Set up two zones and run the fire, or replay a designed example. After each run the page places the student in the researchers' original grouping (exact) and estimates their discovered cluster (live), explains the estimate, and flags where either reading misleads.
This panel stands in for the model's Setup and spark tools. The page does not simulate fire spread; it codes and traces the setups. For the real model, use the live monitor.
N nothing differs · O only drought differs · I one other setting · M several. Upper case = one spark in each zone. = identical rerun · * zones same, wind/sparks changed · + same comparison, tweaked. C = O then +.
The original side is computed exactly from the runs. The discovered side is a logistic model on rule-computed features that predicts the Sonnet-labelled cluster: 86% accurate on whole sessions (cross-validated), 70% after 3 runs. BKT, above, tracks skill; both sides here name a pattern of behaviour.
| # | Zone 1 | Zone 2 | Sparks | Wind | Code | Fair test | P(L) after |
|---|