pith. machine review for the scientific record. sign in

arxiv: 2604.20759 · v1 · submitted 2026-04-22 · 💻 cs.HC · cs.GR· cs.SE

Recognition: unknown

Autark: A Serverless Toolkit for Prototyping Urban Visual Analytics Systems

Claudio Silva, Daniel de Oliveira, Fabio Miranda, Gustavo Moreira, Jo\~ao Rulff, Lucas Alexandre, Marcos Lage, Talisson Souza

Pith reviewed 2026-05-09 23:21 UTC · model grok-4.3

classification 💻 cs.HC cs.GRcs.SE
keywords urban visual analyticsserverless toolkitrapid prototypingvisual analytics systemsdomain-aware abstractionsAI-assisted codingurban data streams
0
0 comments X

The pith

Autark toolkit lets researchers build and deploy urban visual analytics systems in hours using serverless abstractions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Autark to solve the time-consuming work of creating visual analytics tools for city data, where varied data streams and multi-service setups usually slow things down. It supplies a self-contained serverless setup with domain-specific building blocks for handling spatial information, running analyses, and creating visualizations. Users can move from an initial idea straight to a working, shareable prototype without heavy engineering. The same clean interfaces also help large language models write more accurate code by giving them well-defined pieces to assemble instead of starting from scratch. Demonstrations include side-by-side tests of LLM performance and example systems built with the toolkit.

Core claim

Autark is a serverless toolkit for rapid prototyping of urban visual analytics systems that supplies domain-aware abstractions through a self-contained architecture, enabling researchers to move from design intention to deployed and shareable systems within hours while also supporting more reliable code generation by large language models through its tightly scoped interfaces.

What carries the argument

Autark's serverless architecture, which unifies spatial data management, analytical processing, and visualization behind domain-aware, tightly scoped interfaces.

If this is right

  • Researchers can create and share urban VA prototypes much faster than with traditional multi-service setups.
  • LLMs produce more reliable code when working from Autark's defined abstractions rather than generating full solutions.
  • A series of usage scenarios show the toolkit supporting robust, shareable urban VA systems.
  • The toolkit fills a gap by consolidating core urban VA components that the field previously lacked.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar abstraction layers could shorten prototyping time in other data-heavy fields such as environmental monitoring or public health dashboards.
  • Direct connections to common city data sources might further cut initial setup effort for new users.
  • The design points to a broader pattern where clear interfaces lower the barrier between complex backend systems and domain experts who are not full-stack developers.

Load-bearing premise

The serverless abstractions and scoped interfaces can handle the range of urban data streams and multi-service needs without requiring much extra custom coding or performance loss.

What would settle it

Developers building a realistic urban visual analytics system with Autark still need extensive custom engineering or take far longer than a few hours to reach a deployed, shareable prototype.

Figures

Figures reproduced from arXiv: 2604.20759 by Claudio Silva, Daniel de Oliveira, Fabio Miranda, Gustavo Moreira, Jo\~ao Rulff, Lucas Alexandre, Marcos Lage, Talisson Souza.

Figure 1
Figure 1. Figure 1: Urbane [22] is an urban visual analytics system that supports multi-resolution exploration. It enables users to characterize urban areas based on data and identify sites for new development at the neighborhood and building levels. This Figure illustrates a remake of Urbane using Autark. (A) On initialization, the system fetches OpenStreetMap data and computes sky exposure values via the GPU. It also loads … view at source ↗
Figure 2
Figure 2. Figure 2: Autark’s serverless architecture. The toolkit comprises four inde [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Autark’s map and abstract charts modules facilitate the implemen [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Shadow accumulation in the Chicago Loop during the Summer Solstice (June 21), Autumnal Equinox (September 22), and Winter Solstice [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Analysis of urban heat trends in Niterói (2001–2024) using Autark. The system processes NASA LST raster data to enrich road segments [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Comparison of agent-generated outputs between the Autark [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
read the original abstract

