{"as_of":"2026-08-09T07:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12098a0e36ed65e05258b911ba56a7ab0eb3a9e1876dac4ffd8d7714a65b0ee4","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:41:36.766620Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T03:29:15.570760Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T03:30:50.487543Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"cited_work":{"arxiv_id":"2505.18131","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18131","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leve raging KANs for expedient training of multichannel MLPs via preconditioning and geometric refinement","venue":null,"work_id":"ef3dce90-9cdc-4229-aa50-1fb1890ac1db","year":2025},"citing_paper":{"arxiv_id":"2510.25781","last_updated":"2026-05-07T06:10:04Z","snapshot_observed_at":"2026-07-06T22:34:23.736456Z","submitted_at":"2025-10-28T03:03:44Z","title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","version":5},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-18T03:29:15.570760Z"},"links":{"cited_paper":"/paper/2505.18131","citing_paper":"/paper/2510.25781"},"observation_digest":"sha256:784ec842de675e7eb6e80dc6d16ba45b1fde0d27021ab502e8c074010b4ee3ec","observation_id":"e9664c3a-ddc5-49dd-a4d3-6be5763b27c6","resolution":{"observed_at":"2026-05-18T03:30:50.491302Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"cited_work":{"arxiv_id":"2505.18131","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18131","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leve raging KANs for expedient training of multichannel MLPs via preconditioning and geometric refinement","venue":null,"work_id":"ef3dce90-9cdc-4229-aa50-1fb1890ac1db","year":2025},"citing_paper":{"arxiv_id":"2604.21174","last_updated":"2026-05-06T06:52:13Z","snapshot_observed_at":"2026-07-06T23:07:47.244208Z","submitted_at":"2026-04-23T00:41:21Z","title":"Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T13:42:17.380978Z"},"links":{"cited_paper":"/paper/2505.18131","citing_paper":"/paper/2604.21174"},"observation_digest":"sha256:706db878d4782956a4cae5f3bc314123a78742a4a847ea945d85a0cd98ccc10e","observation_id":"f52d1f4b-f45a-498c-a0a2-e89c5b5e6d34","resolution":{"observed_at":"2026-05-11T18:51:07.126159Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"cited_work":{"arxiv_id":"2505.18131","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18131","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leve raging KANs for expedient training of multichannel MLPs via preconditioning and geometric refinement","venue":null,"work_id":"ef3dce90-9cdc-4229-aa50-1fb1890ac1db","year":2025},"citing_paper":{"arxiv_id":"2604.23599","last_updated":"2026-05-03T07:38:23Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-26T08:24:03Z","title":"Partition-of-Unity Gaussian Kolmogorov-Arnold Networks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-08T05:05:34.566530Z"},"links":{"cited_paper":"/paper/2505.18131","citing_paper":"/paper/2604.23599"},"observation_digest":"sha256:91b53a5f66e7f8b8e8a46a6d45267748e623340ac8038e3fbcfa964a07b38f51","observation_id":"43d33cf9-66ac-4135-a6eb-143a16aca0d8","resolution":{"observed_at":"2026-05-11T21:36:12.925873Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.18131/citation-record","integrity":"/paper/2505.18131/integrity","json":"/paper/2505.18131/citation-record.json","paper":"/paper/2505.18131"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.19143","last_updated":"2024-08-07T04:24:19Z","snapshot_observed_at":"2026-07-06T18:22:01.301152Z","submitted_at":"2024-05-29T14:48:49Z","title":"DeepOKAN: Deep Operator Network Based on Kolmogorov Arnold Networks for Mechanics Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.19143","snapshot_observed_at":"2026-08-07T14:41:32.971024Z","title":"W., Pantidis, P., and Mobasher, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:32.971024Z"},"links":{"cited_paper":"/paper/2405.19143","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:de943fa09211639ca17b835613435a458a4ed1abc3dcec54cffa0fd5c77e76d6","observation_id":"a43e6b0a-5670-476c-bbd4-31f1368b0ef8","resolution":{"observed_at":"2026-08-07T14:41:32.971024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.696578Z","title":"(38) We