{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LO6524MPAKGZHFXV5RJVVDG2DA","short_pith_number":"pith:LO6524MP","schema_version":"1.0","canonical_sha256":"5bbddd718f028d9396f5ec535a8cda18182deeece178305507501648ecfe82d0","source":{"kind":"arxiv","id":"2604.08432","version":2},"attestation_state":"computed","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"},"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":"2604.08432","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.optics","submitted_at":"2026-04-09T16:34:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14d521a2d947850eab5ae8be858103eb49e0cb2f3e1b06b0728eecdd9ea393c0","abstract_canon_sha256":"f3ce774bd8dd148cc3428bac36f068832be25b4008e523d6150727fb62be1006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:44.543584Z","signature_b64":"NjqOlN7y6MHWdkM5aPlUbc0sloFHA1jX2n6rlnhw7pg6lcaEJaRNqjPWz/mj99BucmsDSzJnPysHscANqsZRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bbddd718f028d9396f5ec535a8cda18182deeece178305507501648ecfe82d0","last_reissued_at":"2026-05-20T00:05:44.543150Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:44.543150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.08432","created_at":"2026-05-20T00:05:44.543209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.08432v2","created_at":"2026-05-20T00:05:44.543209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08432","created_at":"2026-05-20T00:05:44.543209+00:00"},{"alias_kind":"pith_short_12","alias_value":"LO6524MPAKGZ","created_at":"2026-05-20T00:05:44.543209+00:00"},{"alias_kind":"pith_short_16","alias_value":"LO6524MPAKGZHFXV","created_at":"2026-05-20T00:05:44.543209+00:00"},{"alias_kind":"pith_short_8","alias_value":"LO6524MP","created_at":"2026-05-20T00:05:44.543209+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/LO6524MPAKGZHFXV5RJVVDG2DA","json":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA.json","graph_json":"https://pith.science/api/pith-number/LO6524MPAKGZHFXV5RJVVDG2DA/graph.json","events_json":"https://pith.science/api/pith-number/LO6524MPAKGZHFXV5RJVVDG2DA/events.json","paper":"https://pith.science/paper/LO6524MP"},"agent_actions":{"view_html":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA","download_json":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA.json","view_paper":"https://pith.science/paper/LO6524MP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.08432&json=true","fetch_graph":"https://pith.science/api/pith-number/LO6524MPAKGZHFXV5RJVVDG2DA/graph.json","fetch_events":"https://pith.science/api/pith-number/LO6524MPAKGZHFXV5RJVVDG2DA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA/action/storage_attestation","attest_author":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA/action/author_attestation","sign_citation":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA/action/citation_signature","submit_replication":"https://pith.science/pith/LO6524MPAKGZHFXV5RJVVDG2DA/action/replication_record"}},"created_at":"2026-05-20T00:05:44.543209+00:00","updated_at":"2026-05-20T00:05:44.543209+00:00"}