arXiv subjects

Swati Sharma

Publications and source records attributed to Swati Sharma.

17 recordsLinked to original sources

arXiv2026

Prompt Coach: An Empirical Evaluation of an Agentic Tutor for Learning Prompt Engineering in Software Development

Prompt engineering has emerged as a critical yet undertaught skill for software developers, one that traditional learning approaches are ill-equipped to support given its evolving, interactive, and context-dependent nature. In this paper, we introduce Prompt Coach (PC), an agentic tutor that helps developers learn how to craft high-quality code-generation prompts through Socratic guidance embedded in-flow within their IDE. PC evaluates prompt quality across multiple dimensions and surfaces targeted questions to guide self-correction, grounded in the developer's codebase and the behavior of the target LLM. We present an early empirical study with 15 professional developers combining quantitative prompt quality scoring with qualitative perception measures. Participants showed statistically significant improvements after a single 60-minute session, with the largest gains across dimensions commonly overlooked by developers. They also reported strong trust, high adoption readiness, and unanimous agreement that PC improved their prompt-writing skills.

cs.SE↗

arXiv2026

Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages

The rising demand for inclusive speech technologies amplifies the need for multilingual datasets for Natural Language Processing (NLP) research. However, limited awareness of existing task-specific resources in low-resource languages hinders research. This challenge is especially acute in linguistically diverse countries, such as India. Cross-task profiling of existing Indian speech datasets can alleviate the data scarcity challenge. This involves investigating the utility of datasets across multiple downstream tasks rather than focusing on a single task. Prior surveys typically catalogue datasets for a single task, leaving comprehensive cross-task profiling as an open opportunity. Therefore, we propose Task-Lens, a cross-task survey that assesses the readiness of 50 Indian speech datasets spanning 26 languages for nine downstream speech tasks. First, we analyze which datasets contain metadata and properties suitable for specific tasks. Next, we propose task-aligned enhancements to unlock datasets to their full downstream potential. Finally, we identify tasks and Indian languages that are critically underserved by current resources. Our findings reveal that many Indian speech datasets contain untapped metadata that can support multiple downstream tasks. By uncovering cross-task linkages and gaps, Task-Lens enables researchers to explore the broader applicability of existing datasets and to prioritize dataset creation for underserved tasks and languages.

cs.CL↗

arXiv2025

Optical Spectroscopic Imaging for Early Detection of Salinity Stress in Plants: A Review

Salinity stress poses a significant challenge to global agriculture, necessitating efficient and scalable approaches for early detection and management. This review examines advanced optical spectroscopic imaging techniques, including fluorescence imaging, hyperspectral imaging, and thermal imaging, for their ability to detect physiological and biochemical responses in plants subjected to saline conditions. By focusing exclusively on imaging-based optical methods and excluding traditional spectroscopic techniques, the review emphasises non-invasive tools capable of delivering high sensitivity and specificity. These technologies enable real-time, high-throughput analysis, making them particularly well-suited for large-scale plant screening and breeding programs targeting salt tolerance. The integration of ground-based optical systems with aerial platforms such as unmanned aerial vehicles and satellites significantly expands spatial and temporal monitoring capabilities.

q-bio.QM↗

arXiv2025

Fusing Structural Phenotypes with Functional Data for Early Prediction of Primary Angle Closure Glaucoma Progression

Purpose: To classify eyes as slow or fast glaucoma progressors in patients with primary angle closure glaucoma (PACG) using an integrated approach combining optic nerve head (ONH) structural features and sector-based visual field (VF) functional parameters. Methods: PACG patients with >5 reliable VF tests over >5 years were included. Progression was assessed in Zeiss Forum, with baseline VF within six months of OCT. Fast progression was VFI decline <-2.0% per year; slow progression >-2.0% per year. OCT volumes were AI-segmented to extract 31 ONH parameters. The Glaucoma Hemifield Test defined five regions per hemifield, aligned with RNFL distribution. Mean sensitivity per region was combined with structural parameters to train ML classifiers. Multiple models were tested, and SHAP identified key predictors. Main outcome measures: Classification of slow versus fast progressors using combined structural and functional data. Results: We analyzed 451 eyes from 299 patients. Mean VFI progression was -0.92% per year; 369 eyes progressed slowly and 82 rapidly. The Random Forest model combining structural and functional features achieved the best performance (AUC = 0.87, 2000 Monte Carlo iterations). SHAP identified six key predictors: inferior MRW, inferior and inferior-temporal RNFL thickness, nasal-temporal LC curvature, superior nasal VF sensitivity, and inferior RNFL and GCL+IPL thickness. Models using only structural or functional features performed worse with AUC of 0.82 and 0.78, respectively. Conclusions: Combining ONH structural and VF functional parameters significantly improves classification of progression risk in PACG. Inferior ONH features, MRW and RNFL thickness, were the most predictive, highlighting the critical role of ONH morphology in monitoring disease progression.

