Component-based Synthesis Research Articles

Specification-guided component-based synthesis from effectful libraries

Component-based synthesis seeks to build programs using the APIs provided by a set of libraries. Oftentimes, these APIs have effects, which make it challenging to reason about the correctness of potential synthesis candidates. This is because changes to global state made by effectful library procedures affect how they may be composed together, yielding an intractably large search space that can confound typical enumerative synthesis techniques. If the nature of these effects are exposed as part of their specification, however, deductive synthesis approaches can be used to help guide the search for components. In this paper, we present a new specification-guided synthesis procedure that uses Hoare-style pre- and post-conditions to express fine-grained effects of potential library component candidates to drive a bi-directional synthesis search strategy. The procedure alternates between a forward search process that seeks to build larger terms given an existing context but which is otherwise unaware of the actual goal, alongside a backward search mechanism that seeks terms consistent with the desired goal but which is otherwise unaware of the context from which these terms must be synthesized. To further improve efficiency and scalability, we integrate a conflict-driven learning procedure into the synthesis algorithm that provides a semantic characterization of previously encountered unsuccessful search paths that is used to prune the space of possible candidates as synthesis proceeds. We have implemented our ideas in a tool called and demonstrate its effectiveness on a number of challenging synthesis problems defined over OCaml libraries equipped with effectful specifications.

A synthetic antibiotic class overcoming bacterial multidrug resistance.

The dearth of new medicines effective against antibiotic-resistant bacteria presents a growing global public health concern1. For more than five decades, the search for new antibiotics has relied heavily on the chemical modification of natural products (semisynthesis), a method ill-equipped to combat rapidly evolving resistance threats. Semisynthetic modifications are typically of limited scope within polyfunctional antibiotics, usually increase molecular weight, and seldom permit modifications of the underlying scaffold. When properly designed, fully synthetic routes can easily address these shortcomings2. Here we report the structure-guided design and component-based synthesis of a rigid oxepanoproline scaffold which, when linked to the aminooctose residue of clindamycin, produces an antibiotic of exceptional potency and spectrum of activity, which we name iboxamycin. Iboxamycin is effective against ESKAPE pathogens including strains expressing Erm and Cfr ribosomal RNA methyltransferase enzymes, products of genes that confer resistance to all clinically relevant antibiotics targeting the large ribosomal subunit, namely macrolides, lincosamides, phenicols, oxazolidinones, pleuromutilins and streptogramins. X-ray crystallographic studies of iboxamycin in complex with the native bacterial ribosome, as well as with the Erm-methylated ribosome, uncover the structural basis for this enhanced activity, including a displacement of the {text{m}}_{2}^{6}text{A}2058 nucleotide upon antibiotic binding. Iboxamycin is orally bioavailable, safe and effective in treating both Gram-positive and Gram-negative bacterial infections in mice, attesting to the capacity for chemical synthesis to provide new antibiotics in an era of increasing resistance.

Multi-modal program inference: a marriage of pre-trained language models and component-based synthesis

Multi-modal program synthesis refers to the task of synthesizing programs (code) from their specification given in different forms, such as a combination of natural language and examples. Examples provide a precise but incomplete specification, and natural language provides an ambiguous but more "complete" task description. Machine-learned pre-trained models (PTMs) are adept at handling ambiguous natural language, but struggle with generating syntactically and semantically precise code. Program synthesis techniques can generate correct code, often even from incomplete but precise specifications, such as examples, but they are unable to work with the ambiguity of natural languages. We present an approach that combines PTMs with component-based synthesis (CBS): PTMs are used to generate candidates programs from the natural language description of the task, which are then used to guide the CBS procedure to find the program that matches the precise examples-based specification. We use our combination approach to instantiate multi-modal synthesis systems for two programming domains: the domain of regular expressions and the domain of CSS selectors. Our evaluation demonstrates the effectiveness of our domain-agnostic approach in comparison to a state-of-the-art specialized system, and the generality of our approach in providing multi-modal program synthesis from natural language and examples in different programming domains.

Automatic Building of a Repository for Component-based Synthesis of Warehouse Simulation Models

Simulations are a common tool in the warehouse planning and adoption process for evaluating and comparing variants of a storage system. But simulation modeling is a complex and time-consuming task. Due to limited resources, often not all possible system variants can be modeled. A promising solution is the migration of an existing simulation model to enable component-based software synthesis. An inhabitation algorithm composes structural variants according to a synthesis goal given a repository of typed components. In this paper, we automatically generate a repository and synthesize simulation model variants using a block stacking warehouse simulation model as an example.

