Algorithmic Exam Generation

Authors: Omer Geiger, Shaul Markovitch

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section we present an empirical evaluation of the complete MOEG framework over a procedural domain.
Researcher Affiliation Academia Department of Computer Science Technion Israel Institue of Technology, 32000 Haifa, Israel
Pseudocode Yes Figure 1: Pseudo-code for action landmark approximation method
Open Source Code No The paper does not provide any statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets No For this algebraic domain we devised a question generating algorithm. ... A set of 160 questions used for evaluation, Q, was produced by applying the described procedure 10 times with each (w, d) value pair in {0, 1, 2, 3}2. The paper does not provide concrete access information for this dataset.
Dataset Splits Yes We use an oracle sample for evaluation. Two things are important with regard to this oracle sample: first, it is taken independently from the utility sample, and second, it is considerably larger. ... Default values, used unless stated otherwise, are sample Size = 400, ... A sample of size 1000 was used for the oracle.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments.
Software Dependencies No The paper does not provide specific software dependencies or version numbers.
Experiment Setup Yes Default values, used unless stated otherwise, are sample Size = 400, ke = 10, ϵp = 0.15, ϵw = 0.5. A sample of size 1000 was used for the oracle. ... parameters: Dlim = 40, SOLlim = 100, Tlim = 300 sec.