Showing 1–50 of 196 results for author: Chatterjee, P

Non-Local Energy Dissipation and Topological Obstructions in the Second-Order Positive Modified Burgers' Equation

Authors: Prasanta Chatterjee, Suman Pal

Abstract: We study the higher-order flows of the modified Burgers' equation generated by its standard recursion operator. In particular, we show that the second-order positive flow takes the form of a non-local integro-differential equation. After reducing the equation to a traveling-wave form, we investigate its asymptotic energy behavior. The resulting analysis shows that the non-local energy flux prevent… ▽ More We study the higher-order flows of the modified Burgers' equation generated by its standard recursion operator. In particular, we show that the second-order positive flow takes the form of a non-local integro-differential equation. After reducing the equation to a traveling-wave form, we investigate its asymptotic energy behavior. The resulting analysis shows that the non-local energy flux prevents the formation of both topological kink and bell-shaped solitary waves. We show that the non-local dissipation permanently breaks the asymptotic equilibrium between nonlinear convection and linear dispersion, forcing an irreversible energy imbalance. Our analysis shows that the solitary waves are unstable. The non-local term causes continuous energy loss through radiation. As a result, the traveling wave cannot keep a stable and symmetric shape. △ Less

Submitted 24 August, 2026; originally announced August 2026.

On the Second-Order Positive Burgers' Equation: Integrability, Lax Pair, Darboux Transformations, and Lie Symmetry Reduction

Authors: Suman Pal, Prasanta chatterjee

Abstract: This paper derives the second-order positive Burgers' equation from the standard Burgers' hierarchy to explore its complete integrability and exact analytical solutions. We construct this higher-order nonlinear evolution equation by systematically applying the recursion operator to the classical Burgers' equation. Expanding on this structural framework, we then derive the explicit third-order equa… ▽ More This paper derives the second-order positive Burgers' equation from the standard Burgers' hierarchy to explore its complete integrability and exact analytical solutions. We construct this higher-order nonlinear evolution equation by systematically applying the recursion operator to the classical Burgers' equation. Expanding on this structural framework, we then derive the explicit third-order equation and use Complete Bell Polynomials to generalize the $n$-th order hierarchy. Through the Cole-Hopf transformation, the second-order nonlinear equation rigorously maps to the linear third-order dispersion equation. We establish complete integrability by explicitly formulating the scalar Lax pair (zero-curvature representation), which allows us to directly derive the associated differential and algebraic Darboux transformations. To systematically classify explicit stationary, time-dependent traveling wave, and self-similar profiles, we apply several techniques to the linear domain: separation of variables, the Hirota perturbation method, traveling wave reduction via the Complete Discrimination System for Polynomial Method (CDSPM), and Lie similarity reduction. Crucially, our analysis demonstrates the exact finite truncation of the Hirota perturbation series. We conclude by outlining how this equation impacts the theoretical understanding of fluid dynamics, nonlinear transport phenomena, and higher-order wave propagation. △ Less

Submitted 13 August, 2026; originally announced August 2026.

Emergence of fractal structures from breather interactions in the $(2+1)$-dimensional Konopelchenko--Dubrovsky equation

Authors: Snehalata Nasipuri, Prasanta Chatterjee, Saugata Dutta

Abstract: Fractal structures generated through nonlinear breather interactions are investigated for the $(2+1)$-dimensional Konopelchenko--Dubrovsky (KD) equation by means of the Hirota bilinear method. The bilinear form of the system is first derived, after which breather interaction solutions are constructed analytically through suitable auxiliary functions. It is shown that the interaction of breather wa… ▽ More Fractal structures generated through nonlinear breather interactions are investigated for the $(2+1)$-dimensional Konopelchenko--Dubrovsky (KD) equation by means of the Hirota bilinear method. The bilinear form of the system is first derived, after which breather interaction solutions are constructed analytically through suitable auxiliary functions. It is shown that the interaction of breather waves in the coupled nonlinear environment gives rise to highly intricate multiscale patterns exhibiting self-similar behaviour under successive magnification. To characterize the geometric complexity of the obtained structures, a three-dimensional voxel-based box-counting method is employed. The computed dimensions are found to be non-integer, confirming the fractal nature of the generated patterns. In addition, relative error analysis, standard error estimation, bootstrap standard deviation and convergence analysis are performed to examine the robustness and reproducibility of the estimated dimensions. The present work suggests that nonlinear breather interactions in coupled dispersive systems may provide a natural mechanism for the emergence of fractal geometries and complex multiscale structures. The combined analytical and quantitative framework developed here may provide further insight into nonlinear energy localization and scale-dependent structures arising in fluid dynamics, plasma physics and nonlinear wave propagation. △ Less

Submitted 11 August, 2026; originally announced August 2026.

How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair

Authors: Ramtin Ehsani, Irene Manotas, Saurabh Pujar, Luca Buratti, Preetha Chatterjee

Abstract: Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent. Even when provided with the same contextual information, an LLM may generate a correct patch for one bug but fail on another closely related bug. Why this happens remains poorly understood, and it is unclear how LLMs prioritize the diverse information in bug reports… ▽ More Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent. Even when provided with the same contextual information, an LLM may generate a correct patch for one bug but fail on another closely related bug. Why this happens remains poorly understood, and it is unclear how LLMs prioritize the diverse information in bug reports and whether model attention affects repair success. In this paper, we present the first empirical study of attention patterns in LLM-based program repair, providing interpretable insights into how models process bug reports and where their attention is concentrated during repair. We analyze 319 real-world Python and Java bugs from SWE-bench Verified and Multi-SWE-bench to study (RQ1) how model attention is distributed across bug report sections, (RQ2) how attention patterns within each section differ between successful and unsuccessful repairs, and (RQ3) how these patterns compare to information developers consider important for bug fixing. We find that successful repairs are characterized by diffused attention across multiple diagnostic components such as bug descriptions, stacktraces, and test cases, while failures often exhibit over-localized attention toward metadata such as version information. We further observe that stronger alignment between model attention and developer-identified key sections and phrases is associated with higher repair success. Our results provide the first empirical evidence that attention misallocation is a key factor in LLM-based APR failures, and offer actionable insights for designing more interpretable and reliable future APR systems. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE) 2026 Conference

Expanding Flow Maps

Authors: Sophia Tang, Pranam Chatterjee

Abstract: Flow-based generative models have enabled remarkable progress in fast and controllable generation across continuous and discrete state spaces, yet existing parameterizations are constrained to fixed dimensions or fixed sequence lengths. Here, we introduce Expanding Generative Flows (EFlows), which define flows between distributions of increasing dimensionality along an expanding interpolant that g… ▽ More Flow-based generative models have enabled remarkable progress in fast and controllable generation across continuous and discrete state spaces, yet existing parameterizations are constrained to fixed dimensions or fixed sequence lengths. Here, we introduce Expanding Generative Flows (EFlows), which define flows between distributions of increasing dimensionality along an expanding interpolant that grows the state by augmenting it with conditional noise. Building on this construction, we propose Expanding Flow Maps (EFMs), a new class of flow maps that distill the expanding interpolant into efficient few-step generative models. Each EFM factors the map between any two timesteps into two learnable operations: an expand operator, which augments the state space with new coordinates or tokens conditioned on the current state, and a transport map, which pushes the expanded state forward along the interpolant. Composing these operators yields a single map that jointly expands and denoises the state, recovering existing fixed-canvas flows and flow maps as the special case in which the expand operator is the identity. We further extend the framework to the discrete simplex, enabling variable-size graph generation and variable-length sequence generation. Across both continuous and discrete modalities, we establish EFlows and EFMs as a principled framework for settings in which output size is itself a learned, controllable degree of freedom. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Rethinking Benchmarks and Models for Enzyme Specificity Prediction

Authors: Elizabeth H. Mahood, Natália Komorníková, Tomáš Pluskal, Pranam Chatterjee

Abstract: Artificial Intelligence has had a profound impact on the biological sciences, and in particular has accelerated research on protein form and function. Enzymes are no exception: a surge of predictive models have been recently developed to address a range of enzyme tasks. Models addressing enzyme-substrate (ES) or enzyme-reaction (ER) compatibility could be especially valuable for enzyme annotation,… ▽ More Artificial Intelligence has had a profound impact on the biological sciences, and in particular has accelerated research on protein form and function. Enzymes are no exception: a surge of predictive models have been recently developed to address a range of enzyme tasks. Models addressing enzyme-substrate (ES) or enzyme-reaction (ER) compatibility could be especially valuable for enzyme annotation, biosynthetic pathway elucidation, and biocatalyst retrieval, the central challenge of which is the identification of a true catalyst (or truly compatible reaction) among many similar candidates. While existing models report strong performance on alternative benchmarks, less is known about their capabilities in this regime. Herein, we benchmark four recently released ES and ER prediction models, using tasks and datasets tailored to this setting. We first show that two representative ES prediction models perform near random baselines across two enzyme families when considering enzymes and substrates not encountered during training. To evaluate additional models across a consistent dataset, we next assemble the largest cytochrome P450 (CYP) reaction dataset to date, 2,922 reactions across 768 enzymes, and construct a CYP ranking benchmark requiring the correct enzyme to be prioritized among all CYPs in its native organism. We again find that most models do not outperform sequence-based (BLAST) baselines even after fine-tuning. We finally adapt the bimolecular structure prediction model Boltz to ES prediction by training supervised classifiers on residue-ligand pair embeddings, and show that this approach consistently surpasses the BLAST baselines on our CYP ranking benchmark. Together, our results argue for more discovery-relevant benchmarking and suggest that interaction-aware representations from full biomolecular complexes may provide a promising basis for enzyme prioritization. △ Less

Submitted 6 July, 2026; originally announced July 2026.

SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery

Authors: Hanqun Cao, Zijun Gao, Chunbin Gu, Ge Liu, Pheng Ann Heng, Pranam Chatterjee

Abstract: Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations. Existing approaches such as AF-Cluster operate in sequence space, providing limited control over which conformational basin is sampled. We introduce SF-Cluster, which subsamples MSAs using patterns of predicted local en… ▽ More Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations. Existing approaches such as AF-Cluster operate in sequence space, providing limited control over which conformational basin is sampled. We introduce SF-Cluster, which subsamples MSAs using patterns of predicted local energetic frustration, a representation largely independent of sequence similarity. Across a benchmark of 48 cases spanning fold-switching, allosteric, oligomerization-coupled, and intrinsically disordered systems, and using an AF-Cluster-style dual-reference RMSD criterion, SF-Cluster improves target-state recovery of the alternative conformation over AF-Cluster across the two-state classes, with the largest improvement observed for allosteric systems (+15.5 percentage points). The selected MSAs transfer to an architecturally distinct predictor, indicating that the conformational signal resides in MSA composition. Mechanistically, matched-depth controls show that this recovery advantage is largely explained by the effective depth of the selected subsets, which frustration-pattern selection reliably reaches. At the same time, highly frustrated residues are enriched at sites supported by deep mutational scanning and NMR two-state exchange, and frustration covariation is enriched at state-switching contacts while remaining distinct from coevolutionary coupling. Together, these results identify frustration patterns as a transferable representation for conformational prediction and position MSA subsampling as a representation-guided reweighting problem. △ Less

Submitted 30 June, 2026; originally announced July 2026.

Comments: Accepted at the AI4Science Workshop at ICML 2026 (Oral)

TraceView: Interactive Visualization of Agentic Program Repair Trajectories

Authors: Amirali Sajadi, Tu Nguyen, Kimmie Huynh, Esteban Parra, Preetha Chatterjee

Abstract: LLM-based automated program repair (APR) agents generate patches to fix software bugs with minimal human intervention. These agents often produce long trajectories of reasoning, tool use, and feedback to produce candidate patches. Final patch outcomes show whether a repair attempt succeeded or failed, but they do not show how the agent reached that outcome, or where the process became repetitive o… ▽ More LLM-based automated program repair (APR) agents generate patches to fix software bugs with minimal human intervention. These agents often produce long trajectories of reasoning, tool use, and feedback to produce candidate patches. Final patch outcomes show whether a repair attempt succeeded or failed, but they do not show how the agent reached that outcome, or where the process became repetitive or misaligned with the task. This makes agentic repair failures difficult to diagnose, reproduce, and prevent. To help developers address these challenges, we present TraceView, an interactive tool for labeling and visualizing repair trajectories from APR systems. TraceView organizes raw and pre-labeled agentic runs with Thought, Action, and Result components to support semantic relation labeling and diagnosis, and renders the resulting trajectory as graph views. Furthermore, TraceView provides relation filters, patch outcome summaries, metrics, and node-level evidence panels to help users inspect how reasoning, actions, and feedback connect across the various steps of an agentic repair attempt. We evaluate TraceView with five researchers through a survey-based user study. Participants reported that TraceView made trajectories easier to scan and that its overview-to-detail workflow helped them better understand repair behavior. The TraceView source code is available at https://github.com/SOAR-Lab/agent-traj-visualization. A screencast of TraceView is available at https://youtu.be/9ZCh7Ifj2AQ. △ Less

Submitted 20 June, 2026; originally announced June 2026.

Faster Code, Deeper Debt? A Multivocal Literature Review on Technical Debt and Its Early Signs in LLM-Assisted Software Development

Authors: Ramtin Ehsani, Shriya Rawal, Yuanfang Cai, Preetha Chatterjee

Abstract: With the rapid adoption of LLM-assisted coding, the need to manage the technical debt these systems introduce has become urgent. In this paper, we conduct a multivocal literature review of 104 sources (31 formal, 73 grey) to examine how LLM-assisted development contributes to technical debt and what strategies, metrics, and benchmarks exist to mitigate it. We find that LLMs often amplify tradition… ▽ More With the rapid adoption of LLM-assisted coding, the need to manage the technical debt these systems introduce has become urgent. In this paper, we conduct a multivocal literature review of 104 sources (31 formal, 73 grey) to examine how LLM-assisted development contributes to technical debt and what strategies, metrics, and benchmarks exist to mitigate it. We find that LLMs often amplify traditional forms of technical debt, particularly code, design, and documentation debts, while also introducing new LLM-specific debts. Notably, we identify fast-integration debt, where rapidly generated code prioritizes speed over quality, triggering a domino effect that leads to governance debt and increased long-term maintenance costs. Additional emerging categories include prompt, ethical, data, and provenance debt, reflecting new challenges unique to LLM adoption. To address these, strategies suggested in the literature include human-in-the-loop frameworks, prompt engineering, and data quality alignment. In practice, tools such as SonarQube are commonly used to detect technical debt indicators, while research prototypes such as CodeSmellEval are emerging to assess how LLMs contribute to debts. However, no standardized benchmarks or LLM-specific metrics yet exist, leaving an important gap. Based on findings, we outline insights and future directions to ensure reliable integration of LLMs into software engineering workflows. △ Less

Submitted 11 June, 2026; originally announced June 2026.

Comments: Accepted for publication in ACM Transactions on Software Engineering and Methodology (TOSEM), 2026

A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

Authors: Sophia Tang, Yuchen Zhu, Molei Tao, Pranam Chatterjee

Abstract: Discrete diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via token insertion. Principled reward-guided fine-tuning for any-length discrete diffusion, however, remains largely unexplored. We introduce Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding (A2D2), a unified framework for reward-guided fi… ▽ More Discrete diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via token insertion. Principled reward-guided fine-tuning for any-length discrete diffusion, however, remains largely unexplored. We introduce Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding (A2D2), a unified framework for reward-guided fine-tuning of any-length discrete diffusion models via joint optimization of the insertion and unmasking policies together with a quality-based inference schedule. We derive the Radon-Nikodym derivative for the joint insertion-unmasking path measures, enabling theoretically guaranteed convergence to the intractable reward-tilted sequence distribution without requiring target samples. Building on this, we establish unmasking and insertion quality as tractable approaches for minimizing decoding error and introduce the Adaptive Joint Decoding (AJD) loss, which provably yields the optimal path measure that generates the reward-tilted distribution. Empirically, A2D2 improves reward optimization while enhancing generation flexibility and accuracy over prior fixed-length fine-tuning and inference-time guidance methods. △ Less

Submitted 11 June, 2026; originally announced June 2026.

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

Authors: Riccardo De Santi, Bruce Lee, Cristian Perez Jensen, Kimon Protopapas, Sophia Tang, Cheng-Hao Liu, Pranam Chatterjee, Yisong Yue, Andreas Krause

Abstract: Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In generative discovery, however, one aims to sample valid new-to-nature designs, assigned negligible probability under, and thus inaccessible to, standard models fitted to the observed data. To overcome this limitation, we depar… ▽ More Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In generative discovery, however, one aims to sample valid new-to-nature designs, assigned negligible probability under, and thus inaccessible to, standard models fitted to the observed data. To overcome this limitation, we depart from data distribution matching and view a generative model through its generable set: the region it covers with non-negligible probability. This allows to introduce a new learning principle for out-of-distribution flow modeling: enlarging a model's generable set to increase coverage of the valid design space. We propose Active Flow Expansion (ActFlow), a continued pre-training method that employs verifier feedback to expand a pre-trained model over new valid regions by iteratively adapting to synthetic data generated through active exploration in the learned flow representation. Theoretically, we establish to our knowledge first-of-their-kind statistical learning guarantees for out-of-distribution flow modeling, analyzing generable set expansion as a local-to-global reachability process over a learned representation. Empirically, we assess ActFlow with suitable out-of-distribution generative modeling metrics across small organic molecules, mid-sized drug-like molecules, therapeutic peptides, and protein sequence design tasks. Results show that ActFlow expands valid coverage far beyond the region modeled by the initial pre-trained model, significantly outperforming widely adopted synthetic flow pre-training methods. △ Less

Submitted 7 June, 2026; originally announced June 2026.

Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments

Authors: Abdullah Al Mujahid, Preetha Chatterjee, Mia Mohammad Imran

Abstract: Developers increasingly use AI tools such as ChatGPT, Copilot, and Claude in everyday software workflows, but prior studies often evaluate LLM outputs in isolation rather than examining how developers adapt them in real projects. We analyze 35,361 GitHub code comments that explicitly reference AI use and their associated code blocks. We first open-code 500 unique comments and code blocks to derive… ▽ More Developers increasingly use AI tools such as ChatGPT, Copilot, and Claude in everyday software workflows, but prior studies often evaluate LLM outputs in isolation rather than examining how developers adapt them in real projects. We analyze 35,361 GitHub code comments that explicitly reference AI use and their associated code blocks. We first open-code 500 unique comments and code blocks to derive a taxonomy of AI-assisted development activities, then annotate the full dataset using two LLM-based classifiers and aggregate predictions with Dawid-Skene expectation-maximization. We also analyze 12,996 subsequent commit messages to study how AI-assisted code evolves after introduction, and examine temporal trends from December 2022 to March 2026. Our results show that developers primarily use LLMs for code implementation, followed by code enhancement, debugging, documentation, and testing. Subsequent commits frequently involve refactoring and cleanup, feature integration and extension, and bug fixing, indicating sustained human oversight in adapting AI-assisted code. Over time, AI-referencing comments shift from direct code generation toward knowledge and conceptual support and code enhancement. These findings suggest that AI tools are becoming embedded not only as code-generation aids, but also as collaborative support mechanisms whose outputs are refined, extended, and corrected by developers over time. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: Preprint version

AlloGen: Conformation-Selective Binder Generation with Differential State Scoring

Authors: Hanqun Cao, Zachary Quinn, Aastha Pal, Sumi Kimura, Jingjie Zhang, Pheng Ann Heng, Pranam Chatterjee

Abstract: Protein binder design has largely optimized for affinity alone, leaving conformational selectivity unaddressed: for allosteric targets such as kinases, nuclear receptors, and GPCRs, a binder that engages both active and inactive states provides no functional specificity regardless of how tightly it binds. We introduce AlloGen, a modular framework that decouples backbone generation from a learned s… ▽ More Protein binder design has largely optimized for affinity alone, leaving conformational selectivity unaddressed: for allosteric targets such as kinases, nuclear receptors, and GPCRs, a binder that engages both active and inactive states provides no functional specificity regardless of how tightly it binds. We introduce AlloGen, a modular framework that decouples backbone generation from a learned state-selectivity scorer $Q_θ$, an SE(3)-invariant interface graph transformer trained via a two-phase curriculum that first learns interface geometry before imposing conformational discrimination. Because $Q_θ$ is fully differentiable and generator-agnostic, it integrates with any backbone generator as a passive reranker or an active gradient-based guide without retraining. Across a diverse benchmark of proteins spanning multiple families and conformational mechanisms, AlloGen consistently identifies binders that preferentially recognize desired structural states while rejecting alternative conformations. Experimental validation on calmodulin further demonstrates that these computational selectivity signals translate to physical molecules, yielding de novo peptides that bind the desired holo conformation while exhibiting no detectable binding to the apo state. Together, these results establish conformational selectivity as a learnable property and provide a general framework for state-selective protein binder design. △ Less

Submitted 3 June, 2026; originally announced June 2026.

