{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWJCISXB3MVDIVLBYYXKHOM44S","short_pith_number":"pith:NWJCISXB","schema_version":"1.0","canonical_sha256":"6d92244ae1db2a345561c62ea3b99ce48eecf96ddd733f8045589e760c962bfc","source":{"kind":"arxiv","id":"2410.06308","version":1},"attestation_state":"computed","paper":{"title":"Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Chuqi Chen, Qixuan Zhou, Tao Luo, Yahong Yang, Yang Xiang","submitted_at":"2024-10-08T19:35:19Z","abstract_excerpt":"Neural network-based methods have emerged as powerful tools for solving partial differential equations (PDEs) in scientific and engineering applications, particularly when handling complex domains or incorporating empirical data. These methods leverage neural networks as basis functions to approximate PDE solutions. However, training such networks can be challenging, often resulting in limited accuracy. In this paper, we investigate the training dynamics of neural network-based PDE solvers with a focus on the impact of initialization techniques. We assess training difficulty by analyzing the e"},"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":"2410.06308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2024-10-08T19:35:19Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"bcd56f3cf3674e91d6f2f9ce3f5c5c410ac04db81ab0635af92cee0c258e0f55","abstract_canon_sha256":"ca401d3e6695300bfab8ed7fec37ecf1b686bdc5f37353d74bc1df6ded831c27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:59.748115Z","signature_b64":"3AuQeXN8rp7dvoE0GGLCw6nXB7xdRDsu+ZCg+M4DwWBX+DtO+DpTEMZjG4dubJjAFN8UxPaFQgBDStser7Z8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d92244ae1db2a345561c62ea3b99ce48eecf96ddd733f8045589e760c962bfc","last_reissued_at":"2026-07-05T09:17:59.747710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:59.747710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Chuqi Chen, Qixuan Zhou, Tao Luo, Yahong Yang, Yang Xiang","submitted_at":"2024-10-08T19:35:19Z","abstract_excerpt":"Neural network-based methods have emerged as powerful tools for solving partial differential equations (PDEs) in scientific and engineering applications, particularly when handling complex domains or incorporating empirical data. These methods leverage neural networks as basis functions to approximate PDE solutions. However, training such networks can be challenging, often resulting in limited accuracy. In this paper, we investigate the training dynamics of neural network-based PDE solvers with a focus on the impact of initialization techniques. We assess training difficulty by analyzing the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06308","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/2410.06308/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":"2410.06308","created_at":"2026-07-05T09:17:59.747765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06308v1","created_at":"2026-07-05T09:17:59.747765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06308","created_at":"2026-07-05T09:17:59.747765+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWJCISXB3MVD","created_at":"2026-07-05T09:17:59.747765+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWJCISXB3MVDIVLB","created_at":"2026-07-05T09:17:59.747765+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWJCISXB","created_at":"2026-07-05T09:17:59.747765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00643","citing_title":"Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S","json":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S.json","graph_json":"https://pith.science/api/pith-number/NWJCISXB3MVDIVLBYYXKHOM44S/graph.json","events_json":"https://pith.science/api/pith-number/NWJCISXB3MVDIVLBYYXKHOM44S/events.json","paper":"https://pith.science/paper/NWJCISXB"},"agent_actions":{"view_html":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S","download_json":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S.json","view_paper":"https://pith.science/paper/NWJCISXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06308&json=true","fetch_graph":"https://pith.science/api/pith-number/NWJCISXB3MVDIVLBYYXKHOM44S/graph.json","fetch_events":"https://pith.science/api/pith-number/NWJCISXB3MVDIVLBYYXKHOM44S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S/action/storage_attestation","attest_author":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S/action/author_attestation","sign_citation":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S/action/citation_signature","submit_replication":"https://pith.science/pith/NWJCISXB3MVDIVLBYYXKHOM44S/action/replication_record"}},"created_at":"2026-07-05T09:17:59.747765+00:00","updated_at":"2026-07-05T09:17:59.747765+00:00"}