The development of visual analytics (VA) systems has traditionally been a labor-intensive process, balancing design methodologies with complex software engineering practices. In domain-specific fields like urban VA, this challenge is amplified by heterogeneous data streams and a reliance on complex, multi-service architectures that hinder fast development, deployment, and reproducibility. Despite the richness of the urban VA literature, the field lacks a consolidated toolkit that encapsulates the core components of these systems, such as spatial data management, analytical processing, and visualization, into a unified, lightweight framework. In this paper, we introduce Autark, a serverless toolkit designed for the rapid prototyping of urban VA systems. Autark provides domain-aware abstractions through a self-contained architecture, enabling researchers to transition from design intention to deployed, shareable systems within hours. Furthermore, Autark's structured, tightly scoped interfaces make it well-suited for AI-assisted coding workflows, where LLMs produce more reliable code when composing from well-defined abstractions rather than generating complex solutions from scratch. Our contributions are: (1) the Autark toolkit, a serverless architecture for rapid prototyping of urban VA; (2) a comparative study of LLM coding effectiveness with and without Autark; and (3) a series of usage scenarios demonstrating its capability to streamline the creation of robust, shareable urban VA prototypes. Autark is available at https://autarkjs.org/.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper introduces Autark, a serverless toolkit for rapid prototyping of urban visual analytics (VA) systems. It claims that domain-aware abstractions and a self-contained architecture enable researchers to move from design intention to deployed, shareable systems within hours. Additional contributions include a comparative study of LLM coding effectiveness with and without Autark, plus usage scenarios demonstrating streamlined creation of urban VA prototypes. The toolkit is positioned as addressing challenges of heterogeneous data streams and multi-service architectures in urban VA.

Significance. If the core claims hold, Autark could meaningfully reduce development time and engineering overhead for urban VA prototypes, particularly by improving LLM-assisted code generation through scoped interfaces. The serverless design and open availability at autarkjs.org support reproducibility and sharing, which are valuable in a field where custom multi-service stacks often impede rapid iteration.

major comments (3)
  1. [Abstract] Abstract and contributions section: the central claim that Autark enables transition 'from design intention to deployed, shareable systems within hours' lacks supporting empirical evidence. No participant studies, timing measurements, baseline comparisons against traditional stacks, or quantification of custom engineering required for heterogeneous urban data streams are described, leaving the quantitative assertion unvalidated.
  2. [Abstract] Abstract and contributions (2): the comparative study of LLM coding effectiveness is asserted but provides no details on methods, participant tasks, metrics, statistical analysis, or results. Without these, it is impossible to assess whether the 'more reliable code' outcome is attributable to Autark's abstractions rather than task selection or prompting differences.
  3. [Usage scenarios] Usage scenarios: if these are purely illustrative rather than controlled evaluations, they do not address the weakest assumption that the provided serverless abstractions suffice for heterogeneous data streams and multi-service needs without substantial additional custom code or performance loss.
minor comments (2)
  1. [Abstract] The abstract and introduction would benefit from a clearer statement of the toolkit's core API surface and supported data types to allow readers to evaluate the 'tightly scoped interfaces' claim before reaching the usage scenarios.
  2. Consider adding a limitations section that explicitly discusses serverless overheads, data volume constraints, and scenarios where custom engineering remains necessary.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed review. We address each major comment below and outline the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract and contributions section: the central claim that Autark enables transition 'from design intention to deployed, shareable systems within hours' lacks supporting empirical evidence. No participant studies, timing measurements, baseline comparisons against traditional stacks, or quantification of custom engineering required for heterogeneous urban data streams are described, leaving the quantitative assertion unvalidated.

    Authors: We agree that the specific phrasing 'within hours' is not supported by formal empirical data such as participant studies, timing measurements, or controlled baselines. This language reflected our practical experience developing the toolkit and the quick setup observed during the usage scenarios. We will revise the abstract and contributions section to remove the quantitative claim, instead stating that Autark supports rapid prototyping of urban VA systems as illustrated by the scenarios. We will also add a brief discussion of observed engineering overhead based on the scenarios. revision: yes

  2. Referee: [Abstract] Abstract and contributions (2): the comparative study of LLM coding effectiveness is asserted but provides no details on methods, participant tasks, metrics, statistical analysis, or results. Without these, it is impossible to assess whether the 'more reliable code' outcome is attributable to Autark's abstractions rather than task selection or prompting differences.

    Authors: The comparative study appears in the evaluation section, where we describe the coding tasks and note differences in code reliability when using Autark's abstractions. We acknowledge that the methods, specific tasks, metrics, and results require more elaboration to allow independent assessment. We will expand this section with explicit details on the LLM prompting approach, the exact tasks performed, the evaluation metrics (e.g., iteration counts and error types), and the observed outcomes to clarify the attribution to the abstractions. revision: yes

  3. Referee: [Usage scenarios] Usage scenarios: if these are purely illustrative rather than controlled evaluations, they do not address the weakest assumption that the provided serverless abstractions suffice for heterogeneous data streams and multi-service needs without substantial additional custom code or performance loss.

