{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T7LUPXWTBT7OJRU2VHYIKNK5XM","short_pith_number":"pith:T7LUPXWT","schema_version":"1.0","canonical_sha256":"9fd747ded30cfee4c69aa9f085355dbb2ea5069895a648045f3d9cc6057b07aa","source":{"kind":"arxiv","id":"2404.16189","version":4},"attestation_state":"computed","paper":{"title":"Stability in Training PINNs for Stiff PDEs: Why Initial Conditions Matter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Baoli Hao, Chun Liu, Lifan Wang, Ming Zhong, Ulisses Braga-Neto","submitted_at":"2024-04-24T20:26:34Z","abstract_excerpt":"Training physics-informed neural networks (PINNs) on stiff, time-dependent PDEs remains a fundamental challenge due to optimization instabilities and gradient pathologies. Through a series of rigorous ablation studies and Neural Tangent Kernel (NTK) analysis, we identify that the exact enforcement of initial conditions (ICs) is a decisive factor in stabilizing the training landscape. We present the first systematic ablation of two core strategies: hard initial-condition constrained transformation and self-adaptive loss weighting. Our findings demonstrate that embedding ICs directly into the ne"},"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":"2404.16189","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2024-04-24T20:26:34Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"0d5e0cf8a57a425e076d3ed344c3345a46630d27fdb754257813acdc30d3745b","abstract_canon_sha256":"074f9c8e5c6b95ff935fa1af059000f154999eae4a56270547c5547d5d068439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T01:13:44.610865Z","signature_b64":"FrHRVzTqL4ZblDXXksptQVS94umIC/cK9fbuTZDWB7ylDXs6wJAlD7nBBUn4Rp20Rxprk9RUkmobvNKMWAg2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fd747ded30cfee4c69aa9f085355dbb2ea5069895a648045f3d9cc6057b07aa","last_reissued_at":"2026-08-18T01:13:44.609112Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T01:13:44.609112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stability in Training PINNs for Stiff PDEs: Why Initial Conditions Matter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Baoli Hao, Chun Liu, Lifan Wang, Ming Zhong, Ulisses Braga-Neto","submitted_at":"2024-04-24T20:26:34Z","abstract_excerpt":"Training physics-informed neural networks (PINNs) on stiff, time-dependent PDEs remains a fundamental challenge due to optimization instabilities and gradient pathologies. Through a series of rigorous ablation studies and Neural Tangent Kernel (NTK) analysis, we identify that the exact enforcement of initial conditions (ICs) is a decisive factor in stabilizing the training landscape. We present the first systematic ablation of two core strategies: hard initial-condition constrained transformation and self-adaptive loss weighting. Our findings demonstrate that embedding ICs directly into the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16189","kind":"arxiv","version":4},"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/2404.16189/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":"2404.16189","created_at":"2026-08-18T01:13:44.609794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16189v4","created_at":"2026-08-18T01:13:44.609794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16189","created_at":"2026-08-18T01:13:44.609794+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7LUPXWTBT7O","created_at":"2026-08-18T01:13:44.609794+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7LUPXWTBT7OJRU2","created_at":"2026-08-18T01:13:44.609794+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7LUPXWT","created_at":"2026-08-18T01:13:44.609794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.23359","citing_title":"Adaptive Hard-Soft Physics-Informed Neural Networks for Robust Boundary-Constrained PDE Solving","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12050","citing_title":"Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM","json":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM.json","graph_json":"https://pith.science/api/pith-number/T7LUPXWTBT7OJRU2VHYIKNK5XM/graph.json","events_json":"https://pith.science/api/pith-number/T7LUPXWTBT7OJRU2VHYIKNK5XM/events.json","paper":"https://pith.science/paper/T7LUPXWT"},"agent_actions":{"view_html":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM","download_json":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM.json","view_paper":"https://pith.science/paper/T7LUPXWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16189&json=true","fetch_graph":"https://pith.science/api/pith-number/T7LUPXWTBT7OJRU2VHYIKNK5XM/graph.json","fetch_events":"https://pith.science/api/pith-number/T7LUPXWTBT7OJRU2VHYIKNK5XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM/action/storage_attestation","attest_author":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM/action/author_attestation","sign_citation":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM/action/citation_signature","submit_replication":"https://pith.science/pith/T7LUPXWTBT7OJRU2VHYIKNK5XM/action/replication_record"}},"created_at":"2026-08-18T01:13:44.609794+00:00","updated_at":"2026-08-18T01:13:44.609794+00:00"}