NakedSignal OS · Documentation
Back to the consoleDocumentation

Process and surface inspection

LIVE

Semiconductor fabrication pass/fail and steel plate surface faults. The fab corpus is split chronologically rather than at random, because a process-monitoring model is always asked to predict forward in time — and it has 590 sensor channels over 1,567 lots, so it is expected to be hard and the intervals say so. No separate specification document has been published for this benchmark — the MedEval-1 spec is the document, and this page is that instrument run on another corpus. Everything below is read from the same payload.json the medical leaderboard renders from.

spec MedEval-1 v0.1code fingerprint de32bca72d56seed 20260727device mpsgenerated 2026-08-03T19:03+00:00
4
models scored
2
tasks
8
scored records
878
held-out cases
71.1
best index — Gradient boosting

The index is the weighted mean of the dimensions that were scored, on the weights published in the spec. Dimensions this corpus cannot support are excluded from it rather than counted as zero, which is why an index here is not comparable to a medical one model-for-model — it is a mean over a different set of questions, and the table below says which.

Every model, on all 9 dimensions

Ranked by index. An em-dash is a dimension the harness left null.
#ModelIndex1 Accuracy2 Cross-site3 Calibration4 Limited data5 Subgroup6 Corruption7 Uncertainty Specification sensitivity Cost, latency & footprint
1Gradient boosting200 stages, depth 3, lr 0.0571.175.474.580.348.665.090.9
2Random forest400 trees70.376.054.889.748.272.491.9
3MLP (128, 64)2 hidden layers, adam, early stopping when n>=20068.269.174.591.430.668.285.9
4Logistic regressionstandardised, L2, C=167.170.466.092.634.266.182.4
5Gradient boosting200 stages, depth 3, lr 0.0523.50.071.90.00.086.2
6Random forest400 trees22.40.066.20.00.087.1
7Logistic regressionstandardised, L2, C=121.20.061.80.00.085.2
8MLP (128, 64)2 hidden layers, adam, early stopping when n>=20012.80.024.60.00.084.0
Empty columns, and why they are empty
  • 2. Cross-site robustness No re-acquisition of the same subjects exists in this corpus, so there is nothing to measure. Widening the definition to fill the cell would be a spec change, not a demo.
  • . Not computed on any record in this benchmark, and not approximated.
  • . Not computed on any record in this benchmark, and not approximated.

The measurements the scores came from

Raw metrics, not the 0–100 rescaling.
ModelBalanced accuracy (95% CI)AUCECERisk–coverage AUCMean label-budget retention
Gradient boosting0.789[0.7400.828]0.9510.0510.9220.803
Random forest0.794[0.7460.834]0.9610.0900.9300.897
MLP (128, 64)0.736[0.6830.789]0.9340.0510.8790.914
Logistic regression0.747[0.7000.793]0.9330.0680.8490.926
Gradient boosting0.481[0.4710.490]0.4670.0560.9310.000
Random forest0.499[0.4960.500]0.4480.0680.9350.000
Logistic regression0.493[0.4870.499]0.6090.0760.9260.000
MLP (128, 64)0.493[0.4870.497]0.3820.1510.9200.000

Balanced accuracy carries a bootstrap 95% interval; read it before reading the rank. ECE is expected calibration error, so lower is better and the 0–100 dimension score inverts it. Every value here is on the record; hover any figure for the unrounded number.

Who the best model fails

LIVE

Dimension five, on Gradient boosting — the top-ranked model above. Basis, in the evaluator’s own words: worst demographic subgroup (real metadata). This is the strong reading — the corpus ships the attributes, so the harness did not have to fall back to the worst-class proxy every medical imaging task uses.

steel_typegap 0.184 · worst group 0.559
A300worst0.559
A4000.744

Per-group recall, and the gap between the best and worst group. These numbers measure who the model fails on this corpus. They are not an audit of any deployed system, and the subgroup attributes are model inputs here, as they are in the standard formulation of the task.

The corpus

Semiconductor fabrication pass/fail

secom · Tabular / process sensors
Source
UCI SECOMMcCann & Johnston, SECOM, UCI ML Repository, DOI 10.24432/C54305
Split
chronological split minted by MedEval-1 on the production timestamp shipped in secom_labels.data: earliest 60% train, next 15% validation, latest 25% test. A random split is not defensible on a process-monitoring corpus -- tools drift and are recalibrated, so shuffling lets the model interpolate a tool's state from wafers measured minutes on either side, while production always extrapolates forward. Missing values imputed with the TRAIN median only; channels all-missing or constant on the training period dropped (468 of 590 channels kept).
Sizes
940 train · 392 held out · 2 classes
Classes
pass · fail
Registry note
590 sensor channels over 1,567 production lots, 6.6% failures, heavy missingness. Split is CHRONOLOGICAL on the recorded timestamp, not random: a process-monitoring model is always asked to predict forward in time, and a random split lets it interpolate within a drift it would never see the far side of in production. p is more than a third of n, so this task is expected to be hard and the intervals are expected to be wide -- that is the finding, not a defect.

Steel plate surface faults (7-class)

steel_plate_faults · Tabular / imaging-derived
Source
Semeion Research Center / UCI Steel Plates FaultsSemeion Research Center of Sciences of Communication, UCI ML Repository, DOI 10.24432/C5J88N
Split
minted by MedEval-1 (stratified 60/15/25, seed 20260727); no official split is published for this corpus. The label is the argmax of the seven trailing one-hot fault columns, which are dropped from the features.
Sizes
1,164 train · 486 held out · 7 classes
Classes
pastry · z_scratch · k_scratch · stains · dirtiness · bumps · other
Registry note
Geometric and luminosity descriptors from real plate photographs. Subgroup metadata is the steel grade (A300/A400) -- an industrial stratum rather than a demographic one, and dimension 5 reports it as exactly that. The largest class is a catch-all 'other', so a 7-way accuracy figure is partly a measure of how well a model predicts 'none of the above'.

Re-derive every figure on this page with python src/build_site.py --emit-json in plan_d/ — the same run writes the medical leaderboard. All benchmarks reads the same 9 dimensions per domain, and the trust graph traces any figure here back to the run that produced it.