q-bio.QM↗

arXiv2025

One dimensional analytical solutions of the transport equations for incompressible magnetohydrodynamic (MHD) turbulence

We derive one dimensional (1D) analytical solutions for the transport equations of incompressible magnetohydrodynamic (MHD) turbulence developed by Zank et al. [2012], Adhikari et al. [2023], including the Els\"asser energies and the correlation lengths. The solutions are suitable for an arbitrary given background convection speed and Alfv\'en speed profiles but require near equipartition of turbulent kinetic energy and magnetic field energy. These analytical solutions provide a simple tool to investigate the evolution of turbulence and resulting energetic particle diffusion coefficients in various space and astrophysical environments that possess simple geometry.

astro-ph.HE↗

arXiv2025

Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a token-level dense Reasoning Reflection Reward (R3) aligned with reasoning quality, and (ii) enforces rubric-gating as feasibility constraints at the rollout group level. R3 measures the model's token-level certainty of a reference answer under its chain-of-thought (CoT) prefix, and selectively emphasizes tokens with high cross-rollout variance, which we call reasoning-reflective tokens, that would otherwise be diluted by the bulk of low-variance tokens. The same variance signal also drives a filter that discards queries with insufficient signal for comparative learning. Rubric-gating complements R3 by operationalizing principled task criteria as hard accept/reject checks on final answers. Empirically, across four datasets spanning scientific writing, medicine, legal contracts, and finance, our framework outperforms strong baselines, achieves faster, more sample-efficient learning, and respects feasibility constraints.

cs.CL↗

arXiv2025

3D Structural Phenotype of the Optic Nerve Head at the Intersection of Glaucoma and Myopia -- A Key to Improving Glaucoma Diagnosis in Myopic Populations

Purpose: To characterize the 3D structural phenotypes of the optic nerve head (ONH) in patients with glaucoma, high myopia, and concurrent high myopia and glaucoma, and to evaluate their variations across these conditions. Participants: A total of 685 optical coherence tomography (OCT) scans from 754 subjects of Singapore-Chinese ethnicity, including 256 healthy (H), 94 highly myopic (HM), 227 glaucomatous (G), and 108 highly myopic with glaucoma (HMG) cases. Methods: We segmented the retinal and connective tissues from OCT volumes and their boundary edges were converted into 3D point clouds. To classify the 3D point clouds into four ONH conditions, i.e., H, HM, G, and HMG, a specialized ensemble network was developed, consisting of an encoder to transform high-dimensional input data into a compressed latent vector, a decoder to reconstruct point clouds from the latent vector, and a classifier to categorize the point clouds into the four ONH conditions. Results: The classification network achieved high accuracy, distinguishing H, HM, G, and HMG classes with a micro-average AUC of 0.92 $\pm$ 0.03 on an independent test set. The decoder effectively reconstructed point clouds, achieving a Chamfer loss of 0.013 $\pm$ 0.002. Dimensionality reduction clustered ONHs into four distinct groups, revealing structural variations such as changes in retinal and connective tissue thickness, tilting and stretching of the disc and scleral canal opening, and alterations in optic cup morphology, including shallow or deep excavation, across the four conditions. Conclusions: This study demonstrated that ONHs exhibit distinct structural signatures across H, HM, G, and HMG conditions. The findings further indicate that ONH morphology provides sufficient information for classification into distinct clusters, with principal components capturing unique structural patterns within each group.

eess.IV↗

arXiv2024

Enabling Adoption of Regenerative Agriculture through Soil Carbon Copilots

Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic carbon (SOC) levels, thus improving soil health and sequestering carbon. A challenge to increasing regenerative agriculture practices is cheaply measuring SOC over time and understanding how SOC is affected by regenerative agricultural practices and other environmental factors and farm management practices. To address this challenge, we introduce an AI-driven Soil Organic Carbon Copilot that automates the ingestion of complex multi-resolution, multi-modal data to provide large-scale insights into soil health and regenerative practices. Our data includes extreme weather event data (e.g., drought and wildfire incidents), farm management data (e.g., cropland information and tillage predictions), and SOC predictions. We find that integrating public data and specialized models enables large-scale, localized analysis for sustainable agriculture. In comparisons of agricultural practices across California counties, we find evidence that diverse agricultural activity may mitigate the negative effects of tillage; and that while extreme weather conditions heavily affect SOC, composting may mitigate SOC loss. Finally, implementing role-specific personas empowers agronomists, farm consultants, policymakers, and other stakeholders to implement evidence-based strategies that promote sustainable agriculture and build climate resilience.

