R1ckyTu commited on
Commit
5fc08a5
·
verified ·
1 Parent(s): 9be804a

Org card: five showcase tasks

Browse files
Files changed (1) hide show
  1. README.md +15 -3
README.md CHANGED
@@ -1,10 +1,22 @@
1
  ---
2
  title: README
3
- emoji: 🏆
4
  colorFrom: indigo
5
- colorTo: purple
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: README
3
+ emoji: 📝
4
  colorFrom: indigo
5
+ colorTo: blue
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
+ # Continual Learning Exam
11
+
12
+ Long-horizon agent tasks set in real professional jobs. Each task runs over five stages (T1–T5): the agent works through mail, chat, calendars and workspace files, and what it delivers at one stage becomes input to the next.
13
+
14
+ Five tasks are public in **[CLE-Showcase](https://huggingface.co/datasets/Continual-Learning-Exam/CLE-Showcase)**, with their evaluation materials:
15
+
16
+ | Task | Setting |
17
+ |---|---|
18
+ | 3 | Software-sector equity research: from a Rubrik IPO brief to fact-checking a quarterly LP update (Chinese and English editions) |
19
+ | 50 | Ulcerative colitis biomarker cohort assembly from GEO and consortium data |
20
+ | 120 | TCGA-KIRC prognostic genomics: Cox screen, stability, survival, methylation and copy number |
21
+ | 144 | ESG reporting on published Techtronic Industries FY2024 disclosures |
22
+ | 165 | A PhD student reproducing τ²-bench: literature, figure provenance and a pipeline audit |