Update README.md

README.md

@@ -109,16 +109,6 @@ Contains the computed evaluation metric scores for each model-language combinati
 
 ***
 
-## Notes
-
-- Checkpoints were **reused** from the original authors' repositories; no retraining was performed for MCMD-NT.
-- No random seeds or repeated runs were documented in the original experiment.
-- Results in this repository correspond to the **reproduction attempt** of the original reported values.
-- MCMD-NT shares the same five languages as MCMD but contains newer commits, enabling a temporal generalization assessment.
-- Discrepancies between reproduced and reported results are documented in the thesis.
-
-***
-
 ## References
 
 - Wu et al. (2025). *An Empirical Study on Commit Message Generation with Large Language Models via In-Context Learning.* arXiv:2502.18904.