Programming with a read-eval-synth loop

Peleg, Hila; Gabay, Roi; Itzhaky, Shachar; Yahav, Eran

doi:10.1145/3428227

Cited by 11 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, many new interaction models [14,16,21,25,41] are proposed make PBE and PBD tools easier-to-use. As our paper focuses on the synthesis specification and algorithm design, its interaction model is basic.…”

Section: Related Workmentioning

confidence: 99%

Synthesizing Analytical SQL Queries from Computation Demonstration

Zhou,

Bodik,

Cheung

et al. 2022

Preprint

View full text Add to dashboard Cite

Analytical SQL is widely used in modern database applications and data analysis. However, its partitioning and grouping operators are challenging for novice users. Unfortunately, programming by example, shown effective on standard SQL, are less attractive because examples for analytical queries are more laborious to solve by hand.To make demonstrations easier to create, we designed a new end-user specification, programming by computation demonstration, that allows the user to demonstrate the task using a (possibly incomplete) cell-level computation trace. This specification is exploited in a new abstraction-based synthesis algorithm to prove that a partially formed query cannot be completed to satisfy the specification, allowing us to prune the search space.We implemented our approach in a tool named Sickle and tested it on 80 real-world analytical SQL tasks. Results show that even from small demonstrations, Sickle can solve 76 tasks, in 12.8 seconds on average, while the prior approaches can solve only 60 tasks and are on average 22.5× slower. Our user study with 13 participants reveals that our specification increases user efficiency and confidence on challenging tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Synthesizing Analytical SQL Queries from Computation Demonstration

Zhou,

Bodik,

Cheung

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Smith and Albarghouthi [12] describe how synthesis procedures can be adapted to only consider programs in normal form. MagicHaskeller [6] and RESL [11] filter out programs that evaluate to the same result. Instead of only using input-output examples for the verification of generated programs, Myth [4,10], Smyth [8], and λ 2 [3] use input-output examples during pruning, by eagerly checking incomplete programs for counterexamples using constraint propagation.…”

Section: Introductionmentioning

confidence: 99%

Program Synthesis Using Example Propagation

Niek¹,

Jeuring²,

Heeren³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We present Scrybe, an example-based synthesis tool for a statically-typed functional programming language, which combines topdown deductive reasoning in the style of λ 2 with Smyth-style live bidirectional evaluation. During synthesis, example constraints are propagated through sketches to prune and guide the search. This enables Scrybe to make more effective use of functions provided in the context. To evaluate our tool, it is run on the combined, largely disjoint, benchmarks of λ 2 and Myth. Scrybe is able to synthesize most of the combined benchmark tasks.

show abstract

“…to sort, filter, or interact with the components just described. While interaction with suggestions is often simply selection from a menu, more involved interaction models include active code completion via palettes [33], interactive example augmentation [22], and work on the Read-Eval-Synthesize-Loop [34], which presents a Read-Eval-Print-Loop-inspired interaction model for driving human-in-the-loop synthesis.…”

Section: Introductionmentioning

confidence: 99%

An Integrative Human-Centered Architecture for Interactive Programming Assistants

Blinn

Moon

Griffis

et al. 2022

2022 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)

View full text Add to dashboard Cite

Programming has become a collaboration between human programmers, who drive intent, and interactive assistants that suggest contextually relevant editor actions. There has been considerable work on suggestion synthesis strategies-from semantic autocomplete to modern program synthesis, repair, and machine learning research. This diversity of contextually viable strategies creates a need for an integrative, human-centered perspective on the problem of programming assistant design that (1) confronts the problem of integrating a variety of synthesis strategies, fed by shared semantic analyses capable of operating on program sketches, and (2) centers the needs of the human programmer: comprehending, comparing, ranking, and filtering suggestions generated by various synthesizers, and in some cases participating in a synthesizer's search by supplying additional expressions of intent. This paper contributes a conceptual architecture and API to guide programming assistant designers as they confront these integration and human-centered design challenges. We then instantiate this architecture with two prototype end-toend assistant designs, both developed for the Hazel programming environment, that emphasize understudied design aspects, namely continuity, explainability, human-in-the-loop synthesis, and the integration of multiple analyses with multiple synthesis strategies.

show abstract

Programming with a read-eval-synth loop

Cited by 11 publications

References 61 publications

Synthesizing Analytical SQL Queries from Computation Demonstration

Synthesizing Analytical SQL Queries from Computation Demonstration

Program Synthesis Using Example Propagation

An Integrative Human-Centered Architecture for Interactive Programming Assistants

Contact Info

Product

Resources

About