On the Relationship between Solar Spicules and Propagating Coronal Disturbances: The Role of Shocks

Authors: Ravi Chaurasiya, Sankalp Srivastava, Piyali Chatterjee, Sahel Dey, Robertus Erdélyi, Ankala Raja Bayanna

Abstract: Spicules and propagating coronal disturbances (PCDs) are ubiquitous dynamic features of the solar atmosphere, yet their physical connection remains an open question of paramount importance to the mass and energy transport in the solar atmosphere. Using concurrent multiwavelength high-resolution observations from the Swedish 1-m Solar Telescope and the Solar Dynamics Observatory, supported with two… ▽ More Spicules and propagating coronal disturbances (PCDs) are ubiquitous dynamic features of the solar atmosphere, yet their physical connection remains an open question of paramount importance to the mass and energy transport in the solar atmosphere. Using concurrent multiwavelength high-resolution observations from the Swedish 1-m Solar Telescope and the Solar Dynamics Observatory, supported with two-dimensional radiative magnetohydrodynamic (MHD) simulations, we find that i) shock waves in the chromosphere generated from non-linear wave steepening drive some spicules, ii) in the corona, these shock waves may transition into large amplitude non-linear compressive MHD waves depending on the magnetic field strength and the ambient coronal conditions. In either case, the shocks or the large-amplitude compressive waves in the corona, also transport upward mass flux and produce intensity variations in the form of PCDs in coronal passbands. Further a multi-height wavelet analysis shows dominant $\sim$5 minute periods in the lower chromosphere that evolve into longer periods ($\ge$10 minutes) at higher atmospheric layers, consistent with dispersive propagation in a stratified medium. The observational characteristics together with the numerical simulations, demonstrate that a shock-driven MHD mechanism links spicule formation to coronal disturbances. Finally, mass flux estimates from both the observations and the simulations indicate that these PCDs can also aid in supplying mass to the solar wind. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: 16 pages, 13 figures. Accepted for publication in ApJ

Journal ref: The Astrophysical Journal, 1005, 111 (2026)

Impact of Disorder Dynamics and Multi-Domain Kinetics on the Sliding Ferroelectricity of CVD-Grown 3R-WSe2 Bilayers

Authors: Sourav Paul, Prasenjit Ghosh, Krishna Prasad Maity, Vineet Pandey, Abhijith M. B., Premananda Chatterjee, Kenji Watanabe, Takashi Taniguchi, Nicholas R. Glavin, Ajit K. Roy, Atindra Nath Pal, Vidya Kochat

Abstract: Sliding ferroelectricity in van der Waals (vdW) layered systems has emerged as a promising route toward non-volatile nanoscale devices, where interlayer displacement in non-centrosymmetric bilayers generates an out-of-plane polarization. In particular, 3R-stacked bilayer transition metal dichalcogenides (TMDs) grown via chemical vapor deposition (CVD) have been shown to host such polarization due… ▽ More Sliding ferroelectricity in van der Waals (vdW) layered systems has emerged as a promising route toward non-volatile nanoscale devices, where interlayer displacement in non-centrosymmetric bilayers generates an out-of-plane polarization. In particular, 3R-stacked bilayer transition metal dichalcogenides (TMDs) grown via chemical vapor deposition (CVD) have been shown to host such polarization due to broken inversion symmetry. However, a detailed investigation of the 2D ferroelectric (FE) properties of CVD-grown 2D films, particularly the role of intrinsic disorder, such as structural defects and domain structure, remains poorly understood. Here, we investigate the FE switching characteristics of CVD-grown 3R-stacked WSe2 using a graphene-based ferroelectric field-effect transistor (graphene-FE-FET) architecture, where graphene serves as a highly sensitive probe of induced charge modulation due to polarization switching of FEs. We show that the growth-induced structural disorder significantly impacts polarization switching, while multi-domain kinetics governs the evolution of the FE response. These findings provide important insights into the design and optimization of FE devices based on vdW materials. △ Less

Submitted 30 May, 2026; originally announced June 2026.

Journal ref: Nanoscale 2026

mRNAutilus: Multi-Objective-Guided Discrete Generation of mRNA with Optimized Therapeutic Properties

Authors: Sawan Patel, Sophia Tang, Yesol Kim, Yinuo Zhang, Divya Srijay, Ping-Jung Lin, Shambhavi Shubham, Fengmei Pi, Cedric Wu, Sherwood Yao, Pranam Chatterjee

Abstract: Therapeutic mRNA design requires coordinating multiple interacting sequence features across the full transcript, where codon usage, untranslated regions (UTRs), and their coupling jointly determine stability, translation efficiency, and protein expression. Here, we present mRNA generation via unrolled trajectories and informed latent updates (mRNAutilus), a framework for simultaneous codon optimiz… ▽ More Therapeutic mRNA design requires coordinating multiple interacting sequence features across the full transcript, where codon usage, untranslated regions (UTRs), and their coupling jointly determine stability, translation efficiency, and protein expression. Here, we present mRNA generation via unrolled trajectories and informed latent updates (mRNAutilus), a framework for simultaneous codon optimization and de novo UTR design directly from sequence. mRNAutilus combines a masked discrete diffusion model trained on millions of full-length mRNAs with Monte Carlo Tree Guidance to generate Pareto-efficient sequences under multiple functional objectives, using lightweight regressors over model embeddings to predict half-life, translation efficiency, and protein abundance. Unlike recent methods that design coding sequences and UTRs separately or rely on post hoc assembly and screening, mRNAutilus generates complete transcripts in a single process optimized across properties. Across diverse targets, zero-shot mRNAs encoding P. pyralis luciferase achieve over 400-fold higher expression than wild-type and outperform commercial and machine learning-designed baselines, including zero-shot generative approaches. Zero-shot SARS-CoV-2 Spike mRNAs exceed clinically used and commercial constructs and match or surpass lab-optimized designs with improved durability. We further demonstrate generality in therapeutic settings, including prime editing (PEMax) and programmable proteome modulation, where mRNAutilus-designed constructs enhance expression of peptide-guided E3 ligases (uAbs) for beta-catenin degradation. These results establish a sequence-based, multi-objective framework for generating functional mRNAs tailored to diverse biological applications. △ Less

Submitted 29 May, 2026; originally announced May 2026.

A Unified Range Characterization for the Spherical mean transform

Authors: Pradipta Chatterjee, Nisha Singhal, Abhilash Tushir

Abstract: In this article, we investigate the range characterization for the spherical mean transform (SMT) of functions supported in the unit ball. In earlier works, in the case of odd dimensions, a set of differential conditions was obtained, whereas in the case of even dimensions, integral conditions were obtained. We prove that these conditions that are different based on the parity of dimension are, in… ▽ More In this article, we investigate the range characterization for the spherical mean transform (SMT) of functions supported in the unit ball. In earlier works, in the case of odd dimensions, a set of differential conditions was obtained, whereas in the case of even dimensions, integral conditions were obtained. We prove that these conditions that are different based on the parity of dimension are, in fact, equivalent in odd dimensions. This equivalence shows that the integral conditions yield a unified simple range characterization for the SMT that is valid in both even and odd dimensions. △ Less

Submitted 26 May, 2026; originally announced May 2026.

MSC Class: 33C55; 35R30; 44A12; 44A15; 444A20; 45Q05; 92C55

GeoCycler: Reward-Aligned 3D Diffusion for Constraint-Conditioned Cyclic Peptide Design

Authors: Jingjie Zhang, Hanqun Cao, Haosen Shi, He Mutian, Yu Wang, Zijun Gao, Fang Wu, Xiaojun Yao, Chang-Yu Hsieh, Sinno Jialin Pan, Pranam Chatterjee, Chunbin Gu, Pheng-Ann Heng

Abstract: Cyclic peptides are attractive therapeutic modalities because their closed-ring topology can improve stability and target specificity. However, de novo cyclic peptide design remains challenging for diffusion generators, as macrocyclization requires satisfying sparse, non-smooth, and compositional geometric constraints. Existing constraint-conditioned methods largely rely on inference-time guidance… ▽ More Cyclic peptides are attractive therapeutic modalities because their closed-ring topology can improve stability and target specificity. However, de novo cyclic peptide design remains challenging for diffusion generators, as macrocyclization requires satisfying sparse, non-smooth, and compositional geometric constraints. Existing constraint-conditioned methods largely rely on inference-time guidance, which can steer samples toward desired closures but does not directly change the learned generative distribution. We propose GeoCycler, a reward-weighted diffusion alignment framework for training conditional latent diffusion models toward macrocyclization feasibility. GeoCycler introduces a type-gated stair reward that activates distance-based shaping only when prerequisite residue or linker types are satisfied, providing dense geometric feedback while avoiding misleading signals from chemically incompatible anchors. Together with positive-only reward weighting and replay-based stabilization, GeoCycler aligns a single generator across multiple cyclization topologies. On the LNR benchmark, GeoCycler improves pass@5 closure success over strong guidance-based baselines across stapled, head-to-tail, disulfide, and bicyclic settings. In particular, it improves head-to-tail success by 20.8 percentage points over CP-Composer while maintaining comparable amino-acid and backbone-dihedral statistics. These results suggest that training-time alignment to sparse geometric constraints is a promising alternative to relying solely on post hoc sampling-time correction for cyclic peptide generation. △ Less

Submitted 22 May, 2026; originally announced May 2026.

TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation

Authors: Hanqun Cao, Aastha Pal, Sophia Tang, Yinuo Zhang, Jingjie Zhang, Pheng Ann Heng, Pranam Chatterjee

Abstract: Protein function is often controlled by ligands that bias the direction of state transitions, such as agonists and antagonists, rather than stabilizing a single conformation. This is especially important for clinically relevant G protein-coupled receptors (GPCRs), where therapeutic efficacy depends on functional directionality. Structure-based design methods optimize binding to static conformation… ▽ More Protein function is often controlled by ligands that bias the direction of state transitions, such as agonists and antagonists, rather than stabilizing a single conformation. This is especially important for clinically relevant G protein-coupled receptors (GPCRs), where therapeutic efficacy depends on functional directionality. Structure-based design methods optimize binding to static conformations and cannot represent non-reversible, directional effects or systematically distinguish agonist from antagonist behavior. To address this gap, we introduce Transition-Directed Discrete Diffusion for Allosteric Binder Design (TD3B), a sequence-based generative framework that designs binders with specified agonist or antagonist behavior via a directional transition control objective. TD3B combines a target-aware Direction Oracle, a soft binding-affinity gate, and amortized fine-tuning of a pre-trained discrete diffusion model, enabling targeted agonist and antagonist generation decoupled from binding affinity and unattainable by equilibrium-based or inference-only guidance baselines. The code and checkpoints are available at https://huggingface.co/ChatterjeeLab/TD3B. △ Less

Submitted 10 May, 2026; originally announced May 2026.

Comments: Published as a Spotlight at ICML 2026 (Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea)

Criticality of ISCOs and AdS/CFT

Authors: Chandrasekhar Bhamidipati, Parashar Chatterjee, Sudipta Mukherji, Yogesh Kumar Srivastava

Abstract: We study the trajectories of massive particles in spherically symmetric black holes in arbitrary dimensions, and find certain universal features based on the topological classification of the fixed points. If the system admits a center, we find two possible outcomes: regardless of the value of the angular momentum, the center always survives, which is realized in global AdS spacetimes or, the cent… ▽ More We study the trajectories of massive particles in spherically symmetric black holes in arbitrary dimensions, and find certain universal features based on the topological classification of the fixed points. If the system admits a center, we find two possible outcomes: regardless of the value of the angular momentum, the center always survives, which is realized in global AdS spacetimes or, the center disappears below a critical value of angular momentum, which happens for various spherically symmetric black holes. For the latter case, we find that irrespective of the details of the black hole, there must always be a saddle point. Topological arguments show that there exists a certain critical value of energy, angular momentum and the angular velocity, where the center and the saddle coalesce. This happens at a special point in the parameter space where the trajectories are the limiting innermost stable circular orbits (ISCOs). At the critical point, conserved quantities show universal, van der Waals-like mean-field scaling typical of a second-order phase transition. The anomalous dimensions $γ$ of the double-twist operators in the CFT are found, both using AdS/CFT and through the the heavy-heavy-light-light four point correlators, giving negative and positive values for the center and saddle, respectively, including the emergence of certain non-analytic behaviour at the ISCO. For the center, we also find subleading corrections in $\frac{1}{Δ_H}$ to $γ$ in the dual CFT, and dsicuss the implications of our results. △ Less

Submitted 28 April, 2026; originally announced April 2026.

Comments: 30 pages, 7 figures

Anderson localization via Peierls phase modulation

Authors: Arpita Goswami, Pallabi Chatterjee, Ranjan Modak, Shaon Sahoo

Abstract: We investigate a two leg ladder system subjected to an external magnetic field. In the absence of a magnetic field, the system is described by a clean tight binding model, with no disorder in either the onsite potential or the hopping amplitudes. The effect of magnetic field in this system is studied by introducing the Peierls phases in the hopping amplitudes along a leg (appropriate when the Land… ▽ More We investigate a two leg ladder system subjected to an external magnetic field. In the absence of a magnetic field, the system is described by a clean tight binding model, with no disorder in either the onsite potential or the hopping amplitudes. The effect of magnetic field in this system is studied by introducing the Peierls phases in the hopping amplitudes along a leg (appropriate when the Landau gauge is chosen). For a uniform magnetic field, characterized by a constant Peierls phase, we find that all eigenstates remain delocalized. In contrast, random Peierls phases, representing a random magnetic field, lead to complete localization of the eigenstates. We further show that a quasiperiodic modulation of the Peierls phase can drive a transition from a fully delocalized to a fully localized phase upon tuning the quasiperiodicity. For a two parameter quasiperiodic Peierls phase, varying analogously to a generalized Aubry Andre type potential, we construct the phase diagram of the system. The phase diagram exhibits regions of delocalized and localized phases, separated by intermediate regimes of mixed phase. We also perform a semiclassical analysis that qualitatively yields a similar phase diagram, capturing the localization transition. Our results demonstrate a mechanism for controlling transport properties via the Peierls phase engineering. △ Less

Submitted 18 August, 2026; v1 submitted 12 April, 2026; originally announced April 2026.

Comments: Accepted for Publication in Phys. Rev. B; Final version 21 pages, 25 figures

Journal ref: Phys. Rev. B 114, 094204 (2026)

Quantum-to-semiclassical Husimi dynamics of non-Hermitian localization transitions

Authors: Pallabi Chatterjee, Bhabani Prasad Mandal, Ranjan Modak

Abstract: The localization transition in the Hermitian Aubry-André model is known to have a clear classical origin, with the critical point being exactly predictable from an analysis of classical phase-space trajectories. Motivated by this correspondence, we investigate whether a similar classical origin exists for localization transitions in non-Hermitian quasiperiodic Hamiltonians. Using semiclassical Hus… ▽ More The localization transition in the Hermitian Aubry-André model is known to have a clear classical origin, with the critical point being exactly predictable from an analysis of classical phase-space trajectories. Motivated by this correspondence, we investigate whether a similar classical origin exists for localization transitions in non-Hermitian quasiperiodic Hamiltonians. Using semiclassical Husimi dynamics together with a detailed phase-space stability analysis, we show that localization transitions persist even in the semiclassical limit of such non-Hermitian models. However, in sharp contrast to the Hermitian Aubry-André case, the transition point inferred from classical phase-space analysis does not coincide with the quantum critical point. Instead, we find that the semiclassical transition depends sensitively on the choice of the irrational parameter defining the quasiperiodic potential, indicating the absence of a universal classical-quantum correspondence for the localization transition in the non-Hermitian setting. Nonetheless, we identify a suitable parameter regime in which the classical dynamics can faithfully mimic the quantum dynamics over a finite but appreciable time window. △ Less

Submitted 21 June, 2026; v1 submitted 7 March, 2026; originally announced March 2026.

Comments: 22 pages, 17 figures

Journal ref: Phys. Rev. A 114, 013318 (2026)

AXE: Grey-Box Exploitability Confirmation for Localized Vulnerability Reports

Authors: Amirali Sajadi, Tu Nguyen, Kostadin Damevski, Preetha Chatterjee

Abstract: Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing approaches typically operate in isolation from detection pipelines, failing to leverage readily available metadata such as vulnerability type and source-code loc… ▽ More Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing approaches typically operate in isolation from detection pipelines, failing to leverage readily available metadata such as vulnerability type and source-code location. In this paper, we investigate how reported security vulnerabilities can be assessed in a realistic grey-box exploitation setting that leverages minimal vulnerability metadata, specifically a CWE classification and a vulnerable code location. We introduce Agentic eXploit Engine (AXE), a multi-agent framework for Web application exploitation that maps lightweight detection metadata to concrete exploits through decoupled planning, code exploration, and dynamic execution feedback. Evaluated on the CVE-Bench dataset, AXE achieves a 30% exploitation success rate, a 3x improvement over state-of-the-art black-box baselines. Even in a single-agent configuration, grey-box metadata yields a 1.75x performance gain. Systematic error analysis shows that most failed attempts arise from specific reasoning gaps, including misinterpreted vulnerability semantics and unmet execution preconditions. For successful exploits, AXE produces actionable, reproducible proof-of-concept artifacts, demonstrating its utility in streamlining Web vulnerability triage and remediation. We further evaluate AXE's generalizability through a case study on a recent real-world vulnerability not included in CVE-Bench. △ Less

Submitted 20 June, 2026; v1 submitted 15 February, 2026; originally announced February 2026.

Minimal-Action Discrete Schrödinger Bridge Matching for Peptide Sequence Design

Authors: Shrey Goel, Pranam Chatterjee

Abstract: Generative modeling of peptide sequences requires navigating a discrete and highly constrained space in which many intermediate states are chemically implausible or unstable. Existing discrete diffusion and flow-based methods rely on reversing fixed corruption processes or following prescribed probability paths, which can force generation through low-likelihood regions and require countless sampli… ▽ More Generative modeling of peptide sequences requires navigating a discrete and highly constrained space in which many intermediate states are chemically implausible or unstable. Existing discrete diffusion and flow-based methods rely on reversing fixed corruption processes or following prescribed probability paths, which can force generation through low-likelihood regions and require countless sampling steps. We introduce Minimal-action discrete Schrödinger Bridge Matching (MadSBM), a rate-based generative framework for peptide design that formulates generation as a controlled continuous-time Markov process on the amino-acid edit graph. To yield probability trajectories that remain near high-likelihood sequence neighborhoods throughout generation, MadSBM 1) defines generation relative to a biologically informed reference process derived from pre-trained protein language model logits and 2) learns a time-dependent control field that biases transition rates to produce low-action transport paths from a masked prior to the data distribution. We finally introduce guidance to the MadSBM sampling procedure towards a specific functional objective, expanding the design space of therapeutic peptides; to our knowledge, this represents the first-ever application of discrete classifier guidance to Schrödinger bridge-based generative models. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Towards A Sustainable Future for Peer Review in Software Engineering

Authors: Esteban Parra, Sonia Haiduc, Preetha Chatterjee, Ramtin Ehsani, Polina Iaremchuk

