It Quoted the Failure: Two Kinds of False 'Done'

Automated excerpt

T2 plus one sentence: report done only if a line shows the final check passed. Under T3, no model said "done" on a failed check in two of three runs, but never-ran "done" jumped for all four. Vary the strength of the proof sentence, tracking never-ran work called done against passed work denied done.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.