Transfer
Our published model applied to your data, with no refitting.
Does our model work outside our own lab?
1 Your measurements
A CSV or tab-separated file with one row per machining condition. Semicolon separators and decimal commas from European Excel exports are handled automatically, as are leading title rows.
Drop your file here, or click to choose
.csv, .txt, .tsv — nothing is uploaded
Not sure about the format? Download the template — it already contains the expected columns and two example rows.
2 Match your columns
We guessed the correspondence from your column names. Correct anything that is wrong — the models need these four cutting parameters, in these units.
3 Your two scores
Refit
The model refitted on your data only, scored by leave-one-out.
Are your measurements predictable at all?
Full numbers and fitted coefficients
4 Contribute to the global model optional
Contributing improves the model for everyone without disclosing your measurements. What leaves your browser is listed in full below, and you can inspect it before sending.
What is sent
- What you type in the form below: your name, laboratory, material, measurement method.
- The number of rows and the range (min–max) of each cutting parameter.
- Summary sums over your data —
D'D,D'y,y'y,n— which let us refit the model on the pooled data exactly, without moving any measurement. - The coefficients fitted on your machine, and the two scores above.
What is never sent
- Your measurement table. No row, no individual value, at any point.
One honest caveat: those summary sums are not anonymous. On very few rows they reveal a lot about the dataset — with a single row they would give it away entirely. This is why contributions need at least 5 rows, and why we say so here rather than claiming a guarantee we cannot make.
The global model
Each contribution is reviewed, then folded into a new version by an exact refit on the pooled sums — not by averaging coefficients.