHUj3L5HBFE4Isd3Se79Vuc5JulDb2SJMv8Y5EvuI1y4m3BSzYhw+Y/Irsx8N/zJF8SGsH2xs2E2zCOuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8762fc68d75804b999d0ca5a372e8b0998e7489e9b17e2cdce27089edb5540","last_reissued_at":"2026-07-05T04:05:04.199138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:04.199138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Respecting causality is all you need for training physics-informed neural networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","nlin.CD","physics.flu-dyn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Paris Perdikaris, Shyam Sankaran, Sifan Wang","submitted_at":"2022-03-14T18:08:18Z","abstract_excerpt":"While the popularity of physics-informed neural networks (PINNs) is steadily rising, to this date PINNs have not been successful in simulating dynamical systems whose solution exhibits multi-scale, chaotic or turbulent behavior. In this work we attribute this shortcoming to the inability of existing PINNs formulations to respect the spatio-temporal causal structure that is inherent to the evolution of physical systems. We argue that this is a fundamental limitation and a key source of error that can ultimately steer PINN models to converge towards erroneous solutions. We address this pathology"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07404","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/2203.07404/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":"2203.07404","created_at":"2026-07-05T04:05:04.199193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07404v1","created_at":"2026-07-05T04:05:04.199193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07404","created_at":"2026-07-05T04:05:04.199193+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKDWF7DI25MA","created_at":"2026-07-05T04:05:04.199193+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKDWF7DI25MAJOMZ","created_at":"2026-07-05T04:05:04.199193+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKDWF7DI","created_at":"2026-07-05T04:05:04.199193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25151","citing_title":"Silent Failures in Physics-Informed Neural Networks: Parameter Poisoning and the Limits of Loss-Based Validation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19853","citing_title":"Physics-Informed Neural Network with Squeeze-Excitation-like Attention","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07146","citing_title":"Decision-Aware Evaluation of Physics-Informed Surrogates","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02335","citing_title":"Neural Spectral Element Methods for stiff multiphysics PDEs with electrochemical transport benchmarks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03542","citing_title":"Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25057","citing_title":"Random Neural Network Expressivity for Non-Linear Partial Differential Equations","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25949","citing_title":"Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01179","citing_title":"Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies","ref_index":13,"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":131,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12676","citing_title":"Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02779","citing_title":"Comparison of Trefftz-Based PINNs and Standard PINNs Focusing on Structure Preservation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12368","citing_title":"MetaColloc: Optimization-Free PDE Solving via Meta-Learned Basis Functions","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11316","citing_title":"Error whitening: Why Gauss-Newton outperforms Newton","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03542","citing_title":"Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10136","citing_title":"Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09495","citing_title":"Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02681","citing_title":"The Design and Composition of Structural Causal Decision Processes","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04708","citing_title":"Differentiable Chemistry in PINNs for Solving Parameterized and Stiff Reaction Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13723","citing_title":"Physics-Informed Neural Networks for Solving Derivative-Constrained PDEs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15645","citing_title":"PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM","json":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM.json","graph_json":"https://pith.science/api/pith-number/NKDWF7DI25MAJOMZ2DFFUNZORM/graph.json","events_json":"https://pith.science/api/pith-number/NKDWF7DI25MAJOMZ2DFFUNZORM/events.json","paper":"https://pith.science/paper/NKDWF7DI"},"agent_actions":{"view_html":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM","download_json":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM.json","view_paper":"https://pith.science/paper/NKDWF7DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07404&json=true","fetch_graph":"https://pith.science/api/pith-number/NKDWF7DI25MAJOMZ2DFFUNZORM/graph.json","fetch_events":"https://pith.science/api/pith-number/NKDWF7DI25MAJOMZ2DFFUNZORM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM/action/storage_attestation","attest_author":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM/action/author_attestation","sign_citation":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM/action/citation_signature","submit_replication":"https://pith.science/pith/NKDWF7DI25MAJOMZ2DFFUNZORM/action/replication_record"}},"created_at":"2026-07-05T04:05:04.199193+00:00","updated_at":"2026-07-05T04:05:04.199193+00:00"}