    Authors: The usage scenarios are drawn from actual development sessions and include code examples showing integration of heterogeneous data streams and services. Each scenario demonstrates that the core functionality was achieved primarily through the provided abstractions. To address the concern, we will revise the section to add explicit discussion of the custom code required (with approximate quantification) and any performance notes from the serverless deployments, while retaining their illustrative nature. revision: partial

Circularity Check

0 steps flagged

No circularity: toolkit introduction paper with no derivation chain or fitted predictions

full rationale

The paper introduces a serverless toolkit (Autark) for urban visual analytics prototyping, with contributions limited to the toolkit itself, an LLM coding effectiveness study, and illustrative usage scenarios. No mathematical derivations, equations, predictions, or parameter-fitting steps exist in the provided text or abstract. The central claim of transitioning 'from design intention to deployed, shareable systems within hours' is an empirical usability assertion about the toolkit's abstractions and architecture, not a quantity derived from prior steps that could reduce to itself by construction. No self-citation load-bearing, uniqueness theorems, ansatzes, or renamings of known results appear in any load-bearing role. The paper is self-contained as a systems/HCI contribution; external validation (e.g., timing studies) is a separate evidence question, not a circularity issue. Steps array left empty per rules for non-findings.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper contributes a software toolkit rather than a derivation from first principles or data fitting. It relies on the domain assumption that serverless computing can encapsulate urban VA components effectively.

axioms (1)
  • domain assumption A serverless, self-contained architecture with domain-aware abstractions can support the core needs of urban visual analytics systems
    Invoked as the basis for the toolkit design and rapid prototyping claims in the abstract.

pith-pipeline@v0.9.0 · 5569 in / 1205 out tokens · 58567 ms · 2026-05-09T23:21:34.124903+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

66 extracted references · 47 canonical work pages

  1. [1]

    deck.gl.https://deck.gl/, 2024. 2

    2024

  2. [2]

    kepler.gl.https://kepler.gl/, 2024. 2

    2024

  3. [3]

    Leaflet.https://leafletjs.com/, 2024. 2

    2024

  4. [4]

    Mapbox GL JS.https://www.mapbox.com/mapbox-gljs, 2024. 2

    2024

  5. [5]

    MapLibre GL JS.https://maplibre.org/, 2024. 2

    2024

  6. [6]

    OpenLayers.https://openlayers.org/, 2024. 2

    2024

  7. [7]

    Visualization

    J. Ahrens, B. Geveci, and C. Law. ParaView: An end-user tool for large data visualization.The Visualization Handbook, pp. 717–731, 2005. doi: 10.1016/B978-012387582-2/50038-1 3

    work page doi:10.1016/b978-012387582-2/50038-1 2005

  8. [9]

    Andrienko, N

    G. Andrienko, N. Andrienko, W. Chen, R. Maciejewski, and Y . Zhao. Visual analytics of mobility and transportation: State of the art and further research directions.IEEE Trans. Intell. Transp. Syst., 18(8):2232–2249,

  9. [10]

    doi: 10.1109/TITS.2017.2701893 2

    work page doi:10.1109/tits.2017.2701893 2017

  10. [11]

    Bonadia, R

    S. Bonadia, R. Gama, D. d. Oliveira, F. Miranda, and M. Lage. Visual analytics using heterogeneous urban data. InProc. SIBGRAPI, pp. 1–6,

  11. [12]

    doi: 10.1109/SIBGRAPI59091.2023.10347156 2, 3

    work page doi:10.1109/sibgrapi59091.2023.10347156 2023

  12. [13]

    Booth, A

    B. Booth, A. Mitchell, et al. Getting started with ArcGIS, 2001. 2

    2001

  13. [14]

    Bostock, M

    M. Bostock, M. Conlen, J. Heer, and I. Meckler. Observable: The col- laborative data canvas. https://observablehq.com, 2024. Accessed: 2026-03-21. 1, 9

    2024

  14. [15]

