On the Time-Based Conclusion Stability of Software Defect Prediction Models. (arXiv:1911.06348v1 [cs.SE])

Researchers in empirical software engineering often make claims based on observable data such as defect reports. Unfortunately, in many cases, these claims are generalized beyond the data sets that have been evaluated. Will the researcher’s conclusions hold a year from now for the same software projects? Perhaps not. Recent studies show that in the area…

Question-Conditioned Counterfactual Image Generation for VQA. (arXiv:1911.06352v1 [cs.CV])

While Visual Question Answering (VQA) models continue to push the state-of-the-art forward, they largely remain black-boxes – failing to provide insight into how or why an answer is generated. In this ongoing work, we propose addressing this shortcoming by learning to generate counterfactual images for a VQA model – i.e. given a question-image pair, we…

Capturing the Production of the Innovative Ideas: An Online Social Network Experiment and “Idea Geography” Visualization. (arXiv:1911.06353v1 [cs.SI])

Collective design and innovation are crucial in organizations. To investigate how the collective design and innovation processes would be affected by the diversity of knowledge and background of collective individual members, we conducted three collaborative design task experiments which involved nearly 300 participants who worked together anonymously in a social network structure using a custom-made…

Language Inclusion for Finite Prime Event Structures. (arXiv:1911.06355v1 [cs.FL])

We study the problem of language inclusion between finite, labeled prime event structures. Prime event structures are a formalism to compactly represent concurrent behavior of discrete systems. A labeled prime event structure induces a language of sequences of labels produced by the represented system. We study the problem of deciding inclusion and membership for languages…

Predicting Drug-Drug Interactions from Molecular Structure Images. (arXiv:1911.06356v1 [cs.LG])

Predicting and discovering drug-drug interactions (DDIs) is an important problem and has been studied extensively both from medical and machine learning point of view. Almost all of the machine learning approaches have focused on text data or textual representation of the structural data of drugs. We present the first work that uses drug structure images…

Give me (un)certainty — An exploration of parameters that affect segmentation uncertainty. (arXiv:1911.06357v1 [eess.IV])

Segmentation tasks in medical imaging are inherently ambiguous: the boundary of a target structure is oftentimes unclear due to image quality and biological factors. As such, predicted segmentations from deep learning algorithms are inherently ambiguous. Additionally, “ground truth” segmentations performed by human annotators are in fact weak labels that further increase the uncertainty of outputs…

Adjusted Parallel Transport for Higher Gauge Theories. (arXiv:1911.06390v1 [hep-th])

Many physical theories, including notably string theory, require non-abelian higher gauge fields defining higher holonomy. Previous approaches to such higher connections on categorified principal bundles require these to be fake flat. This condition, however, renders them locally gauge equivalent to connections on abelian gerbes. For particular higher gauge groups, for example 2-group models of the…

Construction of a blow-up solution for a perturbed nonlinear heat equation with a gradient term. (arXiv:1911.06392v1 [math.AP])

We consider in this paper a perturbation of the standard semilinear heat equation by a term involving the space derivative and a non-local term. We prove the existence of a blow-up solution, and give its blow-up profile. Our method relies on the two-step method: we first linearize the equation (in similarity variables) around the expected…

Strongly uncontrollable network topologies. (arXiv:1911.06398v1 [math.OC])

In this paper, we present a class of network topologies under which the Laplacian consensus dynamics exhibits undesirable controllability properties under a broadcast control signal. Specifically, the networks we characterize are uncontrollable for any subset of the nodes chosen as control inputs and that emit a common control signal. We provide a sufficient condition for…