cs.IR↗

arXiv2024

An anisotropic plasma model of the heliospheric interface

We present a pioneering model of the interaction between the solar wind and the surrounding interstellar medium that includes the possibility of different pressures in directions parallel and perpendicular to the magnetic field. The outer heliosheath region is characterized by a low rate of turbulent scattering that would permit development of pressure anisotropy. The effect is best seen on the interstellar side of the heliopause, where a narrow region develops with an excessive perpendicular pressure resembling a plasma depletion layer typical of planetary magnetspheres. The magnitude of this effect for typical heliospheric conditions is relatively small owing to proton-proton collisions. We show, however, that if the circumstellar medium is warm and tenuous, a much broader anisotropic boundary layer can exist, with a dominant perpendicular pressure in the southern hemisphere and a dominant parallel pressure in the north.

physics.space-ph↗

arXiv2024

RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture

There are two common ways in which developers are incorporating proprietary and domain-specific data when building applications of Large Language Models (LLMs): Retrieval-Augmented Generation (RAG) and Fine-Tuning. RAG augments the prompt with the external data, while fine-Tuning incorporates the additional knowledge into the model itself. However, the pros and cons of both approaches are not well understood. In this paper, we propose a pipeline for fine-tuning and RAG, and present the tradeoffs of both for multiple popular LLMs, including Llama2-13B, GPT-3.5, and GPT-4. Our pipeline consists of multiple stages, including extracting information from PDFs, generating questions and answers, using them for fine-tuning, and leveraging GPT-4 for evaluating the results. We propose metrics to assess the performance of different stages of the RAG and fine-Tuning pipeline. We conduct an in-depth study on an agricultural dataset. Agriculture as an industry has not seen much penetration of AI, and we study a potentially disruptive application - what if we could provide location-specific insights to a farmer? Our results show the effectiveness of our dataset generation pipeline in capturing geographic-specific knowledge, and the quantitative and qualitative benefits of RAG and fine-tuning. We see an accuracy increase of over 6 p.p. when fine-tuning the model and this is cumulative with RAG, which increases accuracy by 5 p.p. further. In one particular experiment, we also demonstrate that the fine-tuned model leverages information from across geographies to answer specific questions, increasing answer similarity from 47% to 72%. Overall, the results point to how systems built using LLMs can be adapted to respond and incorporate knowledge across a dimension that is critical for a specific industry, paving the way for further applications of LLMs in other industrial domains.

cs.CL↗

arXiv2024

Domain Adaptation for Sustainable Soil Management using Causal and Contrastive Constraint Minimization

Monitoring organic matter is pivotal for maintaining soil health and can help inform sustainable soil management practices. While sensor-based soil information offers higher-fidelity and reliable insights into organic matter changes, sampling and measuring sensor data is cost-prohibitive. We propose a multi-modal, scalable framework that can estimate organic matter from remote sensing data, a more readily available data source while leveraging sparse soil information for improving generalization. Using the sensor data, we preserve underlying causal relations among sensor attributes and organic matter. Simultaneously we leverage inherent structure in the data and train the model to discriminate among domains using contrastive learning. This causal and contrastive constraint minimization ensures improved generalization and adaptation to other domains. We also shed light on the interpretability of the framework by identifying attributes that are important for improving generalization. Identifying these key soil attributes that affect organic matter will aid in efforts to standardize data collection efforts.

cs.LG↗

arXiv2023

Knowledge Guided Representation Learning and Causal Structure Learning in Soil Science

An improved understanding of soil can enable more sustainable land-use practices. Nevertheless, soil is called a complex, living medium due to the complex interaction of different soil processes that limit our understanding of soil. Process-based models and analyzing observed data provide two avenues for improving our understanding of soil processes. Collecting observed data is cost-prohibitive but reflects real-world behavior, while process-based models can be used to generate ample synthetic data which may not be representative of reality. We propose a framework, knowledge-guided representation learning, and causal structure learning (KGRCL), to accelerate scientific discoveries in soil science. The framework improves representation learning for simulated soil processes via conditional distribution matching with observed soil processes. Simultaneously, the framework leverages both observed and simulated data to learn a causal structure among the soil processes. The learned causal graph is more representative of ground truth than other graphs generated from other causal discovery methods. Furthermore, the learned causal graph is leveraged in a supervised learning setup to predict the impact of fertilizer use and changing weather on soil carbon. We present the results in five different locations to show the improvement in the prediction performance in out-of-sample and few-shots setting.

