{"paper":{"title":"Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks","cross_cats":["cs.AI"],"primary_cat":"physics.optics","authors_text":"Egor Manuylovich, Luca Nogueira Cal\\c{c}ado, Sergei K. Turitsyn","submitted_at":"2026-04-09T16:34:58Z","abstract_excerpt":"Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities, reintroducing optical-electrical-optical bottlenecks. Here we introduce small-scale photonic Kolmogorov-Arnold networks (SSP-KANs) implemented entirely with standard telecommunications components. Each network edge employs a trainable nonlinear module composed of a Mach-Zehnder interferometer, semiconductor optical amplifier, and variable optical attenuators, providing a four-parameter transfer function derived from gain saturation and interferometric mixin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A four-module network achieves 98.4% accuracy on nonlinear classification benchmarks inaccessible to linear models. Performance remains robust under realistic hardware impairments, maintaining high accuracy down to 6-bit input resolution and 14 dB signal-to-noise ratio.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The four-parameter optical transfer function per edge is sufficiently expressive for the target tasks and that the end-to-end differentiable physics model accurately predicts real-device behavior without unmodeled impairments or fabrication variations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Small photonic KANs using commodity telecom nonlinear modules reach 98.4% accuracy on nonlinear classification with only four modules and remain robust to hardware impairments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0a4c249540b2a8fe58affd1b3b0741d5845fceadecf6ff92c4a9a44cd11c592e"},"source":{"id":"2604.08432","kind":"arxiv","version":2},"verdict":{"id":"fc1a36b2-2924-4c08-87ba-9b7f9fe30277","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:32:10.951920Z","strongest_claim":"A four-module network achieves 98.4% accuracy on nonlinear classification benchmarks inaccessible to linear models. Performance remains robust under realistic hardware impairments, maintaining high accuracy down to 6-bit input resolution and 14 dB signal-to-noise ratio.","one_line_summary":"Small photonic KANs using commodity telecom nonlinear modules reach 98.4% accuracy on nonlinear classification with only four modules and remain robust to hardware impairments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The four-parameter optical transfer function per edge is sufficiently expressive for the target tasks and that the end-to-end differentiable physics model accurately predicts real-device behavior without unmodeled impairments or fabrication variations.","pith_extraction_headline":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08432/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"}