summaryrefslogtreecommitdiff
path: root/artifacts
diff options
context:
space:
mode:
Diffstat (limited to 'artifacts')
-rw-r--r--artifacts/vg_5k/encoder_matrix.json48
1 files changed, 48 insertions, 0 deletions
diff --git a/artifacts/vg_5k/encoder_matrix.json b/artifacts/vg_5k/encoder_matrix.json
new file mode 100644
index 0000000..a4dc2d9
--- /dev/null
+++ b/artifacts/vg_5k/encoder_matrix.json
@@ -0,0 +1,48 @@
+{
+ "protocol": "Vision side held fixed (DINOv2-base segments). Only the text encoder varies. All encoders are trained on text alone; no vision-language model is admissible. Priced by the anchor bound, since field correlation was shown not to govern recovery.",
+ "vg_part_oracle_ceiling": 0.359,
+ "rows": [
+ {
+ "encoder": "PPMI (incumbent)",
+ "dimension": 128,
+ "correlation": 0.7154847097529566,
+ "anchor_bound": 0.2890625
+ },
+ {
+ "encoder": "MiniLM-L6 (22M)",
+ "dimension": 384,
+ "correlation": 0.7181425459501315,
+ "anchor_bound": 0.328125
+ },
+ {
+ "encoder": "mpnet-base (110M)",
+ "dimension": 768,
+ "correlation": 0.725563692615733,
+ "anchor_bound": 0.340625
+ },
+ {
+ "encoder": "bert-base (110M)",
+ "dimension": 768,
+ "correlation": 0.7420831753105741,
+ "anchor_bound": 0.340625
+ },
+ {
+ "encoder": "BGE-large (335M)",
+ "dimension": 1024,
+ "correlation": 0.7283621429669194,
+ "anchor_bound": 0.3078125
+ },
+ {
+ "encoder": "Qwen2.5-0.5B",
+ "dimension": 896,
+ "correlation": 0.7278852227261461,
+ "anchor_bound": 0.325
+ },
+ {
+ "encoder": "Qwen2.5-1.5B",
+ "dimension": 1536,
+ "correlation": 0.7281876334842069,
+ "anchor_bound": 0.3109375
+ }
+ ]
+} \ No newline at end of file