cs.LG↗

arXiv2022

DeepG2P: Fusing Multi-Modal Data to Improve Crop Production

Agriculture is at the heart of the solution to achieve sustainability in feeding the world population, but advancing our understanding on how agricultural output responds to climatic variability is still needed. Precision Agriculture (PA), which is a management strategy that uses technology such as remote sensing, Geographical Information System (GIS), and machine learning for decision making in the field, has emerged as a promising approach to enhance crop production, increase yield, and reduce water and nutrient losses and environmental impacts. In this context, multiple models to predict agricultural phenotypes, such as crop yield, from genomics (G), environment (E), weather and soil, and field management practices (M) have been developed. These models have traditionally been based on mechanistic or statistical approaches. However, AI approaches are intrinsically well-suited to model complex interactions and have more recently been developed, outperforming classical methods. Here, we present a Natural Language Processing (NLP)-based neural network architecture to process the G, E and M inputs and their interactions. We show that by modeling DNA as natural language, our approach performs better than previous approaches when tested for new environments and similarly to other approaches for unseen seed varieties.

cs.LG↗

arXiv2022

Causal Modeling of Soil Processes for Improved Generalization

Measuring and monitoring soil organic carbon is critical for agricultural productivity and for addressing critical environmental problems. Soil organic carbon not only enriches nutrition in soil, but also has a gamut of co-benefits such as improving water storage and limiting physical erosion. Despite a litany of work in soil organic carbon estimation, current approaches do not generalize well across soil conditions and management practices. We empirically show that explicit modeling of cause-and-effect relationships among the soil processes improves the out-of-distribution generalizability of prediction models. We provide a comparative analysis of soil organic carbon estimation models where the skeleton is estimated using causal discovery methods. Our framework provide an average improvement of 81% in test mean squared error and 52% in test mean absolute error.

cs.LG↗

arXiv2022

Machine learning can guide experimental approaches for protein digestibility estimations

Food protein digestibility and bioavailability are critical aspects in addressing human nutritional demands, particularly when seeking sustainable alternatives to animal-based proteins. In this study, we propose a machine learning approach to predict the true ileal digestibility coefficient of food items. The model makes use of a unique curated dataset that combines nutritional information from different foods with FASTA sequences of some of their protein families. We extracted the biochemical properties of the proteins and combined these properties with embeddings from a Transformer-based protein Language Model (pLM). In addition, we used SHAP to identify features that contribute most to the model prediction and provide interpretability. This first AI-based model for predicting food protein digestibility has an accuracy of 90% compared to existing experimental techniques. With this accuracy, our model can eliminate the need for lengthy in-vivo or in-vitro experiments, making the process of creating new foods faster, cheaper, and more ethical.

q-bio.QM↗

arXiv2018

Evolution of Glassy Carbon Microstructure: In Situ Transmission Electron Microscopy of the Pyrolysis Process

Glassy carbon is a graphene-rich form of elemental carbon obtained from pyrolysis of polymers, which is composed of three-dimensionally arranged, curved graphene fragments alongside fractions of disordered carbon and voids. Pyrolysis encompasses gradual heating of polymers above 900 degree C under inert atmosphere, followed by cooling to room temperature. Here we report on an experimental method to perform in situ high-resolution transmission electron microscopy (HR-TEM) for the direct visualization of microstructural evolution in a pyrolyzing polymer in the 500-1200 degree C temperature range. The results are compared with the existing microstructural models of glassy carbon. Reported experiments are performed at 80 kV acceleration voltage using MEMS-based heating chips as sample substrates to minimize any undesired beam-damage or sample preparation induced transformations. The outcome suggests that the geometry, expansion and atomic arrangement within the resulting graphene fragments constantly change, and that the intermediate structures provide important cues on the evolution of glassy carbon. A complete understanding of the pyrolysis process will allow for a general process tuning specific to the precursor polymer for obtaining glassy carbon with pre-defined properties.

cond-mat.mtrl-sci↗

arXiv2015

Micro and nano patternable magnetic carbon

Carbon is conventionally not associated with magnetism, and much of the discussion of its nanotechnology perspectives appears to be centered on its electron transport properties. Among the few existing examples of magnetic carbon production, none has found a direct applicability in scalable micro and nano fabrication, Here we introduce a paramagnetic form of carbon whose precursor polymers can be lithographically patterned into micro and nano structures prior to pyrolysis. This unreactive and thermally robust material features strong room-temperature paramagnetism owing to a large number of unpaired electrons with restricted mobility, which is achieved by controlling the progression of bond dissociation and formation during pyrolysis. The manufacture of this magnetic carbon, having (3.97 x 0.8) 10^17 spins/ mg, can immediately benefit a number of spintronic and magnetic MEMS applications, and also shed light on the controversial theories concerning the existence and mechanisms of magnetism in carbon.

cond-mat.mtrl-sci↗