Large language models (LLMs) have demonstrated an impressive ability to generate code for various programming tasks. In many instances, LLMs can generate a correct program for a task when given numerous trials. Consequently, a recent trend is to do large scale sampling of programs using a model and then filtering/ranking the programs based on the program execution on a small number of known unit tests to select one candidate solution. However, these approaches assume that the unit tests are given and assume the ability to safely execute the generated programs (which can do arbitrary dangerous operations such as file manipulations). Both of the above assumptions are impractical in real-world software development. In this paper, we propose CodeRanker, a neural ranker that can predict the correctness of a sampled program without executing it. Our CodeRanker is fault-aware i.e., it is trained to predict different kinds of execution information such as predicting the exact compile/runtime error type (e.g., an IndexError or a TypeError). We show that CodeRanker can significantly increase the pass@1 accuracy of various code generation models (including Codex, GPT-Neo, GPT-J) on APPS, HumanEval and MBPP datasets.

In this work a new perspective of the control of a sucker-rod pumping system is presented. In despite of the widely application of control strategies based on dynamometer cards recognition they present several limitations in the control and maintenance aspects. Nowadays, with the development of a new class of low cost downhole sensors, new control strategies could bee applied. In this work, a control framework using the bottom hole pressure combined with a variable speed drive (VSD) structure is proposed. A hardware in the loop simulation platform was developed to evaluate the measure of the bottom hole pressure contribution in a sucker-rod pumping control system.