PROW: A Step Toward Automatic Program Writing

By Richard J. Waldinger, Richard C. T. Lee. 1969

Subfields: Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Code Generation & Program Synthesis

Citations in the corpus

CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X (2023, methodology): “…LISP-based pioneering deductive synthesis approaches [31, 37] to modern program synthesis systems [23, 30], to end-to-end code generation via deep neural networks [19, 32, 33], tremendous efforts have been made to enable machines to automatically write correct programs as part of the quest to…”
Deep learning in neural networks: An overview (2014, background): “1979: convolution + weight replication + subsampling (Neocognitron).....................................................................................................”
Optimal Ordered Problem Solver (2002, neutral): “Unlike logic-based program synthesizers (Green, 1969, Waldinger and Lee, 1969, Deville and Lau, 1994), program evolvers use biology-inspired concepts of Evolutionary Computation (Rechenberg, 1971, Schwefel, 1974) or Genetic Algorithms (Holland, 1975) to evolve better and better computer programs.”
Program Synthesis (2017, background): “provers, there was a lot of pioneering work on deductive synthesis approaches [41, 85, 144].”
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples (2018, background): “Automatic synthesis of programs that satisfy a given speciﬁcation is a classical problem in AI (Waldinger & Lee, 1969), with extensive literature in both machine learning and programming languages communities.”
IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis (2020, methodology): “Program synthesis is a classic task which has been studied since the early days of Artiﬁcial Intelligence (Waldinger and Lee, 1969; Manna and Waldinger, 1975).”
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis (2018, methodology): “The task of program synthesis is to automatically generate a program that is consistent with a speciﬁcation such as a set of input-output examples, and has been studied since the early days of Artiﬁcial Intelligence (Waldinger and Lee, 1969).”
Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models (2022, background): “specifications in the form of a predicate calculus [41].”
NAPS: Natural Program Synthesis Dataset (2018, background): “It is a problem that has been studied since the earliest days of artiﬁcial intelligence (Waldinger & Lee, 1969; Manna & Waldinger, 1975).”
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X (2023, methodology): “This is the problem of automatic program writing that has been explored since the early days of computer science in the 1960s (Waldinger and Lee, 1969; Summers, 1977).”
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation (2023, methodology): “program synthesis techniques have been developed, including deductive synthesis [18, 31, 53], programming by examples [19, 48] and neural-guided synthesis [25].”
Improving Neural Program Synthesis with Inferred Execution Traces (2018, background): “It is a problem that has been studied since the earliest days of artificial intelligence [Waldinger and Lee, 1969, Manna and Waldinger, 1975].”
Structural Language Models for Any-Code Generation (2019, background): “Program Generation Learning to generate programs is one of the oldest problems in machine learning (Waldinger and Lee, 1969) and has been considered by some as the “holy grail of computer science” (Pnueli and Rosner, 1989; Gulwani et al., 2017).”