# kumo / medicalenv-t12-a16-v1-s28

- taskset: [kumo](https://harnessreport.com/tasks/kumo.md)
- difficulty: medium
- category: reasoning
- language: 
- runnable from the site: no
- agent timeout: 900s

## Results by harness

_none yet_

## Instruction

```
# KUMO Reasoning Game (medicalenv-t12-a16-v1-s28)

One of the following candidate truths is the hidden truth. Your job is to identify it by taking actions (queries) and interpreting the returned observations using the knowledge book.

## Domain / Scenario

- Domain: `MedicalEnv`
- Scenario: `truth_num=12+action_num=16+valid_truth_num=1`

## Candidate Truths

- Sarcoidosis
- Osteoporosis
- Peptic Ulcer Disease
- Unstable Angina
- Alcoholic Liver Disease
- Lung Cancer
- Chronic Kidney Disease
- Inflammatory Bowel Disease (Crohn's Disease)
- Kidney Stones
- COVID-19
- Osteopenia
- Deep Vein Thrombosis

## Available Actions

- COVID-19 PCR Test
- Chest CT Scan
- Liver Function Tests
- Kidney Function Tests
- Urinalysis
- Upper Endoscopy
- Colonoscopy
- Bone Mineral Density Test
- D-Dimer Test
- Electrocardiogram (ECG)
- Chest X-Ray
- Troponin Levels
- Pulmonary Function Tests (Spirometry)
- Influenza Rapid Antigen Test
- Rheumatoid Factor Test
- Tuberculin Skin Test (Mantoux Test)

## How to Interact (Local, Offline)

To take an action and get an observation, run:

```bash
python /app/kumo_cli.py act "<ACTION>"
```

You may take at most **50** action queries. The verifier enforces this limit.

## Knowledge Book

Read the knowledge book (it explains how observations rule out truths):

```bash
cat /app/knowledge_book.txt
```

## Final Answer (Required)

Write **exactly one** truth (verbatim from the “Candidate Truths” list) to:

- `/app/answer.txt`

Example:

```bash
printf '%s\n' 'Some Truth String' > /app/answer.txt
```
```
---
Harness Report runs agent harnesses from their GitHub repos on Harbor tasks and records every model call. Every page is also `.md` and `.json`; index: https://harnessreport.com/llms.txt · MCP: https://harnessreport.com/mcp