Abstract: Peer review is the main mechanism by which the software engineering community assesses the quality of scientific results. However, the rapid growth of paper submissions in software engineering venues has outpaced the availability of qualified reviewers, creating a growing imbalance that risks constraining and negatively impacting the long-term growth of the Software Engineering (SE) research commu… ▽ More Peer review is the main mechanism by which the software engineering community assesses the quality of scientific results. However, the rapid growth of paper submissions in software engineering venues has outpaced the availability of qualified reviewers, creating a growing imbalance that risks constraining and negatively impacting the long-term growth of the Software Engineering (SE) research community. Our vision of the Future of the SE research landscape involves a more scalable, inclusive, and resilient peer review process that incorporates additional mechanisms for: 1) attracting and training newcomers to serve as high-quality reviewers, 2) incentivizing more community members to serve as peer reviewers, and 3) cautiously integrating AI tools to support a high-quality review process. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: Accepted at the 48th International Conference on Software Engineering, Future of Software Engineering (ICSE 2026-FoSE)

Emergent Nodal Spheres and Weyl Fermions via Spin-Texture Coupled to Thin Film Orbital Dirac Semimetals

Authors: Pritam Chatterjee, Anirudha Menon

Abstract: We consider the minimal coupling of a thin film Dirac semimetal Hamiltonian to a generic spin-texture. A simple unitary transformation gauges away the spatial dependence in the exchange term, leading to the generation of effective corrections to the Dirac dispersion. A full function's worth of freedom is obtained as a result. Choosing different pitch vectors, we show that many novel phenomena aris… ▽ More We consider the minimal coupling of a thin film Dirac semimetal Hamiltonian to a generic spin-texture. A simple unitary transformation gauges away the spatial dependence in the exchange term, leading to the generation of effective corrections to the Dirac dispersion. A full function's worth of freedom is obtained as a result. Choosing different pitch vectors, we show that many novel phenomena arise in such systems. For example, a linear pitch vector leads to the generation of a Weyl semimetal -- we observe the anomalous Hall effect and the chiral magnetic effect. The anomalous Hall coefficient requires a non-zero pitch vector whereas the CME is proportional to the exchange coupling. The band structure of the model in the presence of a magnetic field shows a Lifshitz-like transition driven by the exchange coupling. The introduction of a suitable time-dependent pitch vector leads, at the level of the leading-order Floquet effective Hamiltonian, to the emergence of a nodal sphere in momentum space. We further show that, in the full driven problem, a closed quasienergy degeneracy structure persists, continuously connected to this nodal sphere, and constrained by the operator algebra of the Floquet expansion. △ Less

Submitted 27 April, 2026; v1 submitted 24 January, 2026; originally announced January 2026.

Comments: 8 pages, 6 figures

Explicit inversion of spherical Radon transforms in odd dimensions with partial radial data

Authors: Pradipta Chatterjee, Venkateswaran P. Krishnan, Abhilash Tushir

Abstract: We derive an explicit inversion algorithm for the spherical Radon transform in odd dimensions with partial radial data. We prove that the reconstruction of the unknown function can be reduced to solving ordinary differential equations, thereby providing a more explicit approach in odd dimensions than solving Volterra integral equation of the first kind established in prior works. We also provide a… ▽ More We derive an explicit inversion algorithm for the spherical Radon transform in odd dimensions with partial radial data. We prove that the reconstruction of the unknown function can be reduced to solving ordinary differential equations, thereby providing a more explicit approach in odd dimensions than solving Volterra integral equation of the first kind established in prior works. We also provide analytical solutions in some special cases. Finally, we present numerical simulations validating our theoretical results. Our work answers a question posed by Rubin in ``Inversion formulae for the spherical mean in odd dimensions and the Euler-Poisson-Darboux equation,'' Inverse Problems 24 (2008), no. 2, 025021, 10 pp. △ Less

Submitted 24 January, 2026; originally announced January 2026.

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Authors: Ramtin Ehsani, Sakshi Pathak, Shriya Rawal, Abdullah Al Mujahid, Mia Mohammad Imran, Preetha Chatterjee

Abstract: AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why many of them fail to be merged. In this paper, we conduct a large-scale study of 33k agent-authored PRs made by five codin… ▽ More AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why many of them fail to be merged. In this paper, we conduct a large-scale study of 33k agent-authored PRs made by five coding agents across GitHub. (RQ1) We first quantitatively characterize merged and not-merged PRs along four broad dimensions: 1) merge outcomes across task types, 2) code changes, 3) CI build results, and 4) review dynamics. We observe that tasks related to documentation, CI, and build update achieve the highest merge success, whereas performance and bug-fix tasks perform the worst. Not-merged PRs tend to involve larger code changes, touch more files, and often do not pass the project's CI/CD pipeline validation. (RQ2) To further investigate why some agentic PRs are not merged, we qualitatively analyze 600 PRs to derive a hierarchical taxonomy of rejection patterns. This analysis complements the quantitative findings in RQ1 by uncovering rejection reasons not captured by quantitative metrics, including lack of meaningful reviewer engagement, duplicate PRs, unwanted feature implementations, and agent misalignment. Together, our findings highlight key socio-technical and human-AI collaboration factors that are critical to improving the success of future agentic workflows. △ Less

Submitted 21 January, 2026; originally announced January 2026.

Comments: Accepted at International Mining Software Repositories Conference (MSR 2026)

Exact solution of the (2+1)-dimensional damping forcing coupled Burgers equation by using Darboux transformation

Authors: Prasanta Chatterjee, Nanda Kanan Pal, Dipan Saha, Santanu Raut

Abstract: In this article, we investigate the (2+1)-dimensional damping forcing coupled Burgers equation, which is obtain by adding damping and forcing terms from couple Burgers equation. The Lax pair of the (2+1)-dimensional damping forcing coupled Burgers equation is established. With the help of Lax pair, we derive the $N$-fold Darboux transformation of (2+1)-dimensional damping forcing coupled Burgers e… ▽ More In this article, we investigate the (2+1)-dimensional damping forcing coupled Burgers equation, which is obtain by adding damping and forcing terms from couple Burgers equation. The Lax pair of the (2+1)-dimensional damping forcing coupled Burgers equation is established. With the help of Lax pair, we derive the $N$-fold Darboux transformation of (2+1)-dimensional damping forcing coupled Burgers equation. Using one fold and two fold Darboux transformation, we demonstrated some wave solutions including solitary wave solution and periodic wave solution. The impact of damping and forcing terms in solitary wave solution and periodic solution is graphically demonstrated. △ Less

Submitted 20 January, 2026; originally announced January 2026.

Comments: 7pages, No figure

Towards Airborne Object Detection: A Deep Learning Analysis

Authors: Prosenjit Chatterjee, ANK Zaman

Abstract: The rapid proliferation of airborne platforms, including commercial aircraft, drones, and UAVs, has intensified the need for real-time, automated threat assessment systems. Current approaches depend heavily on manual monitoring, resulting in limited scalability and operational inefficiencies. This work introduces a dual-task model based on EfficientNetB4 capable of performing airborne object class… ▽ More The rapid proliferation of airborne platforms, including commercial aircraft, drones, and UAVs, has intensified the need for real-time, automated threat assessment systems. Current approaches depend heavily on manual monitoring, resulting in limited scalability and operational inefficiencies. This work introduces a dual-task model based on EfficientNetB4 capable of performing airborne object classification and threat-level prediction simultaneously. To address the scarcity of clean, balanced training data, we constructed the AODTA Dataset by aggregating and refining multiple public sources. We benchmarked our approach on both the AVD Dataset and the newly developed AODTA Dataset and further compared performance against a ResNet-50 baseline, which consistently underperformed EfficientNetB4. Our EfficientNetB4 model achieved 96% accuracy in object classification and 90% accuracy in threat-level prediction, underscoring its promise for applications in surveillance, defense, and airspace management. Although the title references detection, this study focuses specifically on classification and threat-level inference using pre-localized airborne object images provided by existing datasets. △ Less

Submitted 16 January, 2026; originally announced January 2026.

Toxicity Ahead: Forecasting Conversational Derailment on GitHub

Authors: Mia Mohammad Imran, Robert Zita, Rahat Rizvi Rahman, Preetha Chatterjee, Kostadin Damevski

Abstract: Toxic interactions in Open Source Software (OSS) communities reduce contributor engagement and threaten project sustainability. Preventing such toxicity before it emerges requires a clear understanding of how harmful conversations unfold. However, most proactive moderation strategies are manual, requiring significant time and effort from community maintainers. To support more scalable approaches,… ▽ More Toxic interactions in Open Source Software (OSS) communities reduce contributor engagement and threaten project sustainability. Preventing such toxicity before it emerges requires a clear understanding of how harmful conversations unfold. However, most proactive moderation strategies are manual, requiring significant time and effort from community maintainers. To support more scalable approaches, we curate a dataset of 159 derailed toxic threads and 207 non-toxic threads from GitHub discussions. Our analysis reveals that toxicity can be forecast by tension triggers, sentiment shifts, and specific conversational patterns. We present a novel Large Language Model (LLM)-based framework for predicting conversational derailment on GitHub using a two-step prompting pipeline. First, we generate \textit{Summaries of Conversation Dynamics} (SCDs) via Least-to-Most (LtM) prompting; then we use these summaries to estimate the \textit{likelihood of derailment}. Evaluated on Qwen and Llama models, our LtM strategy achieves F1-scores of 0.901 and 0.852, respectively, at a decision threshold of 0.3, outperforming established NLP baselines on conversation derailment. External validation on a dataset of 308 GitHub issue threads (65 toxic, 243 non-toxic) yields an F1-score up to 0.797. Our findings demonstrate the effectiveness of structured LLM prompting for early detection of conversational derailment in OSS, enabling proactive and explainable moderation. △ Less

Submitted 16 December, 2025; originally announced December 2025.

