{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROUMBLMC35RMTLUF2MCVZAHJGO","short_pith_number":"pith:ROUMBLMC","schema_version":"1.0","canonical_sha256":"8ba8c0ad82df62c9ae85d3055c80e933a66c999ed6e7fc7a108fd0aa7efb1730","source":{"kind":"arxiv","id":"2410.08041","version":1},"attestation_state":"computed","paper":{"title":"On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Vincent Y. F. Tan, Yihang Gao","submitted_at":"2024-10-10T15:34:10Z","abstract_excerpt":"Kolmogorov--Arnold Networks (KANs), a recently proposed neural network architecture, have gained significant attention in the deep learning community, due to their potential as a viable alternative to multi-layer perceptrons (MLPs) and their broad applicability to various scientific tasks. Empirical investigations demonstrate that KANs optimized via stochastic gradient descent (SGD) are capable of achieving near-zero training loss in various machine learning (e.g., regression, classification, and time series forecasting, etc.) and scientific tasks (e.g., solving partial differential equations)"},"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":"2410.08041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T15:34:10Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"0f1b9f88726645e0011b758223663db8397053b1fc1dcd448bce06b46eaea522","abstract_canon_sha256":"93e8f91cfbeac6efcf4957f1929bd80a81dbb823e22478b02f4addfe1d2fa234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:47.767053Z","signature_b64":"c+jTv85W0c/HrdZeTNr9PPeTquQ2p8iBhwVq428jwn6+ikzPsLxGVD7i06P7RmgtIPTGNexPIaUgvM5leak/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba8c0ad82df62c9ae85d3055c80e933a66c999ed6e7fc7a108fd0aa7efb1730","last_reissued_at":"2026-07-05T09:18:47.766588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:47.766588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Vincent Y. F. Tan, Yihang Gao","submitted_at":"2024-10-10T15:34:10Z","abstract_excerpt":"Kolmogorov--Arnold Networks (KANs), a recently proposed neural network architecture, have gained significant attention in the deep learning community, due to their potential as a viable alternative to multi-layer perceptrons (MLPs) and their broad applicability to various scientific tasks. Empirical investigations demonstrate that KANs optimized via stochastic gradient descent (SGD) are capable of achieving near-zero training loss in various machine learning (e.g., regression, classification, and time series forecasting, etc.) and scientific tasks (e.g., solving partial differential equations)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08041","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/2410.08041/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":"2410.08041","created_at":"2026-07-05T09:18:47.766649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08041v1","created_at":"2026-07-05T09:18:47.766649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08041","created_at":"2026-07-05T09:18:47.766649+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROUMBLMC35RM","created_at":"2026-07-05T09:18:47.766649+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROUMBLMC35RMTLUF","created_at":"2026-07-05T09:18:47.766649+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROUMBLMC","created_at":"2026-07-05T09:18:47.766649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21534","citing_title":"Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO","json":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO.json","graph_json":"https://pith.science/api/pith-number/ROUMBLMC35RMTLUF2MCVZAHJGO/graph.json","events_json":"https://pith.science/api/pith-number/ROUMBLMC35RMTLUF2MCVZAHJGO/events.json","paper":"https://pith.science/paper/ROUMBLMC"},"agent_actions":{"view_html":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO","download_json":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO.json","view_paper":"https://pith.science/paper/ROUMBLMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08041&json=true","fetch_graph":"https://pith.science/api/pith-number/ROUMBLMC35RMTLUF2MCVZAHJGO/graph.json","fetch_events":"https://pith.science/api/pith-number/ROUMBLMC35RMTLUF2MCVZAHJGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO/action/storage_attestation","attest_author":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO/action/author_attestation","sign_citation":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO/action/citation_signature","submit_replication":"https://pith.science/pith/ROUMBLMC35RMTLUF2MCVZAHJGO/action/replication_record"}},"created_at":"2026-07-05T09:18:47.766649+00:00","updated_at":"2026-07-05T09:18:47.766649+00:00"}