ProSy: API-Based Synthesis with Probabilistic Model

Program synthesis is an exciting topic that desires to generate programs satisfying user intent automatically. But in most cases, only small programs for simple or domain-specific tasks can be synthesized. The major obstacle of synthesis lies in the huge search space. A common practice in addressing this problem is using a domain-specific language, while many approaches still wish to synthesize programs in general programming languages. With the rapid growth of reusable libraries, component-based synthesis provides a promising way, such as synthesizing Java programs which are only composed of APIs (application programming interfaces). However, the efficiency of searching for proper solutions for complex tasks is still a challenge. Given an unfamiliar programming task, programmers would search for API usage knowledge from various coding resources to reduce the search space. Considering this, we propose a novel approach named ProSy to synthesize API-based programs in Java. The key novelty is to retrieve related knowledge from Javadoc and Stack Overflow and then construct a probabilistic reachability graph. It assigns higher probabilities to APIs that are more likely to be used in implementing the given task. In the synthesis process, the program sketch with a higher probability will be considered first; thus, the number of explored reachable paths would be decreased. Some extension and optimization strategies are further studied in the paper. We implement our approach and conduct several experiments on it. We compare ProSy with SyPet and other state-of-the-art API-based synthesis approaches. The experimental results show that ProSy reduces the synthesis time of SyPet by up to 80%.

Program synthesis by type-guided abstraction refinement

We consider the problem of type-directed component-based synthesis where, given a set of (typed) components and a query type , the goal is to synthesize a term that inhabits the query. Classical approaches based on proof search in intuitionistic logics do not scale up to the standard libraries of modern languages, which span hundreds or thousands of components. Recent graph reachability based methods proposed for Java do scale, but only apply to monomorphic data and components: polymorphic data and components infinitely explode the size of the graph that must be searched, rendering synthesis intractable. We introduce type-guided abstraction refinement (TYGAR), a new approach for scalable type-directed synthesis over polymorphic datatypes and components. Our key insight is that we can overcome the explosion by building a graph over abstract types which represent a potentially unbounded set of concrete types. We show how to use graph reachability to search for candidate terms over abstract types, and introduce a new algorithm that uses proofs of untypeability of ill-typed candidates to iteratively refine the abstraction until a well-typed result is found. We have implemented TYGAR in H+, a tool that takes as input a set of Haskell libraries and a query type, and returns a Haskell term that uses functions from the provided libraries to implement the query type. Our support for polymorphism allows H+ to work with higher-order functions and type classes, and enables more precise queries due to parametricity. We have evaluated H+ on 44 queries using a set of popular Haskell libraries with a total of 291 components. H+ returns an interesting solution within the first five results for 32 out of 44 queries. Our results show that TYGAR allows H+ to rapidly return well-typed terms, with the median time to first solution of just 1.4 seconds. Moreover, we observe that gains from iterative refinement over exhaustive enumeration are more pronounced on harder queries.

FrAngel: component-based synthesis with control structures

In component-based program synthesis, the synthesizer generates a program given a library of components (functions). Existing component-based synthesizers have difficulty synthesizing loops and other control structures, and they often require formal specifications of the components, which can be expensive to generate. We present FrAngel, a new approach to component-based synthesis that can synthesize short Java functions with control structures when given a desired signature, a set of input-output examples, and a collection of libraries (without formal specifications). FrAngel aims to discover programs with many distinct behaviors by combining two main ideas. First, it mines code fragments from partially-successful programs that only pass some of the examples. These extracted fragments are often useful for synthesis due to a property that we call special-case similarity . Second, FrAngel uses angelic conditions as placeholders for control structure conditions and optimistically evaluates the resulting program sketches. Angelic conditions decompose the synthesis process: FrAngel first finds promising partial programs and later fills in their missing conditions. We demonstrate that FrAngel can synthesize a variety of interesting programs with combinations of control structures within seconds, significantly outperforming prior state-of-the-art.

