Checklist INAIO 2025 Stage 2 · Task 5
Classifying the Unnown: Decoding the Mystery of Genetics and Terrain
Cluster fictional creatures by location and classify their genetic strain (A–D) from location and physiological traits with sparse labels.
The task
On the fictional island of Poké, 'Unnown' creatures have genetic strains A, B, C or D that relate only loosely to terrain and physiology, and only a few specimens are labelled. Q1 explores the data; Q2 implements learn_location_clusters with k-means and evaluates clustering against known labels (NMI, homogeneity, completeness); Q3 trains a strain classifier; Q4 tests on a public set; Q5 is private (14 points in total).
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
unnown_train.csvandunnown_test_public.csv.- You submit
- Completed notebook functions and reported metrics.
- Scoring
- Classification accuracy and confusion matrix (clustering: NMI, homogeneity, completeness).
- Rules
- Make a copy of the notebook, share it with the organisers and report LLM chats and external resources used in the main test form.
- Format
- INAIO 2025 Stage 2, 2 March 2025, 10:00 AM – 1:00 PM IST (from the test form). Theory problems in a Google Form plus ML coding problems in Colab notebooks shared with the organisers.