Spaces:
Running
Running
Org card: five showcase tasks
Browse files
README.md
CHANGED
|
@@ -1,10 +1,22 @@
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: indigo
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
|