{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EMGTYG3SYN2F2MHE2JWECAJFPZ","short_pith_number":"pith:EMGTYG3S","schema_version":"1.0","canonical_sha256":"230d3c1b72c3745d30e4d26c4101257e7598216728913796ea447ece7bb5db5e","source":{"kind":"arxiv","id":"2507.16380","version":1},"attestation_state":"computed","paper":{"title":"Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yiqi Gu, Zhihan Zeng","submitted_at":"2025-07-22T09:24:22Z","abstract_excerpt":"This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose convergence may require the network width to increase vastly with the number of training samples. So, the theory derived from over-parameterization may incur prohibitive computational costs and is far from practical experiments. We perform new optimization and generalization analysis for SGD in training two-layer PINNs, making certain assumptions about the targe"},"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":"2507.16380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T09:24:22Z","cross_cats_sorted":[],"title_canon_sha256":"da8b4b3163528614c4570a67b84309d7f6b714ea7287e0631d860bf5b8f8d570","abstract_canon_sha256":"0d494a231a806c2a96a3462a16831bc19faaca8aa98b1a3d9a87d3d58fa3260b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:08.503472Z","signature_b64":"HHlcybssZyNmL37KC9S2gPTcdxKoQQMt5Pf6ST/7GPisRwpSkNpP55nf7a5GQx41QHAO95f7+3m2hKimA4GQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"230d3c1b72c3745d30e4d26c4101257e7598216728913796ea447ece7bb5db5e","last_reissued_at":"2026-07-05T11:41:08.502899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:08.502899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yiqi Gu, Zhihan Zeng","submitted_at":"2025-07-22T09:24:22Z","abstract_excerpt":"This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose convergence may require the network width to increase vastly with the number of training samples. So, the theory derived from over-parameterization may incur prohibitive computational costs and is far from practical experiments. We perform new optimization and generalization analysis for SGD in training two-layer PINNs, making certain assumptions about the targe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16380","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/2507.16380/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":"2507.16380","created_at":"2026-07-05T11:41:08.502966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16380v1","created_at":"2026-07-05T11:41:08.502966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16380","created_at":"2026-07-05T11:41:08.502966+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMGTYG3SYN2F","created_at":"2026-07-05T11:41:08.502966+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMGTYG3SYN2F2MHE","created_at":"2026-07-05T11:41:08.502966+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMGTYG3S","created_at":"2026-07-05T11:41:08.502966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ","json":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ.json","graph_json":"https://pith.science/api/pith-number/EMGTYG3SYN2F2MHE2JWECAJFPZ/graph.json","events_json":"https://pith.science/api/pith-number/EMGTYG3SYN2F2MHE2JWECAJFPZ/events.json","paper":"https://pith.science/paper/EMGTYG3S"},"agent_actions":{"view_html":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ","download_json":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ.json","view_paper":"https://pith.science/paper/EMGTYG3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16380&json=true","fetch_graph":"https://pith.science/api/pith-number/EMGTYG3SYN2F2MHE2JWECAJFPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EMGTYG3SYN2F2MHE2JWECAJFPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ/action/storage_attestation","attest_author":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ/action/author_attestation","sign_citation":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ/action/citation_signature","submit_replication":"https://pith.science/pith/EMGTYG3SYN2F2MHE2JWECAJFPZ/action/replication_record"}},"created_at":"2026-07-05T11:41:08.502966+00:00","updated_at":"2026-07-05T11:41:08.502966+00:00"}