Scoring System Issues Identified in Model Evaluation

The team highlighted inconsistencies in the subnet's scoring system, where models with low validation loss were excluded from scoring and promotion. An internal dashboard was referenced to cross-verify metrics, and concerns were raised about models being locked out of scoring after poor initial performance.

• •UID 222 remained in Group A despite no scores for 5-8 cycles
• •Models with lower val_loss were excluded from scoring
• •Internal dashboard https://dashboard-dev.connito.ai/ used for metric verification
• •Risk of models being permanently demoted after early poor performance