The AI Telco Troubleshooting Challenge by ITU
€35 000 EUR
Completed (7 months ago)
Root Cause Analysis
Fault Detection
Edge AI
Anomaly Detection
Large Language Models
1321 joined
251 active
Start
28 Nov 25
Close
01 Feb 26
Reveal
02 Feb 26
'/%3e%3c/defs%3e%3cpath fill='%23012169' d='M0 0h10080v5040H0z'/%3e%3cpath stroke='%23fff' stroke-width='.6' d='m0 0 6 3m0-3L0 3' clip-path='url(%23b)' transform='scale(840)'/%3e%3cpath stroke='%23e4002b' stroke-width='.4' d='m0 0 6 3m0-3L0 3' clip-path='url(%23c)' transform='scale(840)'/%3e%3cpath stroke='%23fff' stroke-width='840' d='M2520 0v2520M0 1260h5040'/%3e%3cpath stroke='%23e4002b' stroke-width='504' d='M2520 0v2520M0 1260h5040'/%3e%3cg fill='%23fff'%3e%3cuse xlink:href='%23d' x='2520' y='3780'/%3e%3cuse xlink:href='%23a' x='7560' y='4200'/%3e%3cuse xlink:href='%23a' x='6300' y='2205'/%3e%3cuse xlink:href='%23a' x='7560' y='840'/%3e%3cuse xlink:href='%23a' x='8680' y='1869'/%3e%3cuse xlink:href='%23e' x='8064' y='2730'/%3e%3c/g%3e%3c/svg%3e)
Evaluation Fairness
Help · 31 Jan 2026, 13:02 · 3
It seems that some participants are fine-tuning on the test set. How do the organizers plan to detect models trained on the test data? If unseen data will be used for local evaluation, will it follow the same format/structure in train/phase1/phase2?
We do know that. Some participants are worried about it because of a single large score. However, it looks like that participant did not fine tune on the test set. We will try to check and provide a fair eval.
got it, thanks!
yes it is too important