Arpit Narechania
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Arpit Narechania has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Alex Endert
Georgia Institute of Technology, Atlanta, Georgia, USA
7 shared publications - Atanu R. Sinha
Adobe Research, Bangalore, India
2 shared publications - Clio Andris
Georgia Institute of Technology
2 shared publications - Kaustubh Odak
Amazon Web Services, Seattle, Washington, USA
2 shared publications - Yanwei Huang
The Hong Kong University of Science and Technology, Hong Kong S.A.R., China
2 shared publications Adam Coscia
Georgia Institute of Technology, United States
1 shared publication
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Alignment–Process–Outcome: Rethinking How AIs and Humans Collaborate
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessAlignment–Process–Outcome: Rethinking How AIs and Humans Collaborate
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Does a Picture Paint a Thousand Words? Using Visual and Textual Channels to Understand Attitudes and Beliefs
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessDoes a Picture Paint a Thousand Words? Using Visual and Textual Channels to Understand Attitudes and Beliefs
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Vipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessVipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Analyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessAnalyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Facilitating Proactive and Reactive Guidance for Decision Making on the Web: A Design Probe with WebSeek
Web AI agents such as ChatGPT Agent and GenSpark are increasingly used for routine web-based tasks, yet they still rely on text-based input prompts, lack proactive detection of user intent, and offer no support for interactive data analysis and decision making. We present WebSeek, a mixed-initiative browser extension that enables users to discover and extract information from webpages to then flexibly build, transform, and refine tangible data artifacts–such as tables, lists, and visualizations–all within an interactive canvas. Within this environment, users can perform analysis–including data transformations such as joining tables or creating visualizations–while an in-built AI both proactively offers context-aware guidance and automation, and reactively responds to explicit user requests. An exploratory user study (N=15) with WebSeek as a probe reveals participants’ diverse analysis strategies, underscoring their desire for transparency and control during human-AI collaboration.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Open AccessFacilitating Proactive and Reactive Guidance for Decision Making on the Web: A Design Probe with WebSeek
Web AI agents such as ChatGPT Agent and GenSpark are increasingly used for routine web-based tasks, yet they still rely on text-based input prompts, lack proactive detection of user intent, and offer no support for interactive data analysis and decision making. We present WebSeek, a mixed-initiative browser extension that enables users to discover and extract information from webpages to then flexibly build, transform, and refine tangible data artifacts–such as tables, lists, and visualizations–all within an interactive canvas. Within this environment, users can perform analysis–including data transformations such as joining tables or creating visualizations–while an in-built AI both proactively offers context-aware guidance and automation, and reactively responds to explicit user requests. An exploratory user study (N=15) with WebSeek as a probe reveals participants’ diverse analysis strategies, underscoring their desire for transparency and control during human-AI collaboration.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SuperProvenanceWidgets: Tracking and Visualizing Analytic Provenance Across UI Control Elements
ProvenanceWidgets is an existing JavaScript library that tracks the recency and frequency of user interactions with individual UI controls (e.g., range sliders and dropdowns) and dynamically overlays this provenance onto them. In this work, we introduce SuperProvenanceWidgets, an extension to ProvenanceWidgets featuring a new SuperWidget that similarly tracks and visualizes provenance but across multiple UI controls, enabling users to understand how, when, and whether different UI controls were used. Through three example usage scenarios, we demonstrate how this cross-control SuperWidget helps (a) audit and share analysis workflows, (b) surface and mitigate exploration biases, and (c) facilitate user interface design and personalization. We also perform a technical self-assessment using the Cognitive Dimensions of Notations to evaluate the library’s usability for developers. SuperProvenanceWidgets is integrated into the ProvenanceWidgets library and is available as open-source software at ProvenanceWidgets.github.io , empowering developers to build advanced provenance applications.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSuperProvenanceWidgets: Tracking and Visualizing Analytic Provenance Across UI Control Elements
ProvenanceWidgets is an existing JavaScript library that tracks the recency and frequency of user interactions with individual UI controls (e.g., range sliders and dropdowns) and dynamically overlays this provenance onto them. In this work, we introduce SuperProvenanceWidgets, an extension to ProvenanceWidgets featuring a new SuperWidget that similarly tracks and visualizes provenance but across multiple UI controls, enabling users to understand how, when, and whether different UI controls were used. Through three example usage scenarios, we demonstrate how this cross-control SuperWidget helps (a) audit and share analysis workflows, (b) surface and mitigate exploration biases, and (c) facilitate user interface design and personalization. We also perform a technical self-assessment using the Cognitive Dimensions of Notations to evaluate the library’s usability for developers. SuperProvenanceWidgets is integrated into the ProvenanceWidgets library and is available as open-source software at ProvenanceWidgets.github.io , empowering developers to build advanced provenance applications.
- Open Access
A Design Space for Intelligent Agents in Mixed-Initiative Visual Analytics
Mixed-initiative visual analytics (VA) systems, where human and artificial intelligence (AI) agents collaborate as equal partners during analysis, represented a paradigm shift in human-computer interaction. With recent advances in AI, these systems have seen an increase in sophisticated software agents that have improved task planning, reasoning, and completion capabilities. However, while existing work characterizes agent interplay and communication strategies, there is a limited understanding of the overarching design principles for intelligent agents. Through a systematic review of 90 systems (and 207 unique agents), we propose a design space of intelligent agents comprising six dimensions that collectively characterize an agent's perception, environmental understanding, action capability, and communication strategies. We contribute a novel framework for researchers and designers to explore various design choices for new systems and to situate a system in the current landscape. We conclude with future research opportunities for intelligent agents in mixed-initiative VA systems.
