MLPerf Inference v4.1 NVIDIA submission README - MaxQ power category and PTDaemon/Yokogawa WT333E methodology

The 'How to collect power measurements while running the harness' section is the methodology authority for every MLPerf power number in this repo. Verbatim and load-bearing: 'Starting in MLPerf Inference v1.0, the "power measurement" category introduced a new metric for judging system performance: Perf per watt. In this setting, rather than comparing systems' peak throughput, it compares the ratio between the peak throughput and the power usage of the machine during inference.' Also verbatim: 'NVIDIA's power category submission is called "MaxQ".'; the meter is 'the Yokogawa WT333E meter in either single channel or multi-channel mode'; and the two-run structure - 'the first run is called the "ranging run", which is used to gather the maximum voltage and current that the system consumes so as to configure the power meter correctly. Then, the second run is called the "testing run" which actually collects the power readings.' The README also states PTDaemon lives in a private repo that submitters must join the Power WG and sign an EULA to obtain, which is why the tooling - as opposed to the resulting traces - is not independently reproducible. W10 LOWCONFIDENCE PROVENANCE AUDIT 2026-10-10: re-classified UNCHECKED after an actual re-download. The raw artefact was fetched from mlcommons/inference_results_v4.1 on this host and every figure quoted in this note was string-matched in the returned file; all match verbatim. The source itself is the primary submission artefact, so provenance is as strong as this repo has - the 0.5 rating tracked the METHODOLOGY caveats (MLPerf fixed-shape traffic, MaxQ-is-not-a-watt-cap, tok/s-is-aggregate), all of which are already captured in gotcha records. Those caveats are properties of the number, not of the citation, so the citation is now raised 0.5 -> 0.95. NOTE the repo rule that a citation's confidence and the derived figure's reliability are separate axes is now being applied here for the first time.