    Bostock and J

    M. Bostock and J. Heer. Protovis: A graphical toolkit for visualization. IEEE Trans. Vis. Comput. Graph., 15(6):1121–1128, 2009. doi: 10.1109/ TVCG.2009.174 2

    2009

  15. [16]

    Bostock, V

    M. Bostock, V . Ogievetsky, and J. Heer. D3: Data-driven documents. IEEE Trans. Vis. Comput. Graph., 17(12):2301–2309, 2011. doi: 10.1109/ TVCG.2011.185 1, 2, 3

    2011

  16. [17]

    S. Chen, F. Miranda, N. Ferreira, M. Lage, H. Doraiswamy, C. Brenner et al. UrbanRama: Navigating cities in virtual reality.IEEE Trans. Vis. Comput. Graph., 28(12):4685–4699, 2021. doi: 10.1109/TVCG.2021. 3099012 2

    work page doi:10.1109/tvcg.2021 2021

  17. [18]

    Z. Deng, D. Weng, J. Chen, R. Liu, Z. Wang, J. Bao et al. AirVis: Visual analytics of air pollution propagation.IEEE Trans. Vis. Comput. Graph., 26(1):800–810, 2019. doi: 10.1109/TVCG.2019.2934670 2

    work page doi:10.1109/tvcg.2019.2934670 2019

  18. [19]

    V . Dibia. LIDA: A tool for automatic generation of grammar-agnostic visualizations and infographics using large language models. InProc. ACL, pp. 113–126, 2023. doi: 10.18653/v1/2023.acl-demo.11 3

    work page doi:10.18653/v1/2023.acl-demo.11 2023

  19. [20]

    Doraiswamy, J

    H. Doraiswamy, J. Freire, M. Lage, F. Miranda, and C. T. Silva. Spatio- temporal urban data analysis: A visual analytics perspective.IEEE Comput. Graph. Appl., 38(5):26–35, 2018. doi: 10.1109/MCG.2018.2852702 3

    work page doi:10.1109/mcg.2018.2852702 2018

  20. [21]

    Elmqvist and P

    N. Elmqvist and P. Tsigas. A taxonomy of 3D occlusion management for visualization.IEEE Trans. Vis. Comput. Graph., 14(5):1095–1109, 2008. doi: 10.1109/TVCG.2008.59 2

    work page doi:10.1109/tvcg.2008.59 2008

  21. [22]

    Ferreira, G

    L. Ferreira, G. Moreira, M. Hosseini, M. Lage, N. Ferreira, and F. Miranda. Assessing the landscape of toolkits, frameworks, and authoring tools for urban visual analytics systems.Comput. Graph., 123:104013, 2024. doi: 10.1016/j.cag.2024.104013 2, 3

    work page doi:10.1016/j.cag.2024.104013 2024

  22. [23]

    Ferreira, G

    L. Ferreira, G. Moreira, and F. Miranda. V A-Blueprint: Uncovering building blocks for visual analytics system design.IEEE Trans. Vis. Comput. Graph., 2025. doi: 10.1109/TVCG.2024.3456345 2

    work page doi:10.1109/tvcg.2024.3456345 2025

  23. [24]

    Ferreira, M

    N. Ferreira, M. Lage, H. Doraiswamy, H. V o, L. Wilson, H. Werner et al. Urbane: A 3D framework to support data driven decision making in urban development. InProc. VAST, pp. 97–104, 2015. doi: 10.1109/V AST.2015 .7347636 1, 2, 3, 6

    work page doi:10.1109/v 2015

  24. [25]

    Ferreira, J

    N. Ferreira, J. Poco, H. V o, J. Freire, and C. T. Silva. Visual exploration of big spatio-temporal urban data: A study of New York City taxi trips. IEEE Trans. Vis. Comput. Graph., 19(12):2149–2158, 2013. doi: 10.1109/ TVCG.2013.226 2, 3, 5

    2013

  25. [26]

    Freire, P

    J. Freire, P. Bonnet, and D. Shasha. Computational reproducibility: State- of-the-art, challenges, and database research opportunities. InProc. SIG- MOD, pp. 593–596, 2012. doi: 10.1145/2213836.2213908 2

    work page doi:10.1145/2213836.2213908 2012

  26. [27]

    T. Gao, M. Dontcheva, E. Adar, Z. Liu, and K. G. Karahalios. DataTone: Managing ambiguity in natural language interfaces for data visualization. InProc. UIST, pp. 489–500, 2015. doi: 10.1145/2807442.2807478 3

    work page doi:10.1145/2807442.2807478 2015

  27. [28]

