When dealing with incomplete data in statistical learning, or incomplete observations in probabilistic inference, one needs to distinguish the fact that a certain event is observed from the fact that the observed event has happened. Since the modeling and computational complexities entailed by maintaining this proper distinction are often prohibitive, one asks for conditions under which it can be safely ignored. Such conditions are given by the missing at random (mar) and coarsened at random (car) assumptions. In this paper we provide an in-depth analysis of several questions relating to mar/car assumptions. Main purpose of our study is to provide criteria by which one may evaluate whether a car assumption is reasonable for a particular data collecting or observational process. This question is complicated by the fact that several distinct versions of mar/car assumptions exist. We therefore first provide an overview over these different versions, in which we highlight the distinction between distributional and coarsening variable induced versions. We show that distributional versions are less restrictive and sufficient for most applications. We then address from two different perspectives the question of when the mar/car assumption is warranted. First we provide a ''static'' analysis that characterizes the admissibility of the car assumption in terms of the support structure of the joint probability distribution of complete data and incomplete observations. Here we obtain an equivalence characterization that improves and extends a recent result by Grunwald and Halpern. We then turn to a ''procedural'' analysis that characterizes the admissibility of the car assumption in terms of procedural models for the actual data (or observation) generating process. The main result of this analysis is that the stronger coarsened completely at random (ccar) condition is arguably the most reasonable assumption, as it alone corresponds to data coarsening procedures that satisfy a natural robustness property.

The 2004 International Planning Competition, IPC-4, included a probabilistic planning track for the first time. We describe the new domain specification language we created for the track, our evaluation methodology, the competition domains we developed, and the results of the participating teams.

Artificial Intelligence: The Next Twenty-Five Years

Artificial Intelligence: The Next Twenty-Five Years Abstract Through this collection of programmatic statements from key figures in the field, we chart the progress of AI and survey current and future directions for AI research and the AI community. Through this collection of programmatic statements from key figures in the field, we chart the progress of AI and survey current and future directions for AI research and the AI community.

In this first message to the members of AAAI, AAAI President Allen Newell answers the questions "what are we?" "why did we come into existence?" "how will AAAI conduct itself?" and ends with a few thoughts on the name "artificial intelligence."

The Twentieth National Conference on Artificial Intelligence was held July 9-13, 2005, in Pittsburgh, Pennsylvania. The conference, which marked the twenty-fifth anniversary of the Association for the Advancement of Artificial Intelligence (AAAI), received 803 submissions to the technical program. All papers were double-blind reviewed, and 150 papers were accepted for oral presentation, while 79 papers were accepted for poster presentation. The keynote address was delivered by Marvin Minsky.

The AAAI-05 workshops were held on Saturday and Sunday, July 9-10, in Pittsburgh, Pennsylvania. The thirteen workshops were Contexts and Ontologies: Theory, Practice and Applications, Educational Data Mining, Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing, Human Comprehensible Machine Learning, Inference for Textual Question Answering, Integrating Planning into Scheduling, Learning in Computer Vision, Link Analysis, Mobile Robot Workshop, Modular Construction of Humanlike Intelligence, Multiagent Learning, Question Answering in Restricted Domains, and Spoken Language Understanding.

In 1983, I gave the AAAI president's address titled "Artificial Intelligence Prepares for 2001." An article, based on that talk, was published soon after in "AI Magazine. In this article, I retract or modify some of the points made in that piece and reaffirm others. Specifically, I now acknowledge the many important facets of AI research beyond high-level reasoning but maintain my view about the importance of integrated AI systems, such as mobile robots.

The emerging Semantic Web focuses on bringing knowledge representationlike capabilities to Web applications in a Web-friendly way. The ability to put knowledge on the Web, share it, and reuse it through standard Web mechanisms provides new and interesting challenges to artificial intelligence. In this paper, I explore the similarities and differences between the Semantic Web and traditional AI knowledge representation systems, and see if I can validate the analogy "The Semantic Web is to KR as the Web is to hypertext."

This article provides a historical background on how AAAI came into existence. It provides a rationale for why we needed our own society. This article provides a brief description of the considerations that went into making the final choices. It also provides a description of the historic first AAAI conference and the people that made it happen.