From 08fd63b8fee62ccdc284380c9832900ee83f9ede Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 1 Aug 2026 16:15:41 -0500 Subject: 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 --- artifacts/synth_v1/omit_colour.json | 34 ++++++++++++++++++++++ artifacts/synth_v1/omit_count.json | 34 ++++++++++++++++++++++ artifacts/synth_v1/omit_none.json | 34 ++++++++++++++++++++++ artifacts/synth_v1/omit_size.json | 34 ++++++++++++++++++++++ artifacts/synth_v1/omit_size_count.json | 34 ++++++++++++++++++++++ artifacts/synth_v1/rank_causal.json | 51 +++++++++++++++++++++++++++++++++ 6 files changed, 221 insertions(+) create mode 100644 artifacts/synth_v1/omit_colour.json create mode 100644 artifacts/synth_v1/omit_count.json create mode 100644 artifacts/synth_v1/omit_none.json create mode 100644 artifacts/synth_v1/omit_size.json create mode 100644 artifacts/synth_v1/omit_size_count.json create mode 100644 artifacts/synth_v1/rank_causal.json (limited to 'artifacts/synth_v1') 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 diff --git a/artifacts/synth_v1/omit_count.json b/artifacts/synth_v1/omit_count.json new file mode 100644 index 0000000..7a40369 --- /dev/null +++ b/artifacts/synth_v1/omit_count.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": 0.678442918934101, + "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 diff --git a/artifacts/synth_v1/omit_none.json b/artifacts/synth_v1/omit_none.json new file mode 100644 index 0000000..7ff06f9 --- /dev/null +++ b/artifacts/synth_v1/omit_none.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": 0.9284809883663888, + "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 diff --git a/artifacts/synth_v1/omit_size.json b/artifacts/synth_v1/omit_size.json new file mode 100644 index 0000000..d81aa00 --- /dev/null +++ b/artifacts/synth_v1/omit_size.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": 0.8301825436675783, + "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 diff --git a/artifacts/synth_v1/omit_size_count.json b/artifacts/synth_v1/omit_size_count.json new file mode 100644 index 0000000..2eca4dc --- /dev/null +++ b/artifacts/synth_v1/omit_size_count.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": 0.5442660429860929, + "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 diff --git a/artifacts/synth_v1/rank_causal.json b/artifacts/synth_v1/rank_causal.json new file mode 100644 index 0000000..222e469 --- /dev/null +++ b/artifacts/synth_v1/rank_causal.json @@ -0,0 +1,51 @@ +{ + "protocol": "Both fields truncated to the same rank, then matched blind from a spectral start with exact refinement. Hidden pairing generated per trial and read only for scoring.", + "label": "synthetic-watershed", + "size": 256, + "chance": 0.00390625, + "rows": [ + { + "rank": 4, + "correlation": 0.9016677754313268, + "recovery": 0.0625, + "visual_effective_rank": 44.86571084196529 + }, + { + "rank": 8, + "correlation": 0.9058447537972105, + "recovery": 0.12890625, + "visual_effective_rank": 71.3420544398913 + }, + { + "rank": 16, + "correlation": 0.9281446653770646, + "recovery": 0.9557291666666666, + "visual_effective_rank": 95.72603497323556 + }, + { + "rank": 32, + "correlation": 0.9282073730691501, + "recovery": 0.9375, + "visual_effective_rank": 109.47942916160699 + }, + { + "rank": 64, + "correlation": 0.9284208632987705, + "recovery": 0.9583333333333334, + "visual_effective_rank": 106.31167521180129 + }, + { + "rank": 128, + "correlation": 0.9284791170404748, + "recovery": 0.9609375, + "visual_effective_rank": 106.04029186749484 + }, + { + "rank": 256, + "correlation": 0.928480988366389, + "recovery": 0.9583333333333334, + "visual_effective_rank": 106.03700034539153 + } + ], + "reading": "Recovery collapsing at low rank while the correlation stays above the recovery threshold shows the headline correlation is not sufficient and the shared spectrum's width is the binding constraint." +} \ No newline at end of file -- cgit v1.2.3