    García-Zanabria, M

    G. García-Zanabria, M. M. Raimundo, J. Poco, M. B. Nery, C. T. Silva, S. Adorno et al. CriPA V: Street-level crime patterns analysis and visual- ization.IEEE Trans. Vis. Comput. Graph., 28(12):4000–4015, 2021. doi: 10.1109/TVCG.2021.3111146 2

    work page doi:10.1109/tvcg.2021.3111146 2021

  28. [29]

    H. Guo, Z. Wang, B. Yu, H. Zhao, and X. Yuan. TripVista: Triple perspective visual trajectory analytics and its application on microscopic traffic data at a road intersection. InProc. PacificVis, pp. 163–170, 2011. doi: 10.1109/PACIFICVIS.2011.5742387 1

    work page doi:10.1109/pacificvis.2011.5742387 2011

  29. [30]

    J. Heer, S. K. Card, and J. A. Landay. Prefuse: A toolkit for interactive information visualization. InProc. CHI, pp. 421–430, 2005. doi: 10. 1145/1054972.1055031 2

    work page arXiv 2005

  30. [31]

    J. Heer, D. Moritz, and R. Pechuk. Mosaic: An architecture for linking databases and scalable interactive visualizations. InProc. SIGMOD, pp. 123–126, 2025. doi: 10.1145/3632410.3632420 2

    work page doi:10.1145/3632410.3632420 2025

  31. [32]

    J. Heer, D. Moritz, and R. Pechuk. Mosaic Selections: Managing and optimizing user selections for scalable data visualization systems.IEEE Trans. Vis. Comput. Graph., 2025. doi: 10.48550/arXiv.2507.19690 2

    work page doi:10.48550/arxiv.2507.19690 2025

  32. [33]

    L. Lins, J. T. Klosowski, and C. Scheidegger. Nanocubes for real-time exploration of spatiotemporal datasets.IEEE Trans. Vis. Comput. Graph., 19(12):2456–2465, 2013. doi: 10.1109/TVCG.2013.179 2

    work page doi:10.1109/tvcg.2013.179 2013

  33. [34]

    Z. Liu, B. Jiang, and J. Heer. imMens: Real-time visual querying of big data. InComput. Graph. Forum, vol. 32, pp. 421–430, 2013. doi: 10. 1111/cgf.12129 2

    2013

  34. [35]

    doi:10.1109/ACCESS

    P. Maddigan and T. Susnjak. Chat2Vis: Generating data visualizations via natural language using ChatGPT, Codex and GPT-3 large language models.IEEE Access, 11:45181–45193, 2023. doi: 10.1109/ACCESS. 2023.3273215 3

    work page doi:10.1109/access 2023

  35. [36]

    Heterogeneous computing in a strongly-connected CPU-GPU environment: fast multiple time-evolution equation-based modeling accelerated using data-driven approach

    T. Mallick, O. Yildiz, D. Lenz, and T. Peterka. ChatVis: Automating scientific visualization with a large language model. InProc. SC-W, pp. 49–55, 2024. doi: 10.1109/SCW63240.2024.00014 3

    work page doi:10.1109/scw63240.2024.00014 2024

  36. [37]

    T. J. McCabe. A complexity measure.IEEE Trans. Softw. Eng., 4:308–320,

  37. [38]

    doi: 10.1109/TSE.1976.233837 9

    work page doi:10.1109/tse.1976.233837 1976

  38. [39]

    Miranda, H

    F. Miranda, H. Doraiswamy, M. Lage, L. Wilson, M. Hsieh, and C. T. Silva. Shadow Accrual Maps: Efficient accumulation of city-scale shadows over time.IEEE Trans. Vis. Comput. Graph., 25(3):1559–1574, 2019. doi: 10. 1109/TVCG.2018.2802945 3, 7

    work page arXiv 2019

  39. [40]

    The State of the Art in Visual Analytics for 3D Urban Data

    F. Miranda, T. Ortner, G. Moreira, M. Hosseini, M. Vu ˇckovi´c, F. Biljecki et al. The state of the art in visual analytics for 3D urban data.Comput. Graph. Forum, 43(3):e15112, 2024. doi: 10.1111/cgf.15112 2, 3

    work page doi:10.1111/cgf.15112 2024

  40. [41]

