About this Model
CPS-AI (Luchini et al., 2025) is a neural network that is finetuned to score responses from the Creative Problem Solving task.
CPS-AI currently only supports English items and responses, but the model should perform well on responses that have been translated to English via Google Translate.
How do I use CPS-AI?
To have your responses scored, upload a CSV that has a column named 'item' containing the full text of the problem, and another column named 'response', which has the participant's response to the creative problem solving item. The algorithm is case sensitive for the item/response column names, but it does not matter if other columns are present in the input CSV.
The algorithm will add three new columns to your CSV: one named 'prediction' which reflects the model's originality score, another named 'effectiveness_prediction' which reflects the model's assessment of the quality of the solution, and a column named 'modelname', which denotes the model providing the score.
Responses are scored on a -2 to 2 scale, where higher scores reflect more original and effective responses. For more information on how the model was trained and its performance, check out the paper.
