docs/technical/07_conditioning_probe_program.md: paraphrase the program lead's directives (no inline quotations)

docs/technical/07_conditioning_probe_program.md

@@ -2,7 +2,7 @@
 
 ## 7. The probe program
 
-**(2026-08-30 → 09-01.)** The conditioning-probe program asks one question of every representation the shop has built: does it carry the geometry a text-to-image diffusion model needs from its text encoder? Phil's ask on 08-30 was "Can we potentially extract an enriched structure capable of conditioning a diffusion model?" and, of the candidates listed, "Test them." The instrument never changed: 2,048 COCO captions in one draw (seed 7), each representation gauged against a reference encoder by the mean Jaccard overlap of top-10 cosine-neighbour sets and the Spearman correlation of cosine similarities over ~100k random caption pairs, with a random-Gaussian floor (Jaccard .005 / Spearman −.005) as zero. One statistical fact governs the whole section: every number below is **one caption draw and one calibration** — no second draw, no repeat, no effective-rank column on any of ~140 cells, no failing control beyond the floor and one random-init model — so every grade is provisional under the retro-audit's rider that ranks are draw properties until a bar is measured, and the ±.01–.02 "wobble" the journal invokes was asserted, never measured.
+**(2026-08-30 → 09-01.)** The conditioning-probe program asks one question of every representation the shop has built: does it carry the geometry a text-to-image diffusion model needs from its text encoder? Phil's question on 08-30 was whether an enriched structure capable of conditioning a diffusion model could be extracted from the craft and, of the candidates listed, "Test them." The instrument never changed: 2,048 COCO captions in one draw (seed 7), each representation gauged against a reference encoder by the mean Jaccard overlap of top-10 cosine-neighbour sets and the Spearman correlation of cosine similarities over ~100k random caption pairs, with a random-Gaussian floor (Jaccard .005 / Spearman −.005) as zero. One statistical fact governs the whole section: every number below is **one caption draw and one calibration** — no second draw, no repeat, no effective-rank column on any of ~140 cells, no failing control beyond the floor and one random-init model — so every grade is provisional under the retro-audit's rider that ranks are draw properties until a bar is measured, and the ±.01–.02 "wobble" the journal invokes was asserted, never measured.
 
 ### PROBE-1: the mid-depth blackboard