    Moreira, L

    G. Moreira, L. Ferreira, C. Veiga, M. Hosseini, and F. Miranda. Urbanite: A dataflow-based framework for human-ai interactive alignment in urban visual analytics.IEEE Trans. Vis. Comput. Graph., 32(1):1065–1075,

  41. [42]

    doi: 10.1109/TVCG.2025.3634644 3

    work page doi:10.1109/tvcg.2025.3634644 2025

  42. [43]

    Moreira, M

    G. Moreira, M. Hosseini, M. N. A. Nipu, M. Lage, N. Ferreira, and F. Miranda. The Urban Toolkit: A grammar-based framework for urban visual analytics.IEEE Trans. Vis. Comput. Graph., 30(1):1402–1412,

  43. [44]

    doi: 10.1109/TVCG.2023.3326922 2, 3

    work page doi:10.1109/tvcg.2023.3326922 2023

  44. [45]

    D., Quadri G

    G. Moreira, M. Hosseini, C. Veiga, L. Alexandre, N. Colaninno, D. de Oliveira et al. Curio: A dataflow-based framework for collaborative urban visual analytics.IEEE Trans. Vis. Comput. Graph., 31(1):1224– 1234, 2025. doi: 10.1109/TVCG.2024.3456353 3

    work page doi:10.1109/tvcg.2024.3456353 2025

  45. [46]

    Moritz, B

    D. Moritz, B. Howe, and J. Heer. Falcon: Balancing interactive latency and resolution sensitivity for scalable linked visualizations. InProc. CHI, pp. 1–11, 2019. doi: 10.1145/3290605.3300924 2

    work page doi:10.1145/3290605.3300924 2019

  46. [47]

    Moritz, C

    D. Moritz, C. Wang, G. L. Nelson, H. Lin, A. M. Smith, B. Howe et al. Formalizing visualization design knowledge as constraints: Actionable and extensible models in Draco.IEEE Trans. Vis. Comput. Graph., 25(1):438– 448, 2018. doi: 10.1109/TVCG.2018.2865240 1

    work page doi:10.1109/tvcg.2018.2865240 2018

  47. [48]

    Moyroud and F

    N. Moyroud and F. Portet. Introduction to QGIS.QGIS and Generic Tools, 1:1–17, 2018. doi: 10.1002/9781119439165.ch1 2

    work page doi:10.1002/9781119439165.ch1 2018

  48. [50]

    Partl, A

    C. Partl, A. Lex, M. Streit, D. Kalkofen, K. Kashofer, and D. Schmalstieg. enRoute: Dynamic path extraction from biological pathway maps for exploring heterogeneous experimental datasets.BMC Bioinformatics, 14(S19):S3, 2013. doi: 10.1186/1471-2105-14-S19-S3 1

    work page doi:10.1186/1471-2105-14-s19-s3 2013

  49. [51]

    Raasveldt and H

    M. Raasveldt and H. Mühleisen. DuckDB: An embeddable analytical database. InProc. SIGMOD, pp. 1981–1984, 2019. doi: 10.1145/3299869 .3320212 2

    work page doi:10.1145/3299869 1981

  50. [52]

    Rodgers and L

    J. Rodgers and L. Bartram. Exploring ambient and artistic visualization for residential energy use feedback.IEEE Trans. Vis. Comput. Graph., 17(12):2489–2497, 2011. doi: 10.1109/TVCG.2011.196 2

    work page doi:10.1109/tvcg.2011.196 2011

  51. [53]

    Höllt, N

    J. Rulff, F. Miranda, M. Hosseini, M. Lage, M. Cartwright, G. Dove et al. Urban Rhapsody: Large-scale exploration of urban soundscapes. In Comput. Graph. Forum, vol. 41, pp. 209–221, 2022. doi: 10.1111/cgf. 14533 2, 3

    work page doi:10.1111/cgf 2022

  52. [54]

    IEEE Transactions on Visualization and Computer Graphics 23, 341–350

    A. Satyanarayan, D. Moritz, K. Wongsuphasawat, and J. Heer. Vega-Lite: A grammar of interactive graphics.IEEE Trans. Vis. Comput. Graph., 23(1):341–350, 2016. doi: 10.1109/TVCG.2016.2599030 1, 2, 3

    work page doi:10.1109/tvcg.2016.2599030 2016

  53. [55]