Open AccessA Design Space for Intelligent Agents in Mixed-Initiative Visual Analytics
Mixed-initiative visual analytics (VA) systems, where human and artificial intelligence (AI) agents collaborate as equal partners during analysis, represented a paradigm shift in human-computer interaction. With recent advances in AI, these systems have seen an increase in sophisticated software agents that have improved task planning, reasoning, and completion capabilities. However, while existing work characterizes agent interplay and communication strategies, there is a limited understanding of the overarching design principles for intelligent agents. Through a systematic review of 90 systems (and 207 unique agents), we propose a design space of intelligent agents comprising six dimensions that collectively characterize an agent's perception, environmental understanding, action capability, and communication strategies. We contribute a novel framework for researchers and designers to explore various design choices for new systems and to situate a system in the current landscape. We conclude with future research opportunities for intelligent agents in mixed-initiative VA systems.
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-24
Cartographers in Cubicles: How Training and Preferences of Mapmakers Interplay with Structures and Norms in Not-for-Profit Organizations
Choropleth maps are a common and effective way to visualize geographic thematic data. Although cartographers have established many principles about map design, data binning and color usage, less is known about how mapmakers make individual decisions in practice. We interview 16 cartographers and geographic information systems (GIS) experts from 13 government organizations, NGOs, and federal agencies about their choropleth mapmaking decisions and workflows. We categorize our findings and report on how mapmakers follow cartographic guidelines and personal rules of thumb, collaborate with other stakeholders within and outside their organization, and how organizational structures and norms are tied to decision-making during data preparation, data analysis, data binning, map styling, and map post-processing. We find several points of variation as well as regularity across mapmakers and organizations and present takeaways to inform cartographic education and practice, including broader implications and opportunities for CSCW, HCI, and information visualization researchers and practitioners.
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (7) , 1-24
Open AccessCartographers in Cubicles: How Training and Preferences of Mapmakers Interplay with Structures and Norms in Not-for-Profit Organizations
Choropleth maps are a common and effective way to visualize geographic thematic data. Although cartographers have established many principles about map design, data binning and color usage, less is known about how mapmakers make individual decisions in practice. We interview 16 cartographers and geographic information systems (GIS) experts from 13 government organizations, NGOs, and federal agencies about their choropleth mapmaking decisions and workflows. We categorize our findings and report on how mapmakers follow cartographic guidelines and personal rules of thumb, collaborate with other stakeholders within and outside their organization, and how organizational structures and norms are tied to decision-making during data preparation, data analysis, data binning, map styling, and map post-processing. We find several points of variation as well as regularity across mapmakers and organizations and present takeaways to inform cartographic education and practice, including broader implications and opportunities for CSCW, HCI, and information visualization researchers and practitioners.
- 23 September 2025
- Published by Taylor & Francis in Cartography and Geographic Information Science
- Vol. 53 (6) , 659-674
Exploropleth: exploratory analysis of data binning methods in choropleth maps
- 23 September 2025
- Published by Taylor & Francis in Cartography and Geographic Information Science
- Vol. 53 (6) , 659-674
Exploropleth: exploratory analysis of data binning methods in choropleth maps
- Open Access
- 4 September 2025
- Published by Center for Open Science in OSF Preprints
NL4DV-Stylist: Styling Data Visualizations Using Natural Language and Example Charts
Natural language interfaces (NLIs) enable flexible authoring and interaction with visualizations (VIS) using natural language (NL). However, current NLIs predominantly focus on identifying the data attributes and analytic tasks from the user's query and give less emphasis to customizing the design of the output visualizations, which is an important consideration to satisfy personal preferences, meet branding requirements, and/or ensure accessibility. We present NL4DV-Stylist, a Python toolkit that utilizes example charts and NL instructions as design guidance, enhancing current NL to VIS authoring workflows to produce more design-informed visualizations. For instance, if a user generally prefers horizontal legends or wants to re-use the blue color scheme they saw in a scatterplot, they can supply these as inputs to the toolkit, which will incorporate these design preferences when generating visualizations. NL4DV-Stylist is available as open-source software at https://nl4dv.github.io.
- 4 September 2025
- Published by Center for Open Science in OSF Preprints
Open AccessNL4DV-Stylist: Styling Data Visualizations Using Natural Language and Example Charts
Natural language interfaces (NLIs) enable flexible authoring and interaction with visualizations (VIS) using natural language (NL). However, current NLIs predominantly focus on identifying the data attributes and analytic tasks from the user's query and give less emphasis to customizing the design of the output visualizations, which is an important consideration to satisfy personal preferences, meet branding requirements, and/or ensure accessibility. We present NL4DV-Stylist, a Python toolkit that utilizes example charts and NL instructions as design guidance, enhancing current NL to VIS authoring workflows to produce more design-informed visualizations. For instance, if a user generally prefers horizontal legends or wants to re-use the blue color scheme they saw in a scatterplot, they can supply these as inputs to the toolkit, which will incorporate these design preferences when generating visualizations. NL4DV-Stylist is available as open-source software at https://nl4dv.github.io.