How often does a model absorb your words into the artifact?

Every model is given the same 300 editing tasks. A pasted artifact is followed by one trailing user comment, and the seam between them is varied. Absorption = the comment's content shows up in the returned artifact when it is absent from the matched clean run. Lower is better. Click any row to read that model's actual outputs on sampled prompts.

# Model Bare newline Blank line Boundary tags Tags + instruction Native comment Marker gain

Swipe the table sideways to see every seam condition.

0%75%
Marker gain = bare-newline rate − boundary-tag rate, in percentage points.
Bars scale to the selected condition; every cell shows its own rate and 95% Wilson interval.

Rates come from the released run statistics (release/results/statistics.json). Absorption is counted only when the comment's content appears in the treatment output and is absent from the matched clean output, scored by the three-tier cascade: exact phrase → stemmed content words → DeBERTa entailment.