{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SJDR4J5JMZ5OHVG3Z4XCV3F572","short_pith_number":"pith:SJDR4J5J","schema_version":"1.0","canonical_sha256":"92471e27a9667ae3d4dbcf2e2aecbdfeaa6715248db8c8019a5e3c72327d6678","source":{"kind":"arxiv","id":"2402.00326","version":3},"attestation_state":"computed","paper":{"title":"PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bowen Li, Paris Perdikaris, Sifan Wang, Yuhan Chen","submitted_at":"2024-02-01T04:17:56Z","abstract_excerpt":"While physics-informed neural networks (PINNs) have become a popular deep learning framework for tackling forward and inverse problems governed by partial differential equations (PDEs), their performance is known to degrade when larger and deeper neural network architectures are employed. Our study identifies that the root of this counter-intuitive behavior lies in the use of multi-layer perceptron (MLP) architectures with non-suitable initialization schemes, which result in poor trainablity for the network derivatives, and ultimately lead to an unstable minimization of the PDE residual loss. "},"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":"2402.00326","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T04:17:56Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"6ef11219baf6fa5af2de83f6516a12788df08ab40b25adc7993a1a8e0152beec","abstract_canon_sha256":"5770864ce04d13b95776c58fd61f83caf8129fbda987cffe8eba1a705b2f7b59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:59.971061Z","signature_b64":"KB581mmN8ZhMikVKVUDg8Ej6C9G35Rbq1ux6GUY0p+B0E5pco8wh5NWbIm+9Xwsc1KNt0Pj70FCestE5FSGdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92471e27a9667ae3d4dbcf2e2aecbdfeaa6715248db8c8019a5e3c72327d6678","last_reissued_at":"2026-07-05T07:43:59.970637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:59.970637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Bowen Li, Paris Perdikaris, Sifan Wang, Yuhan Chen","submitted_at":"2024-02-01T04:17:56Z","abstract_excerpt":"While physics-informed neural networks (PINNs) have become a popular deep learning framework for tackling forward and inverse problems governed by partial differential equations (PDEs), their performance is known to degrade when larger and deeper neural network architectures are employed. Our study identifies that the root of this counter-intuitive behavior lies in the use of multi-layer perceptron (MLP) architectures with non-suitable initialization schemes, which result in poor trainablity for the network derivatives, and ultimately lead to an unstable minimization of the PDE residual loss. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00326","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/2402.00326/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":"2402.00326","created_at":"2026-07-05T07:43:59.970694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00326v3","created_at":"2026-07-05T07:43:59.970694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00326","created_at":"2026-07-05T07:43:59.970694+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJDR4J5JMZ5O","created_at":"2026-07-05T07:43:59.970694+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJDR4J5JMZ5OHVG3","created_at":"2026-07-05T07:43:59.970694+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJDR4J5J","created_at":"2026-07-05T07:43:59.970694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"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":127,"is_internal_anchor":false},{"citing_arxiv_id":"2410.01990","citing_title":"Deep Learning Alternatives of the Kolmogorov Superposition Theorem","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11378","citing_title":"Numerical Differentiation-based Electrophysiology-Aware Adaptive ResNet for Inverse ECG Modeling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03476","citing_title":"ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23625","citing_title":"Physics informed operator learning of parameter dependent spectra","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572","json":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572.json","graph_json":"https://pith.science/api/pith-number/SJDR4J5JMZ5OHVG3Z4XCV3F572/graph.json","events_json":"https://pith.science/api/pith-number/SJDR4J5JMZ5OHVG3Z4XCV3F572/events.json","paper":"https://pith.science/paper/SJDR4J5J"},"agent_actions":{"view_html":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572","download_json":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572.json","view_paper":"https://pith.science/paper/SJDR4J5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00326&json=true","fetch_graph":"https://pith.science/api/pith-number/SJDR4J5JMZ5OHVG3Z4XCV3F572/graph.json","fetch_events":"https://pith.science/api/pith-number/SJDR4J5JMZ5OHVG3Z4XCV3F572/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572/action/storage_attestation","attest_author":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572/action/author_attestation","sign_citation":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572/action/citation_signature","submit_replication":"https://pith.science/pith/SJDR4J5JMZ5OHVG3Z4XCV3F572/action/replication_record"}},"created_at":"2026-07-05T07:43:59.970694+00:00","updated_at":"2026-07-05T07:43:59.970694+00:00"}