Integrity report for Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.

arXiv:2605.20706 · pith:2026:Z7TJCSCUWWFQEVJQVOY6LR5C75

0Critical

0Advisory

6Detectors run

2026-05-22Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-22 04:42:41.877500+00:00

doi_compliance completed v1.0.0 · findings 0 · 2026-05-22 03:03:08.636334+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-22 03:01:48.489570+00:00

citation_quote_validity completed v0.1.0 · findings 0 · 2026-05-21 19:50:42.263548+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-21 14:22:27.153812+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-21 02:33:35.301474+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/Z7TJCSCUWWFQEVJQVOY6LR5C75/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.