1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
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
}
]
}
|