proceed now to the inductive step forr≥2","venue":null,"work_id":"55ae4e73-8154-428e-8887-7706a8f26d06","year":1998},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.510884Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:b3f3731f8261708cb58eb2fef99ea3a95e64cac0edec0cb7afa8d071a61fa5aa","observation_id":"5c6ed50d-785e-4479-9a16-cef03ccaa356","resolution":{"observed_at":"2026-08-07T14:41:38.796439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.06727","last_updated":"2024-11-14T02:11:56Z","snapshot_observed_at":"2026-07-06T19:48:15.021550Z","submitted_at":"2024-11-11T05:44:48Z","title":"Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.06727","snapshot_observed_at":"2026-08-07T14:41:33.769478Z","title":"Can kan work? exploring the potential of kolmogorov-arnold networks in computer vision.arXiv preprint arXiv:2411.06727,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.769478Z"},"links":{"cited_paper":"/paper/2411.06727","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:8121549194e0bd0ada6015ba3b470f02f4a36260c5eff26c0e3d779c9a9af344","observation_id":"3ae60d8e-80e1-4839-8c79-64d232e126ed","resolution":{"observed_at":"2026-08-07T14:41:33.769478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14916","last_updated":"2024-06-21T07:20:34Z","snapshot_observed_at":"2026-07-06T18:34:43.041841Z","submitted_at":"2024-06-21T07:20:34Z","title":"Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14916","snapshot_observed_at":"2026-08-07T14:41:33.904312Z","title":"Demonstrating the efficacy of kolmogorov-arnold networks in vision tasks.arXiv preprint arXiv:2406.14916,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.904312Z"},"links":{"cited_paper":"/paper/2406.14916","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:6b0b2fbd84d73c2b52ee3a4bc2b857002743733546f4c28a6098362121c79cef","observation_id":"e4f59442-71a6-4704-8e9b-d0e9f9f2a169","resolution":{"observed_at":"2026-08-07T14:41:33.904312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.06068","last_updated":"2018-06-15T17:58:40Z","snapshot_observed_at":"2026-08-08T17:18:59.631676Z","submitted_at":"2018-06-15T17:58:40Z","title":"Detecting Dead Weights and Units in Neural Networks","version":1},"cited_work":{"arxiv_id":"1806.06068","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.06068","snapshot_observed_at":"2026-08-07T14:41:37.637123Z","title":"Detecting Dead Weights and Units in Neural Networks","venue":"cs.LG","work_id":"34fa5792-bc6f-49e6-8d26-ea4fc0f8fd4e","year":2018},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.244425Z"},"links":{"cited_paper":"/paper/1806.06068","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:a689485a8d2850e335317b39577a312a66390d2a4060a8aa6a172587f687d8b0","observation_id":"65322624-be23-4f16-b32e-2aa68f8e30f9","resolution":{"observed_at":"2026-08-07T14:41:37.690176Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08041","last_updated":"2024-10-10T15:34:10Z","snapshot_observed_at":"2026-08-08T06:19:56.288235Z","submitted_at":"2024-10-10T15:34:10Z","title":"On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08041","snapshot_observed_at":"2026-08-07T14:41:34.342539Z","title":"and Tan, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.342539Z"},"links":{"cited_paper":"/paper/2410.08041","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:42b3ff9ef328d1f981d128d078586a349cb263df0e68f3c601d9e266926b7aec","observation_id":"9607c1e8-a447-42b4-9bb7-2e2fcf825ba5","resolution":{"observed_at":"2026-08-07T14:41:34.342539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:34.860001Z","title":"A., Jacob, B., Murphy, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.860001Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:bde5d29c5d8602908e0b637f99d77270846cb03582f40aec90b6f08cce324a79","observation_id":"12bd6a03-a252-45bd-8260-8ccf724c4410","resolution":{"observed_at":"2026-08-07T14:41:34.860001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06470","last_updated":"2024-06-10T17:09:38Z","snapshot_observed_at":"2026-08-09T04:21:22.826411Z","submitted_at":"2024-06-10T17:09:38Z","title":"GKAN: