Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper reviews and evaluates on 63 diverse datasets the performance of simple decision heuristics for the'comparison problem': choosing the better of two objects from multiple ordinal cues (attributes). To be informative, a cue has to be different when the objects have different values. Single-cue: Select the most informative cue from the training sample and discard the rest. Take-the-best: Use the most informative cue whose value differs on the two objects being compared.