{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LO6524MPAKGZHFXV5RJVVDG2DA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f3ce774bd8dd148cc3428bac36f068832be25b4008e523d6150727fb62be1006","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.optics","submitted_at":"2026-04-09T16:34:58Z","title_canon_sha256":"14d521a2d947850eab5ae8be858103eb49e0cb2f3e1b06b0728eecdd9ea393c0"},"schema_version":"1.0","source":{"id":"2604.08432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08432","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08432v2","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08432","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"LO6524MPAKGZ","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"LO6524MPAKGZHFXV","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"LO6524MP","created_at":"2026-05-20T00:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:6e7362c8b8e117d79cb1e503734fb3ebc17a1c3e32aa74ad8517bc4a03b94fe9","target":"graph","created_at":"2026-05-20T00:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks"}],"snapshot_sha256":"0a4c249540b2a8fe58affd1b3b0741d5845fceadecf6ff92c4a9a44cd11c592e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Egor Manuylovich, Luca Nogueira Cal\\c{c}ado, Sergei K. Turitsyn","cross_cats":["cs.AI"],"headline":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.optics","submitted_at":"2026-04-09T16:34:58Z","title":"Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08432","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:32:10.951920Z","id":"fc1a36b2-2924-4c08-87ba-9b7f9fe30277","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Photonic Kolmogorov-Arnold networks built from a few standard telecom modules achieve 98.4% accuracy on nonlinear tasks","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.","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."}},"verdict_id":"fc1a36b2-2924-4c08-87ba-9b7f9fe30277"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2138d1a4963251985a107fc98d5e354f5aaeb23f29b959fb5f79f8cea3b710da","target":"record","created_at":"2026-05-20T00:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f3ce774bd8dd148cc3428bac36f068832be25b4008e523d6150727fb62be1006","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.optics","submitted_at":"2026-04-09T16:34:58Z","title_canon_sha256":"14d521a2d947850eab5ae8be858103eb49e0cb2f3e1b06b0728eecdd9ea393c0"},"schema_version":"1.0","source":{"id":"2604.08432","kind":"arxiv","version":2}},"canonical_sha256":"5bbddd718f028d9396f5ec535a8cda18182deeece178305507501648ecfe82d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bbddd718f028d9396f5ec535a8cda18182deeece178305507501648ecfe82d0","first_computed_at":"2026-05-20T00:05:44.543150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:44.543150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NjqOlN7y6MHWdkM5aPlUbc0sloFHA1jX2n6rlnhw7pg6lcaEJaRNqjPWz/mj99BucmsDSzJnPysHscANqsZRCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:44.543584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2138d1a4963251985a107fc98d5e354f5aaeb23f29b959fb5f79f8cea3b710da","sha256:6e7362c8b8e117d79cb1e503734fb3ebc17a1c3e32aa74ad8517bc4a03b94fe9"],"state_sha256":"ac320428c06ca6df6ba9f1995e595bd93a1f10982179aa5ead2c94c6633dca14"}