Journal ref: ICSE 2026

Remembrance of Tasks Past in Tunable Physical Networks

Authors: Purba Chatterjee, Marcelo Guzman, Andrea J. Liu

Abstract: Sequential learning in physical networks is hindered by catastrophic forgetting, where training a new task erases solutions to earlier ones. We show that we can significantly enhance memory of previous tasks by introducing a hard threshold in the learning rule, allowing only edges with sufficiently large training signals to be altered. Thresholding confines tuning to the spatial vicinity of inputs… ▽ More Sequential learning in physical networks is hindered by catastrophic forgetting, where training a new task erases solutions to earlier ones. We show that we can significantly enhance memory of previous tasks by introducing a hard threshold in the learning rule, allowing only edges with sufficiently large training signals to be altered. Thresholding confines tuning to the spatial vicinity of inputs and outputs for each task, effectively partitioning the network into weakly overlapping functional regions. Using simulations of tunable resistor networks, we demonstrate that this strategy enables robust memory of multiple sequential tasks while reducing the number of edges and the overall tuning cost. Our results hint at constrained training as a simple, local, and scalable mechanism to overcome catastrophic forgetting in tunable matter. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Real-Time Drivers' Drowsiness Detection and Analysis through Deep Learning

Authors: ANK Zaman, Prosenjit Chatterjee, Rajat Sharma

Abstract: A long road trip is fun for drivers. However, a long drive for days can be tedious for a driver to accommodate stringent deadlines to reach distant destinations. Such a scenario forces drivers to drive extra miles, utilizing extra hours daily without sufficient rest and breaks. Once a driver undergoes such a scenario, it occasionally triggers drowsiness during driving. Drowsiness in driving can be… ▽ More A long road trip is fun for drivers. However, a long drive for days can be tedious for a driver to accommodate stringent deadlines to reach distant destinations. Such a scenario forces drivers to drive extra miles, utilizing extra hours daily without sufficient rest and breaks. Once a driver undergoes such a scenario, it occasionally triggers drowsiness during driving. Drowsiness in driving can be life-threatening to any individual and can affect other drivers' safety; therefore, a real-time detection system is needed. To identify fatigued facial characteristics in drivers and trigger the alarm immediately, this research develops a real-time driver drowsiness detection system utilizing deep convolutional neural networks (DCNNs) and OpenCV.Our proposed and implemented model takes real- time facial images of a driver using a live camera and utilizes a Python-based library named OpenCV to examine the facial images for facial landmarks like sufficient eye openings and yawn-like mouth movements. The DCNNs framework then gathers the data and utilizes a per-trained model to detect the drowsiness of a driver using facial landmarks. If the driver is identified as drowsy, the system issues a continuous alert in real time, embedded in the Smart Car technology.By potentially saving innocent lives on the roadways, the proposed technique offers a non-invasive, inexpensive, and cost-effective way to identify drowsiness. Our proposed and implemented DCNNs embedded drowsiness detection model successfully react with NTHU-DDD dataset and Yawn-Eye-Dataset with drowsiness detection classification accuracy of 99.6% and 97% respectively. △ Less

Submitted 15 November, 2025; originally announced November 2025.

Journal ref: 2024 2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings)

Entangled Schrödinger Bridge Matching

Authors: Sophia Tang, Yinuo Zhang, Pranam Chatterjee

Abstract: Simulating trajectories of multi-particle systems on complex energy landscapes is a central task in molecular dynamics (MD) and drug discovery, but remains challenging at scale due to computationally expensive and long simulations. Previous approaches leverage techniques such as flow or Schrödinger bridge matching to implicitly learn joint trajectories through data snapshots. However, many systems… ▽ More Simulating trajectories of multi-particle systems on complex energy landscapes is a central task in molecular dynamics (MD) and drug discovery, but remains challenging at scale due to computationally expensive and long simulations. Previous approaches leverage techniques such as flow or Schrödinger bridge matching to implicitly learn joint trajectories through data snapshots. However, many systems, including biomolecular systems and heterogeneous cell populations, undergo dynamic interactions that evolve over their trajectory and cannot be captured through static snapshots. To close this gap, we introduce Entangled Schrödinger Bridge Matching (EntangledSBM), a framework that learns the first- and second-order stochastic dynamics of interacting, multi-particle systems where the direction and magnitude of each particle's path depend dynamically on the paths of the other particles. We define the Entangled Schrödinger Bridge (EntangledSB) problem as solving a coupled system of bias forces that entangle particle velocities. We show that our framework accurately simulates heterogeneous cell populations under perturbations and rare transitions in high-dimensional biomolecular systems. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers

Authors: Parthiv Chatterjee, Shivam Sonawane, Amey Hengle, Aditya Tanna, Sourish Dasgupta, Tanmoy Chakraborty

Abstract: Document summarization enables efficient extraction of user-relevant content but is inherently shaped by individual subjectivity, making it challenging to identify subjective salient information in multifaceted documents. This complexity underscores the necessity for personalized summarization. However, training models for personalized summarization has so far been challenging, particularly becaus… ▽ More Document summarization enables efficient extraction of user-relevant content but is inherently shaped by individual subjectivity, making it challenging to identify subjective salient information in multifaceted documents. This complexity underscores the necessity for personalized summarization. However, training models for personalized summarization has so far been challenging, particularly because diverse training data containing both user preference history (i.e., click-skip trajectory) and expected (gold-reference) summaries are scarce. The MS/CAS PENS dataset is a valuable resource but includes only preference history without target summaries, preventing end-to-end supervised learning, and its limited topic-transition diversity further restricts generalization. To address this, we propose $\mathrm{PerAugy}$, a novel cross-trajectory shuffling and summary-content perturbation based data augmentation technique that significantly boosts the accuracy of four state-of-the-art baseline (SOTA) user-encoders commonly used in personalized summarization frameworks (best result: $\text{0.132}$$\uparrow$ w.r.t AUC). We select two such SOTA summarizer frameworks as baselines and observe that when augmented with their corresponding improved user-encoders, they consistently show an increase in personalization (avg. boost: $\text{61.2\%}\uparrow$ w.r.t. PSE-SU4 metric). As a post-hoc analysis of the role of induced diversity in the augmented dataset by \peraugy, we introduce three dataset diversity metrics -- $\mathrm{TP}$, $\mathrm{RTC}$, and \degreed\ to quantify the induced diversity. We find that $\mathrm{TP}$ and $\mathrm{DegreeD}$ strongly correlate with user-encoder performance on the PerAugy-generated dataset across all accuracy metrics, indicating that increased dataset diversity is a key factor driving performance gains. △ Less

Submitted 11 October, 2025; originally announced October 2025.

AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance

Authors: Tong Chen, Yinuo Zhang, Pranam Chatterjee

Abstract: Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce AReUReDi (Annealed Rectified Updates for Refining Discrete Flows)… ▽ More Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce AReUReDi (Annealed Rectified Updates for Refining Discrete Flows), a discrete optimization algorithm with theoretical guarantees of convergence to the Pareto front. Building on Rectified Discrete Flows (ReDi), AReUReDi combines Tchebycheff scalarization, locally balanced proposals, and annealed Metropolis-Hastings updates to bias sampling toward Pareto-optimal states while preserving distributional invariance. Applied to peptide and SMILES sequence design, AReUReDi simultaneously optimizes up to five therapeutic properties (including affinity, solubility, hemolysis, half-life, and non-fouling) and outperforms both evolutionary and diffusion-based baselines. These results establish AReUReDi as a powerful, sequence-based framework for multi-property biomolecule generation. △ Less

Submitted 2 October, 2025; v1 submitted 30 September, 2025; originally announced October 2025.

TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

Authors: Sophia Tang, Yuchen Zhu, Molei Tao, Pranam Chatterjee

Abstract: Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these approaches enable optimization without access to explicit samples from the optimal distribution, they require training on rollouts under the current fine-tuned model,… ▽ More Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these approaches enable optimization without access to explicit samples from the optimal distribution, they require training on rollouts under the current fine-tuned model, making them susceptible to reinforcing sub-optimal trajectories that yield poor rewards. To overcome this challenge, we introduce TRee Search Guided TRajectory-Aware Fine-Tuning for Discrete Diffusion (TR2-D2), a novel framework that optimizes reward-guided discrete diffusion trajectories with tree search to construct replay buffers for trajectory-aware fine-tuning. These buffers are generated using Monte Carlo Tree Search (MCTS) and subsequently used to fine-tune a pre-trained discrete diffusion model under a stochastic optimal control objective. We validate our framework on single- and multi-objective fine-tuning of biological sequence diffusion models, highlighting the overall effectiveness of TR2-D2 for reliable reward-guided fine-tuning in discrete sequence generation. △ Less

Submitted 29 September, 2025; originally announced September 2025.

Maternal Characteristics and Newborn Birth Weight: A Comprehensive Statistical Analysis

Authors: Prithwiraj Chatterjee, Abhinav Tanwar, Devadharshini Udayakumar

Abstract: This report presents a statistical analysis of the impact of key maternal characteristics, including age, smoking status, parity, height, weight, and gestation period, on newborn birth weight. A realworld dataset comprising 1,236 observations was utilized for this investigation. The methodology involved comprehensive data cleaning, exploratory data analysis (EDA), and a series of parametric statis… ▽ More This report presents a statistical analysis of the impact of key maternal characteristics, including age, smoking status, parity, height, weight, and gestation period, on newborn birth weight. A realworld dataset comprising 1,236 observations was utilized for this investigation. The methodology involved comprehensive data cleaning, exploratory data analysis (EDA), and a series of parametric statistical tests, specifically the One-Sample t-test, Two-Sample t-test, Chi-Square tests, and Analysis of Variance (ANOVA). All analyses were conducted within the SAS programming environment. The study's findings indicate a statistically significant negative impact of maternal smoking on birth weight, a finding consistent with broader public health literature. Gestation period emerged as the strongest positive predictor of birth weight within this dataset. While the analyses using broad categories of maternal age and parity did not reveal significant differences in mean birth weight, a review of existing literature suggests more intricate, potentially non-linear relationships and nuanced effects of these factors. Similarly, maternal pre-pregnancy weight, though showing a weak linear correlation in this dataset, is widely recognized as a critical determinant of birth weight outcomes, particularly at its extremes. These results emphasize the importance of targeted prenatal care interventions, especially those focused on smoking cessation. The study reinforces the utility of data-driven insights in informing public health policies aimed at improving maternal and child health outcomes. Future research should explore non-linear relationships and potential interactions among various maternal factors. △ Less

Submitted 30 August, 2025; originally announced September 2025.

VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation

Authors: Ayaan Nooruddin Siddiqui, Mahnoor Zaidi, Ayesha Nazneen Shahbaz, Priyadarshini Chatterjee, Krishnan Menon Iyer

Abstract: The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients and imaging modalities. In this work, we propose a novel weakly supervised training framework specifically designed for subcutaneous vessel segmentation. This met… ▽ More The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients and imaging modalities. In this work, we propose a novel weakly supervised training framework specifically designed for subcutaneous vessel segmentation. This method utilizes low-cost, sparse annotations such as centerline traces, dot markers, or short scribbles to guide the learning process. These sparse annotations are expanded into dense probabilistic supervision through a differentiable random walk label propagation model, which integrates vesselness cues and tubular continuity priors driven by image data. The label propagation process results in per-pixel hitting probabilities and uncertainty estimates, which are incorporated into an uncertainty-weighted loss function to prevent overfitting in ambiguous areas. Notably, the label propagation model is trained jointly with a CNN-based segmentation network, allowing the system to learn vessel boundaries and continuity constraints without the need for explicit edge supervision. Additionally, we introduce a topology-aware regularizer that encourages centerline connectivity and penalizes irrelevant branches, further enhancing clinical applicability. Our experiments on clinical subcutaneous imaging datasets demonstrate that our approach consistently outperforms both naive sparse-label training and traditional dense pseudo-labeling methods, yielding more accurate vascular maps and better-calibrated uncertainty, which is crucial for clinical decision-making. This method significantly reduces the annotation workload while maintaining clinically relevant vessel topology. △ Less

Submitted 7 May, 2026; v1 submitted 9 August, 2025; originally announced August 2025.

Comments: arXiv admin note: This submission has been withdrawn due to violation of arXiv policies for acceptable submissions

DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation

Authors: Vikram Singh, Kabir Malhotra, Rohan Desai, Ananya Shankaracharya, Priyadarshini Chatterjee, Krishnan Menon Iyer

Abstract: Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts (such as hairs, rulers, and bubbles), and a critical need for precise boundary localization to aid in accurate diagnosis. The accurate delineation of melanocytic tumors in dermoscopic images is a crucial component of automated skin cancer screening sy… ▽ More Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts (such as hairs, rulers, and bubbles), and a critical need for precise boundary localization to aid in accurate diagnosis. The accurate delineation of melanocytic tumors in dermoscopic images is a crucial component of automated skin cancer screening systems and clinical decision support. In this paper, we present a novel dual-resolution architecture inspired by ResNet, specifically tailored for the segmentation of melanocytic tumors. Our approach incorporates a high-resolution stream that preserves fine boundary details, alongside a complementary pooled stream that captures multi-scale contextual information for robust lesion recognition. These two streams are closely integrated through boundary-aware residual connections, which inject edge information into deep feature maps, and a channel attention mechanism that adapts the model's sensitivity to color and texture variations in dermoscopic images. To tackle common imaging artifacts and the challenges posed by small clinical datasets, we introduce a lightweight artifact suppression block and a multi-task training strategy. This strategy combines the Dice-Tversky loss with an explicit boundary loss and a contrastive regularizer to enhance feature stability. This unified design enables the model to generate pixel-accurate segmentation masks without the need for extensive post-processing or complex pre-training. Extensive evaluation on public dermoscopic benchmarks reveals that our method significantly enhances boundary precision and clinically relevant segmentation metrics, outperforming traditional encoder-decoder baselines. This makes our approach a valuable component for building automated melanoma assessment systems. △ Less

Submitted 7 May, 2026; v1 submitted 9 August, 2025; originally announced August 2025.

Comments: arXiv admin note: This submission has been withdrawn due to violation of arXiv policies for acceptable submissions

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models

Authors: Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee, Rima Hazra, Somak Aditya, Animesh Mukherjee

Abstract: Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar outcome-based reward models, parameter tuning, or heuristic decoding strategies, lack the granularity and proactive nature needed to reliably detect and intervene during s… ▽ More Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar outcome-based reward models, parameter tuning, or heuristic decoding strategies, lack the granularity and proactive nature needed to reliably detect and intervene during subtle yet crucial reasoning steps. Addressing this fundamental gap, we introduce AURA, an innovative, multi-layered framework centered around Process Reward Models (PRMs), providing comprehensive, step level evaluations across logical coherence and safety-awareness. Our framework seamlessly combines introspective self-critique, fine-grained PRM assessments, and adaptive safety-aware decoding to dynamically and proactively guide models toward safer reasoning trajectories. Empirical evidence clearly demonstrates that this approach significantly surpasses existing methods, significantly improving the logical integrity and affordance-sensitive safety of model outputs. This research represents a pivotal step toward safer, more responsible, and contextually aware AI, setting a new benchmark for alignment-sensitive applications. △ Less

Submitted 8 August, 2025; originally announced August 2025.

Fractal Dimension in Nonlinear Wave Dynamics Governed by a Nonlinear Partial Differential Equation

Authors: Saugata Dutta, Kajal Kumar Mondal, Prasanta Chatterjee

Abstract: This work presents a detailed analytical and geometrical investigation of the (2+1)-dimensional Boiti-Leon-Pempinelli system, a nonlinear dispersive model arising in the context of fluid and plasma dynamics. By employing a projective Riccati-based ansatz, a new class of exact solutions is systematically derived. These solutions, when visualized, exhibit intricate geometrical features that evolve a… ▽ More This work presents a detailed analytical and geometrical investigation of the (2+1)-dimensional Boiti-Leon-Pempinelli system, a nonlinear dispersive model arising in the context of fluid and plasma dynamics. By employing a projective Riccati-based ansatz, a new class of exact solutions is systematically derived. These solutions, when visualized, exhibit intricate geometrical features that evolve across multiple spatial scales. To quantify this complexity, a voxel-based box-counting dimension analysis is conducted on the corresponding surface profiles. The analysis reveals non-integer fractal dimensions that vary with magnification, confirming the self-affine nature of the patterns and highlighting the multiscale structure inherent in the system. Such fractal character is not only of theoretical interest but also reflects real-world behaviors in turbulent plasma flows and fine-scale fluid instabilities. The study thus bridges exact analytical solutions with computational fractal geometry, providing a deeper understanding of the BLP system and its relevance in describing natural phenomena characterized by spatial complexity and multiscale interactions. △ Less

Submitted 11 August, 2025; v1 submitted 3 August, 2025; originally announced August 2025.

Information and fitness in two-state systems: self-replicating individuals in a fluctuating environment

Authors: Poulami Chatterjee, Cesar Nieto, Juan Manuel Pedraza, Abhyudai Singh

Abstract: A population of individuals with the same genes can present heterogeneous traits (phenotypes). The prevalence of this heterogeneity can be explained as a bet-hedging strategy that improves the population proliferation rate (fitness) in fluctuating environments. The phenotype distribution is influenced by factors such as competition between phenotypes, the duration of environmental states, and the… ▽ More A population of individuals with the same genes can present heterogeneous traits (phenotypes). The prevalence of this heterogeneity can be explained as a bet-hedging strategy that improves the population proliferation rate (fitness) in fluctuating environments. The phenotype distribution is influenced by factors such as competition between phenotypes, the duration of environmental states, and the rate of phenotype-switching. We illustrate these effects in a system where both the environment and the phenotype can adopt two states. This system includes scenarios such as symmetric bet-hedging and dormant-proliferating phenotypes. We examine how environmental and phenotypic states share mutual information, measured in bits, and explore the relationship between this information and population fitness. We propose that when fitness is measured relative to the case where phenotype and environment are independent, information and fitness can be treated as equivalent measures. We investigate strategies that individuals can use to improve this information, such as adjusting the rates of proliferation and phenotype-switching relative to the environmental fluctuation rate. Through these strategies, with fixed marginal distributions, an increase in information implies an increase in population fitness. We also identify limits to the maximum achievable fitness and information and discuss the value of the information in terms of this new normalized fitness. Our framework offers new insights into how organisms adapt to fluctuating environmental conditions. △ Less

Submitted 31 July, 2025; originally announced August 2025.

Characterizing ion-acoustic shock wave collisions in Martian multicomponent plasma environments

Authors: Jayshree Mondal, Prasanta Chatterjee, Laxmikanta Mandi, Biswajit Sahu

Abstract: We present theoretical investigation of colliding ion-acoustic (IA) shock waves in Martian multicomponent plasmas consisting of hydrogen ($H^+$), oxygen ($O^+$) and oxygen molecule ($O_2^+$) ions, including background superthermal electrons (modeled by a $κ$-(kappa) distribution function). A set of Burgers' equations is obtained by adopting a modified Poincaré-Lighthill-Kuo (PLK) perturbation meth… ▽ More We present theoretical investigation of colliding ion-acoustic (IA) shock waves in Martian multicomponent plasmas consisting of hydrogen ($H^+$), oxygen ($O^+$) and oxygen molecule ($O_2^+$) ions, including background superthermal electrons (modeled by a $κ$-(kappa) distribution function). A set of Burgers' equations is obtained by adopting a modified Poincaré-Lighthill-Kuo (PLK) perturbation method to describe the head-on-collision dynamics of dissipative nonlinear IA wave structures. We have estimated the spatio-temporal scales using parameters typically observed in the Martian atmosphere by the MAVEN spacecraft, for which shock waves are theoretically expected to undergo mutual collisions in the multicomponent plasma. The effects of head-on collisions on the electrostatic potential profiles arising from one-fold and two-fold IA shock interactions are explored. Our numerical analysis reveals that the collision leads to a noticeable broadening of the shock structures with the enhancement of kinematic viscosity. △ Less

Submitted 28 July, 2025; originally announced July 2025.

