A Methodology for LISP Program Construction from Examples

By P. D. Summers. 1977

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): “This problem has been explored since the early days of computer science in the 1960s [31, 37].”
Neural Architecture Search with Reinforcement Learning (2016, methodology): “Neural Architecture Search has some parallels to program synthesis and inductive programming, the idea of searching a program from examples (Summers, 1977; Biermann, 1978).”
Continual and Multi-Task Architecture Search (2019, methodology): “NAS shares some similarity to program synthesis and inductive programming (Summers, 1986; Biermann, 1978), and it has been successfully applied to some simple Q&A tasks (Liang et al., 2010; Neelakantan et al., 2015; Andreas et al., 2016; Lake et al., 2015).”
Neuro-Symbolic Program Synthesis (2016, background): “Program Synthesis, the problem of automatically constructing programs that are consistent with a given speciﬁcation, has long been a subject of research in Computer Science (Biermann, 1978; Summers, 1977).”
Neural Program Synthesis with Priority Queue Training (2018, methodology): “Our method shares the same goal with traditional techniques in program synthesis and inductive programming (Summers, 1977; Biermann, 1978; Muggleton & de Raedt, 1994; Angulin, 1987).”
Syntax-guided synthesis (2013, background): “On the other hand, inductive synthesis [20,21,22] seeks to find a program matching a set of input-output examples.”
Inductive Synthesis of Functional Programs: An Explanation Based Generalization Approach (2006, methodology): “Similar to Summers (1977), the set of functions used in our term construction approach implies the restriction of induced programs to solve structural list programs.”
AOGNets: Compositional Grammatical Architectures for Deep Learning (2017, methodology): “Probabilistic program induction [54, 32, 33] has been used successfully in many settings, but has not shown good performance in difﬁcult visual understanding tasks such as large-scale image classiﬁcation and object detection.”
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis (2018, methodology): “As formal speciﬁcation is often as complex as writing the original program, many techniques were developed to achieve the same goal with simpler partial speciﬁcations in the form of input-output (IO) examples (Amarel, 1970; Summers, 1977).”
Neural Guided Constraint Logic Programming for Program Synthesis (2018, background): “Programming by example (PBE) problems have a long history dating to the 1970’s [14, 15].”
An Empirical Study of the Non-Determinism of ChatGPT in Code Generation (2023, methodology): “While the inductive synthesis approach was based on inductive specifications such as input/output pairs and examples etc, such as works on Lisp programs [8, 56, 58], Pygmalion [57] and more recently FlashFill [20].”
AOGNets: Deep AND-OR Grammar Networks for Visual Recognition (2017, methodology): “Probabilistic program induction [35, 23, 24] has been used successfully in many settings, but has not shown good performance in difficult visual understanding tasks such as large-scale image classification and object detection.”
The Inference of Regular LISP Programs from Examples (1978, background): “[12], Siklassy and Sykes [13], and Summers [14], [15].”
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (2022, methodology): “Earlier tasks include problem specifications in the form of input-output (IO) examples [Summers, 1977, Gulwani et al., 2012] and synthesis methods are limited to probabilistic approaches [Liang et al., 2010] or simple programming concepts [Joulin and Mikolov, 2015, Kurach et al., 2015].”
Inductive Programming: A Survey of Program Synthesis Techniques (2009, methodology): “1 Theorem 1 ([4]).”
Learning to Represent Programs with Property Signatures (2020, background): “Program synthesis is a longstanding goal of computer science research (Manna & Waldinger, 1971; Waldinger et al., 1969; Summers, 1977; Shaw; Pnueli & Rosner, 1989; Manna & Waldinger, 1975), arguably dating to the 1940s and 50s (Copeland, 2012; Backus et al., 1957).”