diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-08-01 16:15:41 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-08-01 16:15:41 -0500 |
| commit | 08fd63b8fee62ccdc284380c9832900ee83f9ede (patch) | |
| tree | 53d49406a0b778e25c7604a7ae0fe5d2ecf15367 /artifacts/synth_v1/omit_colour.json | |
| parent | 58b9c84dae293359f498fdf6afd533df5c9d3c25 (diff) | |
Retire the correlation gate: the shared spectrum governs recovery
A controlled truncation refutes the project's central go/no-go rule.
Projecting the recovering synthetic fields to rank r holds the field
correlation at 0.902-0.929 while recovery moves 6.2% -> 12.9% -> 95.6%
across ranks 4, 8, 16. A field past the supposed 0.9 threshold recovers
13%, so correlation neither predicts nor forbids recovery and the width
of the shared spectrum is what moves it.
The gate becomes a joint condition on correlation and shared width,
measured by principal angles against a scene-shuffled null. Neither
suffices alone: 18 shared directions at 0.508 fails, 11 at 0.902 fails.
With the old gate retired, natural data was finally searched: 0.0000
against 0.0039 chance. The old verdict was right, its reasoning was not.
Also closes route D by measurement. rho_IT ~ sqrt(4 log N / N) rises as N
falls, and at N = 16 through 96 the deepest state a strong searcher
reaches is deeper than the truth in 3/3 replicates at every size.
Free gains: eigenvalue-weighted projection over a wide basis with
128-dim text vectors takes the correlation 0.656 -> 0.716 and shared
width 10 -> 16. Hubness refuted as an inflation hypothesis.
Moving the per-image segmentation eigendecomposition onto the GPU cut
batch time from 130s to 1.9s.
Co-Authored-By: Claude <noreply@anthropic.com>
Diffstat (limited to 'artifacts/synth_v1/omit_colour.json')
| -rw-r--r-- | artifacts/synth_v1/omit_colour.json | 34 |
1 files changed, 34 insertions, 0 deletions
diff --git a/artifacts/synth_v1/omit_colour.json b/artifacts/synth_v1/omit_colour.json new file mode 100644 index 0000000..61f71bc --- /dev/null +++ b/artifacts/synth_v1/omit_colour.json @@ -0,0 +1,34 @@ +{ + "data_dir": "artifacts/synth_v1", + "split": "test", + "samples": 256, + "colour_classes": 10, + "text_families": { + "count_words": [ + "a", + "three", + "four", + "two" + ], + "colour_words": [ + "red", + "orange", + "yellow", + "green", + "blue", + "purple", + "pink", + "white", + "gray", + "brown" + ], + "size_words": [ + [ + "small", + "large" + ] + ] + }, + "field_correlation_at_truth": 0.7356797393477761, + "note": "The dictionary is derived from disjoint corpora; the correlation is a diagnostic computed with hidden pairs and never used by the pipeline." +}
\ No newline at end of file |
