arXiv subjects

Janardan Misra

Publications and source records attributed to Janardan Misra.

At least 19 recordsLinked to original sources

arXiv2026

Rethinking Build vs. Buy Decisions in Enterprise Software: Navigating Trade-offs through a Structured Decision-Support Approach

Build-versus-buy decisions remain a persistent challenge in enterprise software development, shaped by competing strategic, technical, cost, and risk considerations. The increasing availability of third-party solutions alongside the growing feasibility of custom development through cloud-native technologies, APIs, and low-code platforms has further amplified the complexity of these decisions. In practice, organizations often rely on fragmented expertise and informal reasoning, making it difficult to systematically analyze trade-offs or justify decisions over time. This paper presents a structured decision-support approach designed to augment build-versus-buy decision-making in such contexts. The approach is grounded in an ontology of decision factors spanning strategic considerations, application characteristics, cost and budget constraints, and risk dimensions. It combines this factor model with rule-based reasoning and reference-level matching to support decision-making even in cold-start scenarios where historical data is unavailable. The approach is implemented as a lightweight advisory artifact that enables users to evaluate relevant factors, explore trade-offs, and derive recommendations with transparent reasoning. The applicability of the approach is illustrated through a finance domain case, demonstrating how structured factor analysis can clarify decision rationale and highlight conditions under which decisions may change over time. The results suggest that making decision criteria explicit and systematically comparable can improve the quality, transparency, and auditability of build-versus-buy decisions in enterprise settings.

cs.SE↗

arXiv2026

Benchmarking the Energy Savings with Speculative Decoding Strategies

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors -- model size and family, speculative decoding strategies, and dataset characteristics -- influence the energy optimizations.

cs.LG↗

arXiv2025

Brevity is the soul of sustainability: Characterizing LLM response lengths

A significant portion of the energy consumed by Large Language Models (LLMs) arises from their inference processes; hence developing energy-efficient methods for inference is crucial. While several techniques exist for inference optimization, output compression remains relatively unexplored, with only a few preliminary efforts addressing this aspect. In this work, we first benchmark 12 decoder-only LLMs across 5 datasets, revealing that these models often produce responses that are substantially longer than necessary. We then conduct a comprehensive quality assessment of LLM responses, formally defining six information categories present in LLM responses. We show that LLMs often tend to include redundant or additional information besides the minimal answer. To address this issue of long responses by LLMs, we explore several simple and intuitive prompt-engineering strategies. Empirical evaluation shows that appropriate prompts targeting length reduction and controlling information content can achieve significant energy optimization between 25-60\% by reducing the response length while preserving the quality of LLM responses.

cs.CL↗

arXiv2025

Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models

Large language models (LLMs) are increasingly recognized for their exceptional generative capabilities and versatility across various tasks. However, the high inference costs associated with these models have not received adequate attention, particularly when compared to the focus on training costs in existing research. In response to this gap, our study conducts a comprehensive benchmarking of LLM inference energy across a wide range of NLP tasks, where we analyze the impact of different models, tasks, prompts, and system-related factors on inference energy. Specifically, our experiments reveal several interesting insights, including strong correlation of inference energy with output token length and response time. Also, we find that quantization and optimal batch sizes, along with targeted prompt phrases, can significantly reduce energy usage. This study is the first to thoroughly benchmark LLM inference across such a diverse range of aspects, providing insights and offering several recommendations for improving energy efficiency in model deployment.

cs.CL↗

arXiv2021

Winds of Change: Impact of COVID-19 on Vaccine-related Opinions of Twitter users

Administering COVID-19 vaccines at a societal scale has been deemed as the most appropriate way to defend against the COVID-19 pandemic. This global vaccination drive naturally fueled a possibility of Pro-Vaxxers and Anti-Vaxxers strongly expressing their supports and concerns regarding the vaccines on social media platforms. Understanding this online discourse is crucial for policy makers. This understanding is likely to impact the success of vaccination drives and might even impact the final outcome of our fight against the pandemic. The goal of this work is to improve this understanding using the lens of Twitter-discourse data. We first develop a classifier that categorizes users according to their vaccine-related stance with high precision (97%). Using this method we detect and investigate specific user-groups who posted about vaccines in pre-COVID and COVID times. Specifically, we identify distinct topics that these users talk about, and investigate how vaccine-related discourse has changed between pre-COVID times and COVID times. Finally, for the first time, we investigate the change of vaccine-related stances in Twitter users and shed light on potential reasons for such changes in stance. Our dataset and classifier are available at https://github.com/sohampoddar26/covid-vax-stance.

cs.SI↗

arXiv2021

When to Build Quantum Software?

