21 papers · ranked by Valyu relevance
Cristina David, Daniel Kroening
Program synthesis is the mechanized construction of software, dubbed ‘self-writing code’. Synthesis tools relieve the programmer from thinking about how the problem is to be solved; instead, the programmer only provides a description of what is to be achieved. Given a specification of what the program should do, the…
Jose Guadalupe Hernandez, Anil Kumar Saini, Gabriel Ketron, Jason H. Moore
Genetic programming (GP) and large language models (LLMs) differ in how program specifications are provided: GP uses input-output examples, and LLMs use text descriptions. In this work, we compared the ability of PushGP and GPT-4o to synthesize computer programs for tasks from the PSB2 benchmark suite. We used three…
Hal Finkel, Ignacio Laguna
Program synthesis represents a wide array of machine programming techniques that can greatly enhance programmer productivity and software quality characteristics, such as program correctness, performance, and security. Specifically, program synthesis incorporates techniques whereby the following may occur: - The…
Kiara Grouwstra
In this thesis we look into programming by example (PBE), which is about finding a program mapping given inputs to given outputs. PBE has traditionally seen a split between formal versus neural approaches, where formal approaches typically involve deductive techniques such as SAT solvers and types, while the neural…
Shuvendu K. Lahiri, Chao Wang, Paul Krogmeier, Umang Mathur + 3 more
'Adithya Murali' 'P. Madhusudan' 'Mahesh Viswanathan'] We identify a decidable synthesis problem for a class of programs of unbounded size with conditionals and iteration that work over infinite data domains. The programs in our class use uninterpreted functions and relations, and abide by a restriction called…
Shuvendu K. Lahiri, Chao Wang, Yanju Chen, Chenglong Wang + 3 more
'Osbert Bastani' 'Isil Dillig' 'Yu Feng'] In this paper, we present a new program synthesis algorithm based on reinforcement learning. Given an initial policy (i.e. statistical model) trained off-line, our method uses this policy to guide its search and gradually improves it by leveraging feedback obtained from a…
Alessandro Abate, Haniel Barbosa, Clark Barrett, Cristina David + 5 more
'Pascal Kesseli' 'Daniel Kroening' 'Elizabeth Polgreen' 'Andrew Reynolds' 'Cesare Tinelli'] Program synthesis is the mechanised construction of software. One of the main difficulties is the efficient exploration of the very large solution space, and tools often require a user-provided syntactic restriction of the…
Shantanu Mandal, Todd A. Anderson, Javier S. Turek, Justin Gottschlich + 1 more
'Justin Gottschlich' 'Abdullah Muzahid'] Automatic software generation based on some specification is known as program synthesis. Most existing approaches formulate program synthesis as a search problem with discrete parameters. In this paper, we present a novel formulation of program synthesis as a continuous…
Margarida Ferreira, Victor Nicolet, Joey Dodds, Daniel Kroening
We present the first technique to synthesize programs that compose side-effecting functions, pure functions, and control flow, from partial traces containing records of only the side-effecting functions. This technique can be applied to synthesize API composing scripts from logs of calls made to those APIs, or a script…
John Feser, Işıl Dillig, Armando Solar-Lezama
We present a new domain-agnostic synthesis technique for generating programs from input-output examples. Our method, called metric program synthesis, relaxes the well-known observational equivalence idea (used widely in bottom-up enumerative synthesis) into a weaker notion of observational similarity, with the goal of…
Pablo Samuel Castro, Nenad Tomasev, Ankit Anand, Navodita Sharma + 13 more
Symbolic models play a key role in cognitive science, expressing computationally precise hypotheses about how the brain implements a cognitive process. Identifying an appropriate model typically requires a great deal of effort and ingenuity on the part of a human scientist. Here, we adapt FunSearch 39, a recently…
George Chao, Evan Appleton, Clair S. Gutierrez, Lilia Evgeniou + 4 more
Pluripotent cells specialize into numerous cell types by receiving external signals, making fate decisions, and executing differentiation functions – a paradigm similar to computer algorithms. While advances in biosensor design have enabled cells to respond to diverse stimuli, the ability to maintain a synthetic memory…
Brian Hie, Salvatore Candido, Zeming Lin, Ori Kabeli + 4 more
Combining a basic set of building blocks into more complex forms is a universal design principle. Most protein designs have proceeded from a manual bottom-up approach using parts created by nature, but top-down design of proteins is fundamentally hard due to biological complexity. We demonstrate how the modularity and…
Pieter Floris Jacobs, Robert Pollice
Scientists across domains are often challenged to master domain-specific languages (DSLs) for their research, which are merely a means to an end but are pervasive in fields like computational chemistry. Automated code generation promises to overcome this barrier, allowing researchers to focus on their core expertise.…
Authors not listed
Computer-aided synthesis planning aims to identify viable synthetic routes from a target compound to readily available building blocks by iteratively decomposing molecules into smaller precursors. Self-play search algorithms, trained with simulated experience, reach state-of-the-art performance. However, these methods…
Authors not listed
Identifying synthesis routes from knowledge graphs poses challenges beyond retrosynthesis, including path–finding artifacts and data issues. We introduce “SynGPS”, a novel algorithm that overcomes these limitations by identifying viable routes even with common artifacts. SynGPS can resolve nonsensical cycles…
Kathleen S. Dreyer, Anh V. Nguyen, Gauri G. Bora, Lauren E. Redus + 6 more
Genetic programs can direct living systems to perform diverse, pre-specified functions. As the library of parts available for building such programs continues to expand, computation-guided design is increasingly helpful and necessary. Predictive models aid the challenging design process, but iterative simulation and…
Authors not listed
Computer-Assisted Synthesis Programs are increasingly employed by organic chemists. Often, these tools combine neural networks for policy prediction with heuristic search algorithms. We propose two novel enhancements, which we call eUCT and dUCT, to the Monte Carlo tree search (MCTS) algorithm. The enhancements were…
Authors not listed
Automated chemistry platforms hold the potential to enable large-scale organic synthesis campaigns, such as producing a library of compounds for biological evaluation. The efficiency of such platforms will depend on the schedule according to which the synthesis operations are executed. In this work, we study the…
Miha Moškon, Žiga Pušnik, Lidija Magdevska, Nikolaj Zimic + 1 more
Basic synthetic information processing structures, such as logic gates, oscillators and flip-flops, have already been implemented in living organisms. Current implementations of these structures are, however, hardly scalable and are yet to be extended to more complex processing structures that would constitute a…
Rafal Madaj, Akhil Sanker, Ben Geoffrey A S, Host Antony David + 4 more
We report a novel python based programmatic tool that automates the dry lab drug discovery workflow for Hepatitis C virus. Firstly, the python program is written to automate the process of data mining PubChem database to collect data required to perform a machine learning based AutoQSAR algorithm through which drug…