Graph Kolmogorov-Arnold Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06470","snapshot_observed_at":"2026-08-07T14:41:35.036555Z","title":"Gkan: Graph kolmogorov-arnold networks.arXiv preprint arXiv:2406.06470,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.036555Z"},"links":{"cited_paper":"/paper/2406.06470","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:818e2e1223c30fd0ec09586fe73addcb2201723da49bba8451156c07948516a0","observation_id":"d7fdf2c5-e304-495d-891a-0b35679ea990","resolution":{"observed_at":"2026-08-07T14:41:35.036555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14248","last_updated":"2024-09-29T11:21:48Z","snapshot_observed_at":"2026-08-09T02:25:41.916205Z","submitted_at":"2024-08-09T03:50:58Z","title":"Higher-order-ReLU-KANs (HRKANs) for solving physics-informed neural networks (PINNs) more accurately, robustly and faster","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14248","snapshot_observed_at":"2026-08-07T14:41:35.519040Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.519040Z"},"links":{"cited_paper":"/paper/2409.14248","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:953c3a1100bf690a17b71e11e86d08fee619338fb3f85658f1d631e1efb01d0f","observation_id":"0f27f497-14a5-492c-99b2-ae137987e93c","resolution":{"observed_at":"2026-08-07T14:41:35.519040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.06078","last_updated":"2024-11-09T05:54:17Z","snapshot_observed_at":"2026-07-06T19:47:47.232714Z","submitted_at":"2024-11-09T05:54:17Z","title":"A Survey on Kolmogorov-Arnold Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.06078","snapshot_observed_at":"2026-08-07T14:41:35.589260Z","title":"A., Islam, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.589260Z"},"links":{"cited_paper":"/paper/2411.06078","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:e60a7953158fddcaf8392800ba6094b11fb0a9b3be602ef4708141b9f3b3f89d","observation_id":"52114120-c127-4eae-b22d-0dd4403d96e8","resolution":{"observed_at":"2026-08-07T14:41:35.589260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:35.903468Z","title":"J., Blanco, L., Pereira, R., and Caus, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.903468Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:782d6f52bfdd10f01a43196ab4daa674b31e2a351be997d84828f538c2f4ab8a","observation_id":"c270de27-a23c-459f-a16e-4341b6b25721","resolution":{"observed_at":"2026-08-07T14:41:35.903468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:36.179543Z","title":"K., Li, B., and Perdikaris, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.179543Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:d279dd2b5c5b183269198ba8fb683c46c0cedc091b1415c24799b18788f2de46","observation_id":"d51c65a4-a3fe-49de-8fc5-6471d9706f5f","resolution":{"observed_at":"2026-08-07T14:41:36.179543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:36.258510Z","title":"doi: 10.1016/j.inffus","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.258510Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:4ccf5015cbbdd3e388875a9d7118032cbba78f4cc9c6a0cefe64771ef2993892","observation_id":"06cd3b2f-eac3-4e48-ae9a-33aca99149fc","resolution":{"observed_at":"2026-08-07T14:41:36.258510Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07906","last_updated":"2024-08-15T03:24:07Z","snapshot_observed_at":"2026-08-05T20:28:01.835569Z","submitted_at":"2024-08-15T03:24:07Z","title":"KAN versus MLP on Irregular or Noisy Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.07906","snapshot_observed_at":"2026-08-07T14:41:36.325607Z","title":"Kan versus mlp on irregular or noisy functions.arXiv preprint arXiv:2408.07906,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.325607Z"},"links":{"cited_paper":"/paper/2408.07906","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:30b3940962d4918ce6c5f61919b90600fe3b96bce7bbd0a6252188c76e5db311","observation_id":"83a92786-088a-4887-8950-4a0a52ea5210","resolution":{"observed_at":"2026-08-07T14:41:36.325607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.911889Z","title":"We define the ReLUr−1 basis functions as ψ[r] i (x) =ReLU(x−t i)r−1.