arXiv subjects

Shraddha Surana

Publications and source records attributed to Shraddha Surana.

5 recordsLinked to original sources

arXiv2026

Identifying Latent Declarative Representations of Code for Assisting Repository Migration

Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a program as the implementation of an unobserved, declarative description of its computation and investigate whether making this latent declarative representation explicit improves repository-scale porting. ADFD-Migrate approximates the latent representation with an annotated data-flow diagram (ADFD) of processes, data stores, external entities, flows, and behavioral contracts. An LLM infers the source ADFD from bounded repository context, guided by static-analysis coverage checks. Dependency-aware chunking orders bounded process groups for target-language generation. Differences between the source ADFD and a statically recovered target ADFD then guide regeneration. We evaluate ADFD-Migrate on f2x50, a new benchmark of 50~Fortran repositories spanning 1.5k--1.6M lines of code and three complexity tiers, and assess the resulting ports along two dimensions: porting soundness, measured by source-oracle behavioral agreement, and porting completeness, measured by a composite migration outcome index. Against 382 curated Fortran-oracle probes, the generated Python passes 327 (85.6\%), with 40 repositories passing every attempted probe. ADFD-Migrate exposes all 382 planned behaviors as runnable targets, compared with 99 and 98 for direct and repository-context translation and 69 and 30 for the static-profile and dependency-chunking ablations. It also achieves a 93.1\% mean migration outcome index and a 17--59 percentage-point outcome-index advantage over direct translation on 47 repositories. These results suggest that an inspectable semantic bottleneck can improve the coverage and integration of repository-scale migration while enabling lower-cost generation for many repositories.

cs.SE↗

arXiv2026

Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming

Engineering information systems for scientific data analysis presents significant challenges: complex workflows requiring exploration of large solution spaces, close collaboration with domain specialists, and the need for maintainable, interpretable implementations. Traditional manual development is time-consuming, while "No Code" approaches using large language models (LLMs) often produce unreliable systems. We present iProg, a tool implementing Interactive Structured Inductive Programming. iProg employs a variant of a '2-way Intelligibility' communication protocol to constrain collaborative system construction by a human and an LLM. Specifically, given a natural-language description of the overall data analysis task, iProg uses an LLM to first identify an appropriate decomposition of the problem into a declarative representation, expressed as a Data Flow Diagram (DFD). In a second phase, iProg then uses an LLM to generate code for each DFD process. In both stages, human feedback, mediated through the constructs provided by the communication protocol, is used to verify LLMs' outputs. We evaluate iProg extensively on two published scientific collaborations (astrophysics and biochemistry), demonstrating that it is possible to identify appropriate system decompositions and construct end-to-end information systems with better performance, higher code quality, and order-of-magnitude faster development compared to Low Code/No Code alternatives. The tool is available at: https://shraddhasurana.github.io/dhaani/

cs.AI↗

arXiv2025

Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge

The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated solutions. This paper presents a structured inductive programming approach with LLMs that successfully solves tasks across all IPARC categories. The controlled nature of IPARC reveals insights into LLM-based code generation, including the importance of prior structuring, LLMs' ability to aid structuring (requiring human refinement), the need to freeze correct code, the efficiency of code reuse, and how LLM-generated code can spark human creativity. These findings suggest valuable mechanisms for human-LLM collaboration in tackling complex program synthesis.

cs.SE↗

arXiv2021

Machine Learning for Scientific Discovery

Machine Learning algorithms are good tools for both classification and prediction purposes. These algorithms can further be used for scientific discoveries from the enormous data being collected in our era. We present ways of discovering and understanding astronomical phenomena by applying machine learning algorithms to data collected with radio telescopes. We discuss the use of supervised machine learning algorithms to predict the free parameters of star formation histories and also better understand the relations between the different input and output parameters. We made use of Deep Learning to capture the non-linearity in the parameters. Our models are able to predict with low error rates and give the advantage of predicting in real time once the model has been trained. The other class of machine learning algorithms viz. unsupervised learning can prove to be very useful in finding patterns in the data. We explore how we use such unsupervised techniques on solar radio data to identify patterns and variations, and also link such findings to theories, which help to better understand the nature of the system being studied. We highlight the challenges faced in terms of data size, availability, features, processing ability and importantly, the interpretability of results. As our ability to capture and store data increases, increased use of machine learning to understand the underlying physics in the information captured seems inevitable.

astro-ph.IM↗

arXiv2020

Predicting star formation properties of galaxies using deep learning

Understanding the star-formation properties of galaxies as a function of cosmic epoch is a critical exercise in studies of galaxy evolution. Traditionally, stellar population synthesis models have been used to obtain best fit parameters that characterise star formation in galaxies. As multiband flux measurements become available for thousands of galaxies, an alternative approach to characterising star formation using machine learning becomes feasible. In this work, we present the use of deep learning techniques to predict three important star formation properties -- stellar mass, star formation rate and dust luminosity. We characterise the performance of our deep learning models through comparisons with outputs from a standard stellar population synthesis code.

astro-ph.GA↗