Scan to Floor Plan

Six and nine are not in conflict: six is how many generations the comparison keeps side by side, and nine is the source repo's own pipeline version number for the third of them, grid_v9. The apartment plan published on this site was drawn by that ninth version, a plain grid method, and its title block says so; the villa beside it was drawn by v11 footprint, an earlier plain method. Both are versions the learned pipeline was built to supersede, which is the finding, and each sheet names its own method. The machine-learning pipeline that superseded it on paper wins on two scans out of eighteen, and still won two after fine-tuning; three once it is paired with a plain method's building outline as an ensemble. Knowing why is worth more than the pipeline would have been.

The apartment plan published on this site was drawn by the ninth version, a plain grid method, and its own title block says so. Anyone can check: the label reads grid_v9. The villa beside it reads v11_footprint, an earlier plain method, and that is the point rather than an exception: both published plans were drawn by versions the learned pipeline was built to supersede. That is the honest state of this work, and shipping the version that scores best rather than the version that sounds best is the whole point of having built the scoreboard. The learned pipeline is not abandoned; it is waiting on being paired with something that fixes the area shortfall, which is a different piece of work from tuning it harder.