(30) Define A[r] ∈R (n+r−1)×(n+r−1) as the change-of-basis matrix between B[r] = h b[r] 1−r,","venue":null,"work_id":"947e4267-3cd6-4030-8cfd-afe7da9a49f4","year":2022},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.433722Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:f941e8c1c5f0cef49bf0567866c9128fecc565b46fbeb16702da01dd2a15f5fe","observation_id":"c62b1ffe-f005-4a84-9936-b0bcbd765341","resolution":{"observed_at":"2026-08-07T14:41:39.025934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.427188Z","title":null,"venue":null,"work_id":"2b663384-84be-4a6a-92e3-0c267a8f6a5b","year":2015},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.575835Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:9d252f1ba6d23d345addbc0b3f6ee8e4d6d792dc7aeb4959e98ad2fa24d3de22","observation_id":"542924f9-bb5f-4a63-86c1-6e625861e313","resolution":{"observed_at":"2026-08-07T14:41:38.578673Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.218709Z","title":null,"venue":null,"work_id":"a888e7df-5d16-4759-a3ab-370e8843323c","year":2015},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.666935Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:a565e17de259f04394676bc9c03e84be9b9a94f07d21adb637f912bdb10af266","observation_id":"3ea988b3-53f1-44b8-89f4-0068c8891a97","resolution":{"observed_at":"2026-08-07T14:41:38.322586Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:41:38.060910Z","title":null,"venue":null,"work_id":"7a6195b6-592c-46ae-9f20-5c6c8af5f603","year":2024},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.766620Z"},"links":{"citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:c133da8b08fc8e5255590f4a01dc957727299622756bf9ac7ac7d189bfe79d42","observation_id":"4348de9f-3c96-4929-b4c9-0a231f65ed28","resolution":{"observed_at":"2026-08-07T14:41:38.110830Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02917","last_updated":"2024-06-05T04:10:36Z","snapshot_observed_at":"2026-07-06T18:25:40.229186Z","submitted_at":"2024-06-05T04:10:36Z","title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02917","snapshot_observed_at":"2026-08-07T14:41:35.446006Z","title":"D., Wang, Z., Zou, Z., and Karniadakis, G","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1958,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.446006Z"},"links":{"cited_paper":"/paper/2406.02917","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:434fff9b166287d544581944a8c31f0e0c17e27d2591934055fbc8280cb2f271","observation_id":"5213f60a-56e1-4a92-ae6c-62c654983778","resolution":{"observed_at":"2026-08-07T14:41:35.446006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18373","last_updated":"2024-07-29T03:46:15Z","snapshot_observed_at":"2026-08-02T23:25:27.831569Z","submitted_at":"2024-07-25T20:14:58Z","title":"Physics Informed Kolmogorov-Arnold Neural Networks for Dynamical Analysis via Efficent-KAN and WAV-KAN","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18373","snapshot_observed_at":"2026-08-07T14:41:35.266619Z","title":"K., Arya, M., Jacobs, K., Bondar, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1959,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.266619Z"},"links":{"cited_paper":"/paper/2407.18373","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:3f0e6e7d1e94a1489f8c423cf008b08efc6c63234347896845da896e7b863cdb","observation_id":"2716aa12-0820-4195-8de7-5e7f43962a5e","resolution":{"observed_at":"2026-08-07T14:41:35.266619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07289","last_updated":"2016-02-22T07:02:58Z","snapshot_observed_at":"2026-07-06T04:37:28.029641Z","submitted_at":"2015-11-23T15:58:05Z","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07289","snapshot_observed_at":"2026-08-07T14:41:34.071691Z","title":"Fast and accurate deep network learning by exponential linear units (elus).arXiv preprint