Despite ongoing advancements in quantum computing, businesses are still faced with the problem to decide if they would benefit from investing into this novel technology for building a business critical application. This uncertainty is not only owing to the limitations in the current state of the technology but also due to the gap between the level at which business applications are analyzed (e.g., using high level semi-formal languages) and the level at which quantum computing related information is currently available (e.g., formally specified computational problems, their algorithmic solutions with computational complexity theoretic analysis) to make informed decisions. To fill the discourse gap, in this paper, we present design of an interactive advisor, which augments users while deciding to invest into quantum software development as a plausible future option in their application context. Towards that we apply business process modeling and natural language similarity analysis using text-embeddings to associated business context with computational problems and formulate constraints in terms of quantum speedup and resource requirements to select software development platforms.

cs.SE↗

arXiv2020

autoNLP: NLP Feature Recommendations for Text Analytics Applications

While designing machine learning based text analytics applications, often, NLP data scientists manually determine which NLP features to use based upon their knowledge and experience with related problems. This results in increased efforts during feature engineering process and renders automated reuse of features across semantically related applications inherently difficult. In this paper, we argue for standardization in feature specification by outlining structure of a language for specifying NLP features and present an approach for their reuse across applications to increase likelihood of identifying optimal features.

cs.CL↗

arXiv2018

Java Source-code Clustering: Unifying Syntactic and Semantic Features

This is a companion draft to paper 'Software Clustering: Unifying Syntactic and Semantic Features', in proceedings of the 19th Working Conference on Reverse Engineering (WCRE 2012). It discusses the clustering process in detail, which appeared in the paper in an abridged form. It also contains certain additional process steps which were not covered in the WCRE paper. The clustering process is described for applications with Java source-code. However, as argued in the WCRE paper, it can be seamlessly adapted to many other programming paradigms.

cs.SE↗

arXiv2018

Computational Complexity of Observing Evolution in Artificial-Life Forms

Observations are an essential component of the simulation based studies on artificial-evolutionary systems (AES) by which entities are identified and their behavior is observed to uncover higher-level "emergent" phenomena. Because of the heterogeneity of AES models and implicit nature of observations, precise characterization of the observation process, independent of the underlying micro-level reaction semantics of the model, is a difficult problem. Building upon the multiset based algebraic framework to characterize state-space trajectory of AES model simulations, we estimate bounds on computational resource requirements of the process of automatically discovering life-like evolutionary behavior in AES models during simulations. For illustration, we consider the case of Langton's Cellular Automata model and characterize the worst case computational complexity bounds for identifying entity and population level reproduction.

cs.NE↗

arXiv2018

A Note on Digitization of Real-Time Models and Logics

Digitization provides a sound and complete method to reduce the problem of verifying whether a real-time system satisfies a property under dense-time semantics to whether the same real-time system satisfies the property over discrete-time. This is a brief overview of digitization of real-time models and logics covering known results, value, limitations, and alternatives.

cs.LO↗

arXiv2018

An Inductive Formalization of Self Reproduction in Dynamical Hierarchies

Formalizing self reproduction in dynamical hierarchies is one of the important problems in Artificial Life (AL) studies. We study, in this paper, an inductively defined algebraic framework for self reproduction on macroscopic organizational levels under dynamical system setting for simulated AL models and explore some existential results. Starting with defining self reproduction for atomic entities we define self reproduction with possible mutations on higher organizational levels in terms of hierarchical sets and the corresponding inductively defined `meta' - reactions. We introduce constraints to distinguish a collection of entities from genuine cases of emergent organizational structures.

cs.AI↗

arXiv2018

A Recursive PLS (Partial Least Squares) based Approach for Enterprise Threat Management

Most of the existing solutions to enterprise threat management are preventive approaches prescribing means to prevent policy violations with varying degrees of success. In this paper we consider the complementary scenario where a number of security violations have already occurred, or security threats, or vulnerabilities have been reported and a security administrator needs to generate optimal response to these security events. We present a principled approach to study and model the human expertise in responding to the emergent threats owing to these security events. A recursive Partial Least Squares based adaptive learning model is defined using a factorial analysis of the security events together with a method for estimating the effect of global context dependent semantic information used by the security administrators. Presented model is theoretically optimal and operationally recursive in nature to deal with the set of security events being generated continuously. We discuss the underlying challenges and ways in which the model could be operationalized in centralized versus decentralized, and real-time versus batch processing modes.

cs.CR↗

arXiv2018

Data-Driven Application Maintenance: Views from the Trenches

In this paper we present our experience during design, development, and pilot deployments of a data-driven machine learning based application maintenance solution. We implemented a proof of concept to address a spectrum of interrelated problems encountered in application maintenance projects including duplicate incident ticket identification, assignee recommendation, theme mining, and mapping of incidents to business processes. In the context of IT services, these problems are frequently encountered, yet there is a gap in bringing automation and optimization. Despite long-standing research around mining and analysis of software repositories, such research outputs are not adopted well in practice due to the constraints these solutions impose on the users. We discuss need for designing pragmatic solutions with low barriers to adoption and addressing right level of complexity of problems with respect to underlying business constraints and nature of data.