Accelerating API-Based Program Synthesis via API Usage Pattern Mining

Program Synthesis is an exciting topic in software engineering which aims to generate programs satisfying user intent automatically. Although different approaches have been proposed in program synthesis, only small or domain-specific programs can be generated in practice, the main obstacle of which lies in the intractability of program space. With the rapid growth of reusable libraries, component-based synthesis provides a promising way, such as synthesizing Java programs that are only composed of APIs. However, the efficiency of searching for proper solutions for complex tasks is still a challenge. In certain scenarios, some API methods are frequently called together. The usage of these API methods always follows some usage patterns. Incorporating the information about API usage patterns will help to accelerate the speed of program synthesis. However, state-of-the-art synthesis tools do not capture the inherent relationships between API methods. Aiming at this problem, we propose a novel approach to accelerate the speed of API-based program synthesis via API usage pattern mining. It is a general approach that can be applied to any approach of API-based synthesis. We first collect open source projects of high quality from the Internet and use an off-the-shelf API-usage-pattern-mining tool to mine API usage patterns from these code snippets. We use two strategies to incorporate the information about API usage patterns with program synthesis, and either strategy can improve the efficiency of program synthesis. We evaluate our approach on 20 real programming tasks, which shows that our approach can accelerate the speed of program synthesis by 86% compared to the baseline.

Component-based synthesis of table consolidation and transformation tasks from examples

This paper presents a novel component-based synthesis algorithm that marries the power of type-directed search with lightweight SMT-based deduction and partial evaluation. Given a set of components together with their over-approximate first-order specifications, our method first generates a program sketch over a subset of the components and checks its feasibility using an SMT solver. Since a program sketch typically represents many concrete programs, the use of SMT-based deduction greatly increases the scalability of the algorithm. Once a feasible program sketch is found, our algorithm completes the sketch in a bottom-up fashion, using partial evaluation to further increase the power of deduction for rejecting partially-filled program sketches. We apply the proposed synthesis methodology for automating a large class of data preparation tasks that commonly arise in data science. We have evaluated our synthesis algorithm on dozens of data wrangling and consolidation tasks obtained from on-line forums, and we show that our approach can automatically solve a large class of problems encountered by R users.

Component-based synthesis for complex APIs

Component-based approaches to program synthesis assemble programs from a database of existing components, such as methods provided by an API. In this paper, we present a novel type-directed algorithm for component-based synthesis. The key novelty of our approach is the use of a compact Petri-net representation to model relationships between methods in an API. Given a target method signature S, our approach performs reachability analysis on the underlying Petri-net model to identify sequences of method calls that could be used to synthesize an implementation of S. The programs synthesized by our algorithm are guaranteed to type check and pass all test cases provided by the user. We have implemented this approach in a tool called SyPet, and used it to successfully synthesize real-world programming tasks extracted from on-line forums and existing code repositories. We also compare SyPet with two state-of-the-art synthesis tools, namely InSynth and CodeHint, and demonstrate that SyPet can synthesize more programs in less time. Finally, we compare our approach with an alternative solution based on hypergraphs and demonstrate its advantages.

Synthesis of loop-free programs

We consider the problem of synthesizing loop-free programs that implement a desired functionality using components from a given library. Specifications of the desired functionality and the library components are provided as logical relations between their respective input and output variables. The library components can be used at most once, and hence the library is required to contain a reasonable overapproximation of the multiset of the components required. We solve the above component-based synthesis problem using a constraint-based approach that involves first generating a synthesis constraint, and then solving the constraint. The synthesis constraint is a first-order ∃∀ logic formula whose size is quadratic in the number of components. We present a novel algorithm for solving such constraints. Our algorithm is based on counterexample guided iterative synthesis paradigm and uses off-the-shelf SMT solvers. We present experimental results that show that our tool Brahma can efficiently synthesize highly nontrivial 10-20 line loop-free bitvector programs. These programs represent a state space of approximately 20 10 programs, and are beyond the reach of the other tools based on sketching and superoptimization.

Understanding interleaved code

Complex programs often contain multiple, interwoven strands of computation, each responsible for accomplishing a distinct goal. The individual strands responsible for each goal are typically delocalized and overlap rather than being composed in a simple linear sequence. We refer to these code fragments as being interleaved. Interleaving may be intentional-for example, in optimizing a program, a programmer might use some intermediate result for several purposes-or it may creep into a program unintentionally, due to patches, quick fixes, or other hasty maintenance practices. To understand this phenomenon, we have looked at a variety of instances of interleaving in actual programs and have distilled characteristic features. This paper presents our characterization of interleaving and the implications it has for tools that detect certain classes of interleaving and extract the individual strands of computation. Our exploration of interleaving has been done in the context of a case study of a corpus of production mathematical software, written in Fortran from the Jet Propulsion Laboratory. This paper also describes our experiences in developing tools to detect specific classes of interleaving in this software, driven by the need to enhance a formal description of this software library's components. The description, in turn aids in the automated component-based synthesis of software using the library.