arXiv:1511.07289,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1988,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.071691Z"},"links":{"cited_paper":"/paper/1511.07289","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:2551f260706a8ae05b27241fecec4dbde8d48652fe242405e33d7e84b81ef7bc","observation_id":"bbdd7a56-b7b2-4a17-9fba-0f1b8a76a556","resolution":{"observed_at":"2026-08-07T14:41:34.071691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07200","last_updated":"2024-06-14T15:46:11Z","snapshot_observed_at":"2026-08-08T21:02:58.042224Z","submitted_at":"2024-05-12T07:55:43Z","title":"Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07200","snapshot_observed_at":"2026-08-07T14:41:35.719199Z","title":"Chebyshev polynomial-based kolmogorov-arnold networks: An efficient architecture for nonlinear function approximation.arXiv preprint arXiv:2405.07200,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1993,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.719199Z"},"links":{"cited_paper":"/paper/2405.07200","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:86ab1407f533c152fb264ec817f301097cf2ae2d7cee3433b61a88a362a47809","observation_id":"981ea586-e5b9-48b4-a24e-5e03516dee74","resolution":{"observed_at":"2026-08-07T14:41:35.719199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13228","last_updated":"2024-10-22T02:53:15Z","snapshot_observed_at":"2026-07-06T19:35:04.087584Z","submitted_at":"2024-10-17T05:30:59Z","title":"From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13228","snapshot_observed_at":"2026-08-07T14:41:35.811698Z","title":"D., Oommen, V ., Varghese, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.811698Z"},"links":{"cited_paper":"/paper/2410.13228","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:d616480dc082d8fd67e025153011079a4e9d7028bf9944461289d1aeeadb7543","observation_id":"fc3cf6b5-0b7a-49c2-b1da-698838336912","resolution":{"observed_at":"2026-08-07T14:41:35.811698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02075","last_updated":"2024-08-12T17:17:00Z","snapshot_observed_at":"2026-07-06T18:25:01.240019Z","submitted_at":"2024-06-04T07:54:31Z","title":"ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02075","snapshot_observed_at":"2026-08-07T14:41:35.351894Z","title":"Relu-kan: New kolmogorov-arnold networks that only need matrix addition, dot multiplication, and relu.arXiv preprint arXiv:2406.02075,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":1999,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.351894Z"},"links":{"cited_paper":"/paper/2406.02075","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:7484d88579b92cb8caa0ba8254c25ab82dde4a3afcaefbaa2f9808f42fad620e","observation_id":"326ef646-7d99-4676-8eea-c9219d744a74","resolution":{"observed_at":"2026-08-07T14:41:35.351894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.04924","last_updated":"2022-09-06T00:42:23Z","snapshot_observed_at":"2026-07-06T13:40:19.948018Z","submitted_at":"2022-08-09T17:40:57Z","title":"On the Activation Function Dependence of the Spectral Bias of Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.04924","snapshot_observed_at":"2026-08-07T14:41:34.654358Z","title":"W., Tan, Q., and Xu, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.654358Z"},"links":{"cited_paper":"/paper/2208.04924","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:d0ebd9b514f8841244b2fb4188d92b2120913bf3c3775821b4ebb83edefe26a2","observation_id":"e6112ab4-4496-431c-8fc0-0b45d5fa43c4","resolution":{"observed_at":"2026-08-07T14:41:34.654358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08468","last_updated":"2023-08-16T16:19:25Z","snapshot_observed_at":"2026-08-08T00:09:25.738049Z","submitted_at":"2023-08-16T16:19:25Z","title":"An Expert's Guide to Training Physics-informed Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08468","snapshot_observed_at":"2026-08-07T14:41:35.997129Z","title":"An expert’s guide to training physics-informed neural networks.arXiv preprint arXiv:2308.08468,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.997129Z"},"links":{"cited_paper":"/paper/2308.08468","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:27b8654d427f0d05b37a05c779376ab2c7de00d481a2db5f085349cb9b70d94c","observation_id":"25de4e36-0473-41d9-b7f9-2bf06b7b37f6","resolution":{"observed_at":"2026-08-07T14:41:35.997129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18380","last_updated":"2025-03-06T10:25:17Z","snapshot_observed_at":"2026-07-06T18:37:21.973331Z","submitted_at":"2024-06-26T14:21:21Z","title":"KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18380","snapshot_observed_at":"2026-08-07T14:41:33.400103Z","title":"Kagnns: