From 03f68f76011d510db017d3b15fdd6a231677f79a Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 1 Aug 2026 16:24:08 -0500 Subject: Mark the superseded gate claims in the earlier results documents NATURAL_RESULTS keeps its verdict paragraph but flags that the statistic behind it does not govern recovery, and that the search has since been run. SYNTH_RESULTS gets a note on the parenthesis that turned out to be the whole story: structured fields are low-rank, the threshold formula assumes full-rank noise, and the caveat sat unfollowed for months. Co-Authored-By: Claude --- NATURAL_RESULTS.md | 10 ++++++++++ SYNTH_RESULTS.md | 6 ++++++ logs/obj_large_gpu.log | 2 +- 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/NATURAL_RESULTS.md b/NATURAL_RESULTS.md index 650c77e..e0ea4b7 100644 --- a/NATURAL_RESULTS.md +++ b/NATURAL_RESULTS.md @@ -104,6 +104,16 @@ photographs of the same scene rather than transformations of one. ## Verdict +**Superseded 2026-08-01 — see `RANK_RESULTS.md`.** The go/no-go statistic +used below was shown not to govern recovery: a synthetic field truncated +to rank 8 correlates at 0.906 and recovers 13%, so 0.9 is neither a +threshold nor a licence. The verdict on natural data survives the +correction — the search was subsequently run and returned 0.0000 against +0.0039 chance — but it is now a measurement rather than an inference, and +the deficit is diagnosed as much in the width of the shared spectrum +(15 directions against 26) as in the correlation. The paragraph below is +kept as written for the record. + The go/no-go statistic stands at 0.656 against the 0.9 that polynomial recovery needs, so no recovery run is warranted. The trajectory in one session is 0.166 to 0.656, and the remaining gap is now attributable: diff --git a/SYNTH_RESULTS.md b/SYNTH_RESULTS.md index 0e6617f..ab82851 100644 --- a/SYNTH_RESULTS.md +++ b/SYNTH_RESULTS.md @@ -266,6 +266,12 @@ rho = 0.51--0.57. Identifiable, not efficiently recoverable, exactly as observed. (Our fields are structured rather than Wigner, so the theory guides rather than proves.) +*Added 2026-08-01: that parenthesis was the whole story and we left it +as a parenthesis. Structured means low-rank, and the threshold formula +assumes full-rank noise, which is why the 0.9 figure later turned out to +predict nothing — see `RANK_RESULTS.md`. The caveat was correctly +identified and not followed up for months.* + **Correlation and identifiability are different axes.** The colour channel alone reaches rho = 0.863, far above the mixed descriptor, but its scenes collide: only 126 distinct colour multisets among 256 scenes, diff --git a/logs/obj_large_gpu.log b/logs/obj_large_gpu.log index 0ba1ad7..748f6bd 100644 --- a/logs/obj_large_gpu.log +++ b/logs/obj_large_gpu.log @@ -1,3 +1,3 @@ Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. `torch_dtype` is deprecated! Use `dtype` instead! - segment: 0%| | 0/250 [00:00