The paper shows how a question-answering system can use first-order logic as its language and an automatic theorem prover, based upon the resolution inference principle, as its deductive mechanism. The resolution proof procedure is extended to a constructive proof procedure. An answer construction algorithm is given whereby the system is able not only to produce yes or no answers but also to find or construct an object satisfying a specified condition. A working computer program, QA3, based on these ideas, is described. Methods are presented for solving state transformation problems. In addition to question-answering, the program can do automatic programming, control and problem solving for a simple robot, pattern recognition, and puzzles. (Author).

Automated Theorem Proving: A Logical Basis

Automated reasoning programs are successfully tackling challenging problems in mathematics and logic, program verification, and circuit design. This two-volume book includes all the published papers of Dr Larry Wos, one of the world's pioneers in automated reasoning. It provides a wealth of information for students, teachers, researchers, and even historians of computer science about this rapidly growing field.The book has the following special features:(1) It presents the strategies introduced by Wos which have made automated reasoning a practical tool for solving challenging puzzles and deep problems in mathematics and logic;(2) It provides a history of the field — from its earliest stages as mechanical theorem proving to its broad base now as automated reasoning;(3) It illustrates some of the remarkable successes automated reasoning programs have had in tackling challenging problems in mathematics, logic, program verification, and circuit design;(4) It includes a CD-ROM, with a searchable index of all the papers, enabling readers to peruse the papers easily for ideas.

Pattern-Directed Inference Systems provides a description of the design and implementation of pattern-directed inference systems (PDIS) for various applications. The book also addresses the theoretical significance of PDIS for artificial intelligence and cognitive psychology. The book is divided into eight sections. The introduction provides a brief overview of pattern-directed inference systems, including a historical perspective, a review of basic concepts, and a survey of work in this area. Subsequent chapters address topics on architecture and design, methods for accessing and controlling rule based systems, methods for obtaining adaptive behavior via rule-based systems and cognitive modeling. Constructing models of human information processing, natural language understanding and multilevel systems and complexity are described as well. The last section discusses the earlier chapters in the book and provides a unifying set of principles for the PDIS formalism. Computer scientists, psychologists, engineers, and researchers in artificial intelligence will find the book very informative.

"Kind of crude, but it works, boy, it works!" AZan NeweZZ to Herb Simon, Christmas 1955 In 1954 a computer program produced what appears to be the first computer generated mathematical proof: Written by M. Davis at the Institute of Advanced Studies, USA, it proved a number theoretic theorem in Presburger Arithmetic. Christmas 1955 heralded a computer program which generated the first proofs of some propositions of Principia Mathematica, developed by A. Newell, J. Shaw, and H. Simon at RAND Corporation, USA. In Sweden, H. Prawitz, D. Prawitz, and N. Voghera produced the first general program for the full first order predicate calculus to prove mathematical theorems; their computer proofs were obtained around 1957 and 1958, about the same time that H. Gelernter finished a computer program to prove simple high school geometry theorems. Since the field of computational logic (or automated theorem proving) is emerging from the ivory tower of academic research into real world applications, asserting also a definite place in many university curricula, we feel the time has corne to examine and evaluate its history. The article by Martin Davis in the first of this series of volumes traces the most influential ideas back to the 'prehistory' of early logical thought showing how these ideas influenced the underlying concepts of most early automatic theorem proving programs.