jamie8johnson commited on
Commit
1344331
·
verified ·
1 Parent(s): d6b546c

eval: fix dataset IDs to CoIR-Retrieval org + per-language CSN scores

Browse files
Files changed (1) hide show
  1. .eval_results/coir-v7.yaml +36 -18
.eval_results/coir-v7.yaml CHANGED
@@ -1,53 +1,71 @@
1
  - dataset:
2
- id: archersama/codesearchnet
3
  task_id: default
4
- value: 0.707
5
  date: '2026-03-22'
6
- notes: avg NDCG@10 across 6 languages (Go/Java/JS/Ruby/Python/PHP)
7
  - dataset:
8
- id: archersama/cosqa
9
  task_id: default
10
- value: 0.354
11
  date: '2026-03-22'
12
- notes: NDCG@10, out-of-distribution transfer
 
 
 
 
 
 
 
 
 
 
 
 
13
  - dataset:
14
- id: archersama/codesearchnet-ccr
15
  task_id: default
16
- value: 0.508
17
  date: '2026-03-22'
18
- notes: avg NDCG@10, cross-code retrieval
19
  - dataset:
20
- id: archersama/apps
21
  task_id: default
22
- value: 0.105
23
  date: '2026-03-22'
24
- notes: NDCG@10, program synthesis
25
  - dataset:
26
- id: archersama/codetrans-dl
 
 
 
 
 
 
27
  task_id: default
28
  value: 0.194
29
  date: '2026-03-22'
30
- notes: NDCG@10, code translation
31
  - dataset:
32
- id: archersama/stackoverflow-qa
33
  task_id: default
34
  value: 0.882
35
  date: '2026-03-22'
36
  notes: NDCG@10
37
  - dataset:
38
- id: archersama/codefeedback-mt
39
  task_id: default
40
  value: 0.382
41
  date: '2026-03-22'
42
  notes: NDCG@10, multi-turn
43
  - dataset:
44
- id: archersama/codefeedback-st
45
  task_id: default
46
  value: 0.737
47
  date: '2026-03-22'
48
  notes: NDCG@10, single-turn
49
  - dataset:
50
- id: archersama/synthetic-text2sql
51
  task_id: default
52
  value: 0.558
53
  date: '2026-03-22'
 
1
  - dataset:
2
+ id: CoIR-Retrieval/codesearchnet-go-queries-corpus
3
  task_id: default
4
+ value: 0.785
5
  date: '2026-03-22'
6
+ notes: NDCG@10, Go
7
  - dataset:
8
+ id: CoIR-Retrieval/codesearchnet-java-queries-corpus
9
  task_id: default
10
+ value: 0.656
11
  date: '2026-03-22'
12
+ notes: NDCG@10, Java
13
+ - dataset:
14
+ id: CoIR-Retrieval/codesearchnet-javascript-queries-corpus
15
+ task_id: default
16
+ value: 0.545
17
+ date: '2026-03-22'
18
+ notes: NDCG@10, JavaScript
19
+ - dataset:
20
+ id: CoIR-Retrieval/codesearchnet-ruby-queries-corpus
21
+ task_id: default
22
+ value: 0.613
23
+ date: '2026-03-22'
24
+ notes: NDCG@10, Ruby
25
  - dataset:
26
+ id: CoIR-Retrieval/codesearchnet-python-queries-corpus
27
  task_id: default
28
+ value: 0.975
29
  date: '2026-03-22'
30
+ notes: NDCG@10, Python
31
  - dataset:
32
+ id: CoIR-Retrieval/codesearchnet-php-queries-corpus
33
  task_id: default
34
+ value: 0.667
35
  date: '2026-03-22'
36
+ notes: NDCG@10, PHP
37
  - dataset:
38
+ id: CoIR-Retrieval/cosqa-queries-corpus
39
+ task_id: default
40
+ value: 0.354
41
+ date: '2026-03-22'
42
+ notes: NDCG@10, out-of-distribution transfer
43
+ - dataset:
44
+ id: CoIR-Retrieval/codetrans-dl-queries-corpus
45
  task_id: default
46
  value: 0.194
47
  date: '2026-03-22'
48
+ notes: NDCG@10
49
  - dataset:
50
+ id: CoIR-Retrieval/stackoverflow-qa-queries-corpus
51
  task_id: default
52
  value: 0.882
53
  date: '2026-03-22'
54
  notes: NDCG@10
55
  - dataset:
56
+ id: CoIR-Retrieval/codefeedback-mt-queries-corpus
57
  task_id: default
58
  value: 0.382
59
  date: '2026-03-22'
60
  notes: NDCG@10, multi-turn
61
  - dataset:
62
+ id: CoIR-Retrieval/codefeedback-st-queries-corpus
63
  task_id: default
64
  value: 0.737
65
  date: '2026-03-22'
66
  notes: NDCG@10, single-turn
67
  - dataset:
68
+ id: CoIR-Retrieval/synthetic-text2sql-queries-corpus
69
  task_id: default
70
  value: 0.558
71
  date: '2026-03-22'