The role of evaluation in AI and law: an examination of its different forms in the AI and law journal

摘要: This paper explores the presence and forms of evaluation in articles published journal Artificial Intelligence Law for ten-year period from 2005 through 2014. It represents a meta-level study some most significant works produced by AI community, this case nearly 140 research journal. also compares its findings to previous work conducted on appearing Proceedings International Conference (ICAIL). In addition, highlights harnessing performance as one their chief scientific tools means which they use it. extends argument why is essential formal reports such those As two earlier topic, it pursues answers questions: how good system, algorithm or proposal?, reliable approach technique?, and, ultimately, does method work? The investigates role reports, underscoring that performance-based 'ethic' signifies level maturity rigor within community. examines recent publications address same critical issue broader field Intelligence.