Skip to Main Content
Table 4: 
Ablation testing on comparative questions: Top beam’s F1 score obtained by omitting each of the above features from CIPITR, originally having F1 of 15.123%.
FeatureF1 (%)
Action Repetition 1.68 
Phase Change 2.41 
Valid Variable Instantiation 3.08 
Biasing last operator 7.52 
Auxiliary Reward 9.85 
Beam Pruning 10.34 
FeatureF1 (%)
Action Repetition 1.68 
Phase Change 2.41 
Valid Variable Instantiation 3.08 
Biasing last operator 7.52 
Auxiliary Reward 9.85 
Beam Pruning 10.34 
Close Modal

or Create an Account

Close Modal
Close Modal