cs.SE↗

arXiv2016

Designing Intelligent Automation based Solutions for Complex Social Problems

Deciding effective and timely preventive measures against complex social problems affecting relatively low income geographies is a difficult challenge. There is a strong need to adopt intelligent automation based solutions with low cost imprints to tackle these problems at larger scales. Starting with the hypothesis that analytical modelling and analysis of social phenomena with high accuracy is in general inherently hard, in this paper we propose design framework to enable data-driven machine learning based adaptive solution approach towards enabling more effective preventive measures. We use survey data collected from a socio-economically backward region of India about adolescent girls to illustrate the design approach.

stat.ML↗

arXiv2010

A Decidable Timeout based Extension of Propositional Linear Temporal Logic

We develop a timeout based extension of propositional linear temporal logic (which we call TLTL) to specify timing properties of timeout based models of real time systems. TLTL formulas explicitly refer to a running global clock together with static timing variables as well as a dynamic variable abstracting the timeout behavior. We extend LTL with the capability to express timeout constraints. From the expressiveness view point, TLTL is not comparable with important known clock based real-time logics including TPTL, XCTL, and MTL, i.e., TLTL can specify certain properties, which cannot be specified in these logics (also vice-versa). We define a corresponding timeout tableau for satisfiability checking of the TLTL formulas. Also a model checking algorithm over timeout Kripke structure is presented. Further we prove that the validity checking for such an extended logic remains PSPACE-complete even in the presence of timeout constraints and infinite state models. Under discrete time semantics, with bounded timeout increments, the model-checking problem that if a TLTL-formula holds in a timeout Kripke structure is also PSPACE complete. We further prove that when TLTL is interpreted over discrete time, it can be embedded in the monadic second order logic with time, and when TLTL is interpreted over dense time without the condition of non-zenoness, the resulting logic becomes $Σ_1^1$-complete.

cs.LO↗

arXiv2010

A Simplification of a Real-Time Verification Problem

We revisit the problem of real-time verification with dense dynamics using timeout and calendar based models and simplify this to a finite state verification problem. To overcome the complexity of verification of real-time systems with dense dynamics, Dutertre and Sorea, proposed timeout and calender based transition systems to model the behavior of real-time systems and verified safety properties using k-induction in association with bounded model checking. In this work, we introduce a specification formalism for these models in terms of Timeout Transition Diagrams and capture their behavior in terms of semantics of Timed Transition Systems. Further, we discuss a technique, which reduces the problem of verification of qualitative temporal properties on infinite state space of (a large fragment of) these timeout and calender based transition systems into that on clockless finite state models through a two-step process comprising of digitization and canonical finitary reduction. This technique enables us to verify safety invariants for real-time systems using finite state model-checking avoiding the complexity of infinite state (bounded) model checking and scale up models without applying techniques from induction based proof methodology. Moreover, we can verify liveness properties for real-time systems, which is not possible by using induction with infinite state model checkers. We present examples of Fischer's Protocol, Train-Gate Controller, and TTA start-up algorithm to illustrate how such an approach can be efficiently used for verifying safety, liveness, and timeliness properties specified in LTL using finite state model checkers like SAL-smc and Spin. We also demonstrate how advanced modeling concepts like inter-process scheduling, priorities, interrupts, urgent and committed location can be specified as extensions of the proposed specification formalism.

cs.LO↗

arXiv2009

A Randomized Algorithm for 3-SAT

In this work we propose and analyze a simple randomized algorithm to find a satisfiable assignment for a Boolean formula in conjunctive normal form (CNF) having at most 3 literals in every clause. Given a k-CNF formula phi on n variables, and alpha in{0,1}^n that satisfies phi, a clause of phi is critical if exactly one literal of that clause is satisfied under assignment alpha. Paturi et. al. (Chicago Journal of Theoretical Computer Science 1999) proposed a simple randomized algorithm (PPZ) for k-SAT for which success probability increases with the number of critical clauses (with respect to a fixed satisfiable solution of the input formula). Here, we first describe another simple randomized algorithm DEL which performs better if the number of critical clauses are less (with respect to a fixed satisfiable solution of the input formula). Subsequently, we combine these two simple algorithms such that the success probability of the combined algorithm is maximum of the success probabilities of PPZ and DEL on every input instance. We show that when the average number of clauses per variable that appear as unique true literal in one or more critical clauses in phi is between 1 and 1.9317, combined algorithm performs better than the PPZ algorithm.

cs.DS↗

arXiv2009

Towards a Framework for Observing Artificial Evolutionary Systems

Establishing the emergence of evolutionary behavior as a defining characteristic of 'life' is a major step in the Artificial life (ALife) studies. We present here an abstract formal framework for this aim based upon the notion of high-level observations made on the ALife model at hand during its simulations. An observation process is defined as a computable transformation from the underlying dynamic structure of the model universe to a tuple consisting of abstract components needed to establish the evolutionary processes in the model. Starting with defining entities and their evolutionary relationships observed during the simulations of the model, the framework prescribes a series of definitions, followed by the axioms (conditions) that must be met in order to establish the level of evolutionary behavior in the model. The examples of Cellular Automata based Langton Loops and Lambda calculus based Algorithmic Chemistry are used to illustrate the framework. Generic design suggestions for the ALife research are also drawn based upon the framework design and case study analysis.

cs.NE↗