Kolmogorov-arnold networks meet graph learning.arXiv preprint arXiv:2406.18380,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.400103Z"},"links":{"cited_paper":"/paper/2406.18380","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:1c7568a5b0b527d6085be2297a50af3710211fad202f66414346a2e4ce6fd733","observation_id":"ba797265-2eec-44f5-8d10-dc9e4b5ecda9","resolution":{"observed_at":"2026-08-07T14:41:33.400103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10205","last_updated":"2024-08-19T17:59:04Z","snapshot_observed_at":"2026-08-07T07:05:01.235030Z","submitted_at":"2024-08-19T17:59:04Z","title":"KAN 2.0: Kolmogorov-Arnold Networks Meet Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10205","snapshot_observed_at":"2026-08-07T14:41:35.166866Z","title":"Kan 2.0: Kolmogorov-arnold networks meet science.arXiv preprint arXiv:2408.10205, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:35.166866Z"},"links":{"cited_paper":"/paper/2408.10205","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:352899c6137798f4383a2df56047a3c3d62e3e8f4be83812e23ac038b2b246eb","observation_id":"4de3d28d-e4ff-4fac-96e8-ceefb02f1c36","resolution":{"observed_at":"2026-08-07T14:41:35.166866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.06286","last_updated":"2024-11-09T21:10:23Z","snapshot_observed_at":"2026-08-03T13:41:45.602286Z","submitted_at":"2024-11-09T21:10:23Z","title":"SPIKANs: Separable Physics-Informed Kolmogorov-Arnold Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.06286","snapshot_observed_at":"2026-08-07T14:41:34.951389Z","title":"A., and Stinis, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.951389Z"},"links":{"cited_paper":"/paper/2411.06286","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:292f8b97c2084421cac7393e442196d778dff9fbff754df96102a49e57c397c3","observation_id":"4ff515cc-ef00-41d0-a7d4-66c3f56515c0","resolution":{"observed_at":"2026-08-07T14:41:34.951389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12832","last_updated":"2024-05-27T15:12:55Z","snapshot_observed_at":"2026-08-08T00:03:19.892740Z","submitted_at":"2024-05-21T14:36:16Z","title":"Wav-KAN: Wavelet Kolmogorov-Arnold Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12832","snapshot_observed_at":"2026-08-07T14:41:33.272364Z","title":"and Chen, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.272364Z"},"links":{"cited_paper":"/paper/2405.12832","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:e374ae7bcfd2875cea500828696bbf97c7acaf862c3e4b96b7de753f5c628c6a","observation_id":"8f553753-46aa-42a7-9086-3d5193a1d80c","resolution":{"observed_at":"2026-08-07T14:41:33.272364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04516","last_updated":"2025-08-14T20:08:19Z","snapshot_observed_at":"2026-07-06T19:46:37.095394Z","submitted_at":"2024-11-07T08:18:33Z","title":"Physics-informed Kolmogorov-Arnold Network with Chebyshev Polynomials for Fluid Mechanics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04516","snapshot_observed_at":"2026-08-07T14:41:34.453631Z","title":"Physics-informed kolmogorov-arnold network with chebyshev polynomials for fluid mechanics.arXiv preprint arXiv:2411.04516,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.453631Z"},"links":{"cited_paper":"/paper/2411.04516","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:bc1a631ce42bc946ffffd49940dd7c06fb3a53cf6442109812fc94eca0f39ef3","observation_id":"50b6f878-a269-41ee-a046-77b8f0b2d59a","resolution":{"observed_at":"2026-08-07T14:41:34.453631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-07T14:41:33.116774Z","title":"L., Kiros, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.116774Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:a3987f69c8ceb5de4fbe1837a80765c342a0b76b9ceeeca54e91021d596c8dae","observation_id":"a0a4eb29-bcf7-403a-8792-52c714472d87","resolution":{"observed_at":"2026-08-07T14:41:33.116774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03027","last_updated":"2024-10-03T22:22:43Z","snapshot_observed_at":"2026-08-04T12:39:47.293872Z","submitted_at":"2024-10-03T22:22:43Z","title":"MLP-KAN: Unifying Deep Representation and Function Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03027","snapshot_observed_at":"2026-08-07T14:41:34.553936Z","title":"Mlp-kan: Unifying deep representation and function learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.553936Z"},"links":{"cited_paper":"/paper/2410.03027","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:cdd61dea9b4b96762589dbca0dacac4f47de8699facd53c46e45a7f241e3ca04","observation_id":"95dcfc66-8209-415f-9deb-f09ddf80ba2d","resolution":{"observed_at":"2026-08-07T14:41:34.553936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07314","last_updated":"2024-09-11T05:10:12Z","snapshot_observed_at":"2026-07-06T19:00:31.507813Z","submitted_at":"2024-08-14T06:15:55Z","title":"Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis","version":3},"cited_work":{"arxiv_id":"2408.07314","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.07314","snapshot_observed_at":"2026-08-07T14:41:37.821206Z","title":"Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis","venue":"cs.LG","work_id":"f19879d2-4821-404a-b2fb-ff453b31078b","year":2024},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.168619Z"},"links":{"cited_paper":"/paper/2408.07314","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:805ff4dec1417b3b1f66920c51d4d890fbe579f56b59300cd2e8466a031352fb","observation_id":"abc002ce-0817-43cb-bf54-5d5797806ed5","resolution":{"observed_at":"2026-08-07T14:41:37.891558Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11075","last_updated":"2025-09-14T09:09:20Z","snapshot_observed_at":"2026-08-07T05:26:14.053971Z","submitted_at":"2024-07-13T04:29:36Z","title":"Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11075","snapshot_observed_at":"2026-08-07T14:41:34.763135Z","title":"and Zhang, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:34.763135Z"},"links":{"cited_paper":"/paper/2407.11075","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:5fa046e87bc072a51cada05ca69952672a2860a6ffe595b21e2ee6b52c631a6c","observation_id":"11af4b06-d585-48ef-a8e4-e23c1e1fccb8","resolution":{"observed_at":"2026-08-07T14:41:34.763135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00326","last_updated":"2024-02-11T22:53:59Z","snapshot_observed_at":"2026-08-08T23:49:46.745808Z","submitted_at":"2024-02-01T04:17:56Z","title":"PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00326","snapshot_observed_at":"2026-08-07T14:41:36.081705Z","title":"Piratenets: Physics-informed deep learning with residual adaptive networks.arXiv preprint arXiv:2402.00326,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:36.081705Z"},"links":{"cited_paper":"/paper/2402.00326","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:52f30f46b590385435ba8adf708d5ed28f04cd6473d8d0db00b3d883927321e1","observation_id":"fcaca961-0a17-484f-a79c-718691a612c0","resolution":{"observed_at":"2026-08-07T14:41:36.081705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13550","last_updated":"2024-09-27T15:41:33Z","snapshot_observed_at":"2026-07-06T19:18:45.024436Z","submitted_at":"2024-09-20T14:49:21Z","title":"A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.13550","snapshot_observed_at":"2026-08-07T14:41:33.607671Z","title":"A preliminary study on continual learning in computer vision using kolmogorov-arnold networks.arXiv preprint arXiv:2409.13550,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:33.607671Z"},"links":{"cited_paper":"/paper/2409.13550","citing_paper":"/paper/2505.18131"},"observation_digest":"sha256:813602296361dffe087de530f77b9f4c758043b3a9b639d3cb1892d0c0de5deb","observation_id":"2a64e3b3-00bd-47b0-b52c-47fe32df0232","resolution":{"observed_at":"2026-08-07T14:41:33.607671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.18131","last_updated":"2025-05-23T17:41:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T00:04:10.552363Z","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":37},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2505.18131."}