Multiarrangement: A Plug & Play Geometric Data Collection Package For Video Stimuli

We present Multiarrangement, an offline, open-source Python toolkit for collecting human similarity judgments for video stimuli through multi-arrangement tasks. Participants arrange subsets of stimuli in a 2D arena such that Euclidean distances reflect perceived dissimilarity. The toolkit supports two experimental paradigms: a set-cover scheduling system that uses combinatorial covering designs, aiming to avoid overwhelming the participant for stimulus-rich settings, and an adaptive Lift-the-Weakest scheduler that focuses each new trial on the globally least certain pair and informative neighbors. Across trials, partial distance evidence is fused into a representational dissimilarity matrix. Further refinement is also available with optional reliability-like weighting and inverse MDS which can reduce cross-trial prediction error. We document task design, algorithms, a small within-subject validation, and provide practical guidance for reliable use.