AI-Powered Commit Explorer (APCE)

Authors: Yousab Grees, Polina Iaremchuk, Ramtin Ehsani, Esteban Parra, Preetha Chatterjee, Sonia Haiduc

Abstract: Commit messages in a version control system provide valuable information for developers regarding code changes in software systems. Commit messages can be the only source of information left for future developers describing what was changed and why. However, writing high-quality commit messages is often neglected in practice. Large Language Model (LLM) generated commit messages have emerged as a w… ▽ More Commit messages in a version control system provide valuable information for developers regarding code changes in software systems. Commit messages can be the only source of information left for future developers describing what was changed and why. However, writing high-quality commit messages is often neglected in practice. Large Language Model (LLM) generated commit messages have emerged as a way to mitigate this issue. We introduce the AI-Powered Commit Explorer (APCE), a tool to support developers and researchers in the use and study of LLM-generated commit messages. APCE gives researchers the option to store different prompts for LLMs and provides an additional evaluation prompt that can further enhance the commit message provided by LLMs. APCE also provides researchers with a straightforward mechanism for automated and human evaluation of LLM-generated messages. Demo link https://youtu.be/zYrJ9s6sZvo △ Less

Submitted 21 July, 2025; originally announced July 2025.

Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning

Authors: Prateek Chanda, Saral Sureka, Parth Pratim Chatterjee, Krishnateja Killamsetty, Nikhil Shivakumar Nayak, Ganesh Ramakrishnan

Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks. In practice, mixtures are often fixed using simple heuristics (e.g., uniform or size-proportional sampling) that ignore task interactions, which can hurt transfer and waste budget on redundant sources. We introduce TaskPGM, a framework for learnin… ▽ More Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks. In practice, mixtures are often fixed using simple heuristics (e.g., uniform or size-proportional sampling) that ignore task interactions, which can hurt transfer and waste budget on redundant sources. We introduce TaskPGM, a framework for learning continuous task mixtures via an energy-based model over tasks. Tasks form the nodes of a Markov random field: unary potentials capture per-task utility, and pairwise potentials encode inter-task relationships using behavioral divergences computed from predictive distributions of single-task fine-tuned models (e.g., Jensen--Shannon divergence and pointwise mutual information). Optimizing this objective yields mixtures that balance coverage against redundancy. We show that the resulting set function is weakly submodular under budget constraints, enabling approximation guarantees for discrete selection variants. Across multiple model families (LLaMA-7B, Qwen2-7B) and evaluation suites (BIG-Bench Hard), TaskPGM improves over standard mixing strategies and provides interpretable structure over task interactions. △ Less

Submitted 5 June, 2026; v1 submitted 16 July, 2025; originally announced July 2025.

Comments: 9, 8 tables, 7 figures

MSC Class: 68T50 ACM Class: I.2.7; I.2.6; I.2.4

IPS Lower Bounds for Formulas and Sum of ROABPs

Authors: Prerona Chatterjee, Utsab Ghosal, Partha Mukhopadhyay, Amit Sinhababu

Abstract: We give new lower bounds for the fragments of the Ideal Proof System (IPS) introduced by Grochow and Pitassi (JACM 2018). The Ideal Proof System is a central topic in algebraic proof complexity developed in the context of Nullstellensatz refutation (Beame, Impagliazzo, Krajicek, Pitassi, Pudlak, FOCS 1994) and simulates Extended Frege efficiently. Our main results are as follows. 1. mult-IPS_{Li… ▽ More We give new lower bounds for the fragments of the Ideal Proof System (IPS) introduced by Grochow and Pitassi (JACM 2018). The Ideal Proof System is a central topic in algebraic proof complexity developed in the context of Nullstellensatz refutation (Beame, Impagliazzo, Krajicek, Pitassi, Pudlak, FOCS 1994) and simulates Extended Frege efficiently. Our main results are as follows. 1. mult-IPS_{Lin'}: We prove nearly quadratic-size formula lower bound for multilinear refutation (over the Boolean hypercube) of a variant of the subset-sum axiom polynomial. Extending this, we obtain a nearly matching qualitative statement for a constant degree target polynomial. 2. IPS_{Lin'}: Over the fields of characteristic zero, we prove exponential-size sum-of-ROABPs lower bound for the refutation of a variant of the subset-sum axiom polynomial. The result also extends over the fields of positive characteristics when the target polynomial is suitably modified. The modification is inspired by the recent results (Hakoniemi, Limaye, Tzameret, STOC 2024 and Behera, Limaye, Ramanathan, Srinivasan, ICALP 2025). The mult-IPS_{Lin'} lower bound result is obtained by combining the quadratic-size formula lower bound technique of Kalorkoti (SICOMP 1985) with some additional ideas. The proof technique of IPS_{Lin'} lower bound result is inspired by the recent lower bound result of Chatterjee, Kush, Saraf and Shpilka (CCC 2024). △ Less

Submitted 5 October, 2025; v1 submitted 13 July, 2025; originally announced July 2025.

Comments: Accepted to FSTTCS 2025

How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench

Authors: Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee

Abstract: Large language models (LLMs) and their agentic frameworks are increasingly adopted to perform development tasks such as automated program repair (APR). While prior work has identified security risks in LLM-generated code, most have focused on synthetic, simplified, or isolated tasks that lack the complexity of real-world program repair. In this study, we present the first large-scale security anal… ▽ More Large language models (LLMs) and their agentic frameworks are increasingly adopted to perform development tasks such as automated program repair (APR). While prior work has identified security risks in LLM-generated code, most have focused on synthetic, simplified, or isolated tasks that lack the complexity of real-world program repair. In this study, we present the first large-scale security analysis of LLM-generated patches using 20,000+ GitHub issues. We evaluate patches proposed by developers, a standalone LLM (Llama 3.3 Instruct-70B), and three top-performing agentic frameworks (OpenHands, AutoCodeRover, HoneyComb). Finally, we analyze a wide range of code, issue, and project-level factors to understand the conditions under which generating insecure patches is more likely. Our findings reveal that Llama introduces many new vulnerabilities, exhibiting unique patterns not found in developers' code. Agentic workflows also generate a number of vulnerabilities, particularly when given more autonomy. We find that vulnerabilities in LLM-generated patches are associated with distinctive code characteristics and are commonly observed in issues missing specific types of information. These results suggest that contextual factors play a critical role in the security of the generated patches and point toward the need for proactive risk assessment methods that account for both issue and code-level information. △ Less

Submitted 29 December, 2025; v1 submitted 30 June, 2025; originally announced July 2025.

Hierarchical Knowledge Injection for Improving LLM-based Program Repair

Authors: Ramtin Ehsani, Esteban Parra, Sonia Haiduc, Preetha Chatterjee

Abstract: Prompting LLMs with bug-related context (e.g., error messages, stack traces) improves automated program repair, but many bugs still remain unresolved. In real-world projects, developers often rely on broader repository and project-level context beyond the local code to resolve such bugs. In this paper, we investigate how automatically extracting and providing such knowledge can improve LLM-based p… ▽ More Prompting LLMs with bug-related context (e.g., error messages, stack traces) improves automated program repair, but many bugs still remain unresolved. In real-world projects, developers often rely on broader repository and project-level context beyond the local code to resolve such bugs. In this paper, we investigate how automatically extracting and providing such knowledge can improve LLM-based program repair. We propose a layered knowledge injection framework that incrementally augments LLMs with structured context. It starts with the Bug Knowledge Layer, which includes information such as the buggy function and failing tests; expands to the Repository Knowledge Layer, which adds structural dependencies, related files, and commit history; and finally injects the Project Knowledge Layer, which incorporates relevant details from documentation and previously fixed bugs. We evaluate this framework on a dataset of 314 bugs from BugsInPy using two LLMs (Llama 3.3 and GPT-4o-mini), and analyze fix rates across six bug types. By progressively injecting knowledge across layers, our approach achieves a fix rate of 79% (250/314) using Llama 3.3, a significant improvement of 23% over previous work. All bug types show improvement with the addition of repository-level context, while only a subset benefit further from project-level knowledge, highlighting that different bug types require different levels of contextual information for effective repair. We also analyze the remaining unresolved bugs and find that more complex and structurally isolated bugs, such as Program Anomaly and GUI bugs, remain difficult even after injecting all available information. Our results show that layered context injection improves program repair and suggest the need for interactive and adaptive APR systems. △ Less

Submitted 3 October, 2025; v1 submitted 30 June, 2025; originally announced June 2025.

Comments: Accepted at IEEE/ACM Automated Software Engineering (ASE) 2025 Conference

Journal ref: Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2025, pp. 1440-1452

What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues

Authors: Ramtin Ehsani, Sakshi Pathak, Esteban Parra, Sonia Haiduc, Preetha Chatterjee

Abstract: Conversational large-language models are extensively used for issue resolution tasks. However, not all developer-LLM conversations are useful for effective issue resolution. In this paper, we analyze 686 developer-ChatGPT conversations shared within GitHub issue threads to identify characteristics that make these conversations effective for issue resolution. First, we analyze the conversations and… ▽ More Conversational large-language models are extensively used for issue resolution tasks. However, not all developer-LLM conversations are useful for effective issue resolution. In this paper, we analyze 686 developer-ChatGPT conversations shared within GitHub issue threads to identify characteristics that make these conversations effective for issue resolution. First, we analyze the conversations and their corresponding issues to distinguish helpful from unhelpful conversations. We begin by categorizing the types of tasks developers seek help with to better understand the scenarios in which ChatGPT is most effective. Next, we examine a wide range of conversational, project, and issue-related metrics to uncover factors associated with helpful conversations. Finally, we identify common deficiencies in unhelpful ChatGPT responses to highlight areas that could inform the design of more effective developer-facing tools. We found that only 62% of the ChatGPT conversations were helpful for successful issue resolution. ChatGPT is most effective for code generation and tools/libraries/APIs recommendations, but struggles with code explanations. Helpful conversations tend to be shorter, more readable, and exhibit stronger semantic and linguistic alignment. Larger, more popular projects and more experienced developers benefit more from ChatGPT. At the issue level, ChatGPT performs best on simpler problems with limited developer activity and faster resolution, typically well-scoped tasks like compilation errors. The most common deficiencies in unhelpful ChatGPT responses include incorrect information and lack of comprehensiveness. Our findings have wide implications including guiding developers on effective interaction strategies for issue resolution, informing the development of tools or frameworks to support optimal prompt design, and providing insights on fine-tuning LLMs for issue resolution tasks. △ Less

Submitted 29 September, 2025; v1 submitted 27 June, 2025; originally announced June 2025.

Comments: Accepted for publication in Empirical Software Engineering (EMSE), 2025

Journal ref: Empirical Software Engineering, 31, 22 (2026)