{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XFZTZFIQATHOGKUHVGQ3NXOEEN","short_pith_number":"pith:XFZTZFIQ","schema_version":"1.0","canonical_sha256":"b9733c951004cee32a87a9a1b6ddc4236f822f290b739a2052e1817534bafdf6","source":{"kind":"arxiv","id":"2506.07958","version":1},"attestation_state":"computed","paper":{"title":"Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math-ph","math.AP","math.MP","math.SP"],"primary_cat":"cs.LG","authors_text":"Farinaz Mostajeran, Salah A. Faroughi","submitted_at":"2025-06-09T17:30:13Z","abstract_excerpt":"Physics-informed Kolmogorov-Arnold Networks (PIKANs), and in particular their Chebyshev-based variants (cPIKANs), have recently emerged as promising models for solving partial differential equations (PDEs). However, their training dynamics and convergence behavior remain largely unexplored both theoretically and numerically. In this work, we aim to advance the theoretical understanding of cPIKANs by analyzing them using Neural Tangent Kernel (NTK) theory. Our objective is to discern the evolution of kernel structure throughout gradient-based training and its subsequent impact on learning effic"},"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":"2506.07958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:30:13Z","cross_cats_sorted":["math-ph","math.AP","math.MP","math.SP"],"title_canon_sha256":"221fb2b4c3816569fc81ac0c7fb061840109fdd2dc62242433abb3fef05ad359","abstract_canon_sha256":"9190836c2e2de2bbb6748a1fba02bbbe6723e0ee7bb1c6a4c24d1a1c332c9b97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:36.099206Z","signature_b64":"10mvRfr32sZCGPgtmKvdJrksuGd0ksHeWgHRbLrGOp53HeLM27Ar8XjKtf+ax+KVA7Ty8Kq//2dNCU0Sf/BoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9733c951004cee32a87a9a1b6ddc4236f822f290b739a2052e1817534bafdf6","last_reissued_at":"2026-07-05T11:18:36.098644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:36.098644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math-ph","math.AP","math.MP","math.SP"],"primary_cat":"cs.LG","authors_text":"Farinaz Mostajeran, Salah A. Faroughi","submitted_at":"2025-06-09T17:30:13Z","abstract_excerpt":"Physics-informed Kolmogorov-Arnold Networks (PIKANs), and in particular their Chebyshev-based variants (cPIKANs), have recently emerged as promising models for solving partial differential equations (PDEs). However, their training dynamics and convergence behavior remain largely unexplored both theoretically and numerically. In this work, we aim to advance the theoretical understanding of cPIKANs by analyzing them using Neural Tangent Kernel (NTK) theory. Our objective is to discern the evolution of kernel structure throughout gradient-based training and its subsequent impact on learning effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07958","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/2506.07958/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":"2506.07958","created_at":"2026-07-05T11:18:36.098712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07958v1","created_at":"2026-07-05T11:18:36.098712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07958","created_at":"2026-07-05T11:18:36.098712+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFZTZFIQATHO","created_at":"2026-07-05T11:18:36.098712+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFZTZFIQATHOGKUH","created_at":"2026-07-05T11:18:36.098712+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFZTZFIQ","created_at":"2026-07-05T11:18:36.098712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21945","citing_title":"Beyond Data-Driven: How Physics-Informed Neural Networks are Reshaping Multi-Physics Design and Discovery","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07755","citing_title":"Physics-Informed Neural Networks for Joint Source and Parameter Estimation in Advection-Diffusion Equations","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN","json":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN.json","graph_json":"https://pith.science/api/pith-number/XFZTZFIQATHOGKUHVGQ3NXOEEN/graph.json","events_json":"https://pith.science/api/pith-number/XFZTZFIQATHOGKUHVGQ3NXOEEN/events.json","paper":"https://pith.science/paper/XFZTZFIQ"},"agent_actions":{"view_html":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN","download_json":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN.json","view_paper":"https://pith.science/paper/XFZTZFIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07958&json=true","fetch_graph":"https://pith.science/api/pith-number/XFZTZFIQATHOGKUHVGQ3NXOEEN/graph.json","fetch_events":"https://pith.science/api/pith-number/XFZTZFIQATHOGKUHVGQ3NXOEEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN/action/storage_attestation","attest_author":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN/action/author_attestation","sign_citation":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN/action/citation_signature","submit_replication":"https://pith.science/pith/XFZTZFIQATHOGKUHVGQ3NXOEEN/action/replication_record"}},"created_at":"2026-07-05T11:18:36.098712+00:00","updated_at":"2026-07-05T11:18:36.098712+00:00"}