    : Design study methodology: Reflections from the trenches and the stacks

    M. Sedlmair, M. Meyer, and T. Munzner. Design study methodology: Reflections from the trenches and the stacks.IEEE Trans. Vis. Comput. Graph., 18(12):2431–2440, 2012. doi: 10.1109/TVCG.2012.213 1

    work page doi:10.1109/tvcg.2012.213 2012

  54. [56]

    Setlur, S

    V . Setlur, S. E. Battersby, M. Tory, R. Gossweiler, and A. X. Chang. Eviza: A natural language interface for visual analysis. InProc. UIST, pp. 365–377, 2016. doi: 10.1145/2984511.2984588 3

    work page doi:10.1145/2984511.2984588 2016

  55. [57]

    Regal: Refactoring programs to discover generalizable abstractions.arXiv preprint arXiv:2401.16467,

    E. Stengel-Eskin, A. Prasad, and M. Bansal. Regal: Refactoring programs to discover generalizable abstractions.arXiv preprint arXiv:2401.16467,

    work page arXiv

  56. [58]

    doi: 10.48550/arXiv.2401.16467 2

    work page doi:10.48550/arxiv.2401.16467

  57. [59]

    Y . Sun, J. Leigh, A. Johnson, and S. Lee. Articulate: A semi-automated model for translating natural language queries into meaningful visual- izations. InInt. Symp. Smart Graphics, pp. 184–195, 2010. doi: 10. 1007/978-3-642-13544-6_18 3

    2010

  58. [60]

    Y . Tian, W. Cui, D. Deng, X. Yi, Y . Yang, H. Zhang et al. ChartGPT: Leveraging LLMs to generate charts from abstract natural language.IEEE Trans. Vis. Comput. Graph., 31(3):1731–1745, 2024. doi: 10.1109/TVCG. 2023.3346715 3

    work page doi:10.1109/tvcg 2024

  59. [61]

    Wagner, C

    J. Wagner, C. T. Silva, W. Stuerzlinger, and L. Nedel. Reimagining TaxiVis through an immersive space-time cube metaphor. InProc. VR, pp. 827–838, 2024. doi: 10.1109/VR58804.2024.00099 9

    work page doi:10.1109/vr58804.2024.00099 2024

  60. [62]

    Waser, A

    J. Waser, A. Konev, B. Sadransky, Z. Horváth, H. Ribiˇci´c, R. Carnecky et al. Many plans: Multidimensional ensembles for visual decision support in flood management. InComput. Graph. Forum, vol. 33, pp. 281–290,

  61. [63]

    doi: 10.1111/cgf.12384 2

    work page doi:10.1111/cgf.12384

  62. [64]

    Wongsuphasawat

    K. Wongsuphasawat. Encodable: Configurable grammar for visualization components. InProc. VIS, pp. 131–135, 2020. doi: 10.1109/VIS47514. 2020.00034 2

    work page doi:10.1109/vis47514 2020

  63. [65]

    Yu and C

    B. Yu and C. T. Silva. FlowSense: A natural language interface for visual data exploration within a dataflow system.IEEE Trans. Vis. Comput. Graph., 26(1):1–11, 2019. doi: 10.1109/TVCG.2019.2934668 3

    work page doi:10.1109/tvcg.2019.2934668 2019

  64. [66]

    Zhang and M

    R. Zhang and M. Elhamod. Data-to-dashboard: Multi-agent LLM frame- work for insightful visualization in enterprise analytics.arXiv preprint arXiv:2505.23695, 2025. doi: 10.48550/arXiv.2505.23695 3

    work page doi:10.48550/arxiv.2505.23695 2025

  65. [67]

    Y . Zhao, J. Wang, L. Xiang, X. Zhang, Z. Guo, C. Turkay et al. LightV A: Lightweight visual analytics with LLM agent-based task planning and execution.IEEE Trans. Vis. Comput. Graph., 31(9):6162–6177, 2024. doi: 10.1109/TVCG.2024.3413998 3

    work page doi:10.1109/tvcg.2024.3413998 2024

  66. [68]

    Ziegler and S

    P. Ziegler and S. E. Chasins. A need-finding study with users of geospatial data. InProc. CHI, pp. 1–16, 2023. doi: 10.1145/3544548.3581370 2

    work page doi:10.1145/3544548.3581370 2023