CLARA: An AI-Augmented Analytics Dashboard for Collaboration Literacy

arxiv: 2605.17259 · v1 · pith:BLYT3PVFnew · submitted 2026-05-17 · 💻 cs.HC

CLARA: An AI-Augmented Analytics Dashboard for Collaboration Literacy

Dawei Xie , Khalil Anderson , Tochukwu Eze , Chenghong Lin , Bookyung Shin , Marcelo Worsley This is my paper

Pith reviewed 2026-05-19 23:20 UTC · model grok-4.3

classification 💻 cs.HC

keywords collaboration literacyAI-augmented analyticsconcept mapscollaboration assessmentknowledge infrastructuresemantic representationslearning analyticsagentic systems

0 comments p. Extension

pith:BLYT3PVF Add to your LaTeX paper

What is a Pith Number?

\usepackage{pith}
\pithnumber{BLYT3PVF}

Prints a linked pith:BLYT3PVF badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

The pith

CLARA extracts concept maps and seven-dimension assessments from transcripts to create shared representations that improve both user analytics and AI retrieval over text-only baselines.

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

The paper introduces CLARA as an agentic system that converts collaboration transcripts into semantic artifacts: concept maps of emerging ideas and relationships plus assessments across seven collaboration dimensions. These artifacts drive an interactive dashboard for human users while also populating vector databases that AI agents use for retrieval and reasoning. The dual use creates a common ground where humans and machines operate over the same structured representations rather than raw text. Evaluation indicates the approach delivers reliable quality analysis and outperforms transcript-only methods in retrieval performance and response quality. This matters for fields that need to assess how groups actually build ideas together instead of relying on surface behavioral signals.

Core claim

CLARA is an agentic analytics system that extracts semantic representations from transcripts as analytics artifacts: concept maps representing emergent ideas and relationships, and collaboration assessment characterizing collaboration quality across seven dimensions. While users explore these artifacts through the dashboard, the same artifacts are indexed into distinct vector database collections for agent retrieval and reasoning. This architecture establishes a human-AI common ground where users and AI can operate over shared representations. Evaluation results show that CLARA produces reliable collaboration quality analysis and, owing to the artifacts serving as knowledge infrastructure, 1

What carries the argument

The artifacts serving as knowledge infrastructure: concept maps of ideas and relationships together with seven-dimension collaboration assessments, which are simultaneously presented to users and indexed for AI retrieval to create shared representations.

If this is right

CLARA produces reliable collaboration quality analysis from discussion transcripts.
Indexing the artifacts into vector collections improves retrieval performance compared to transcript-only baselines.
Response quality from AI agents rises when they reason over the artifacts rather than raw text.
The artifacts act as knowledge infrastructure that scaffolds both human interpretation and AI reasoning in learning analytics.

Where Pith is reading between the lines

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

The same artifact approach could extend to real-time group settings outside education, such as project teams or meetings, if extraction remains stable.
If the seven-dimension assessments prove consistent, they might support automated feedback loops that help groups adjust their collaboration mid-discussion.
Connecting the artifacts to other data sources like logs of edits or contributions could create richer shared models without adding new collection steps.

Load-bearing premise

AI models can accurately extract semantic artifacts such as concept maps and collaboration assessments from transcripts without introducing substantial errors or biases that undermine the shared representations.

What would settle it

A direct comparison where human experts annotate the same transcripts for concepts and the seven dimensions, then measure agreement rates with the AI-extracted artifacts and check whether retrieval accuracy drops when the artifacts are removed.

Figures

Figures reproduced from arXiv: 2605.17259 by Bookyung Shin, Chenghong Lin, Dawei Xie, Khalil Anderson, Marcelo Worsley, Tochukwu Eze.

**Figure 1.** Figure 1: System Workflow. (A) CLARA transcribes discussion in real time, calculates psycholinguistic metrics, and prompts the LLM to produce collaboration assessments and concept maps; (B) Transcripts and artifacts are embedded and indexed in distinct database collections; (C) Users can interact with LLM-produced artifacts through the dashboard; (D) The CLARA Agent reasons and iteratively calls tools to query diffe… view at source ↗

read the original abstract

Collaboration literacy requires adapting to the evolving demands of group work within complex discussions, making it difficult to develop and assess. Traditional analytics metrics capture behavioral signals while missing the semantic dimensions of how learners approach collaboration and build on each other's ideas. We present Collaboration Literacy through Artifact Reasoning and Augmentation (CLARA), an agentic analytics system that extracts semantic representations from transcripts as analytics artifacts: concept maps representing emergent ideas and relationships, and collaboration assessment characterizing collaboration quality across seven dimensions. While users explore these artifacts through the dashboard, the same artifacts are indexed into distinct vector database collections for agent retrieval and reasoning. This architecture establishes a human-AI common ground where users and AI can operate over shared representations. Evaluation results show that CLARA produces reliable collaboration quality analysis and, owing to the artifacts serving as knowledge infrastructure, improves both retrieval performance and response quality over transcript-only baselines. Our work suggests that AI-produced artifacts may scaffold human interpretation and ground AI reasoning in learning analytics workflows.

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.

Desk Editor's Note private letter to a colleague

CLARA builds a dashboard and retrieval system around AI-extracted concept maps and seven-dimension collaboration scores, but the accuracy of those extractions is not validated in the reported work.

read the letter

The main takeaway is that CLARA turns discussion transcripts into concept maps and seven-dimension quality scores, then uses those artifacts both for a human dashboard and for agentic retrieval so that people and AI share the same representations. This is a concrete step beyond pure behavioral metrics in learning analytics. The architecture is laid out clearly enough that someone could replicate the basic flow of extraction, indexing, and dual use. The paper earns credit for identifying the gap in semantic depth and for showing how the same artifacts could ground both human interpretation and AI reasoning. Evaluation results are claimed to show reliable analysis plus gains over transcript-only baselines, which is the kind of outcome that would matter for education technology if it holds. The soft spot is exactly where the stress test flags it: there is no reported human validation, inter-rater agreement, or error analysis for the LLM-extracted concept maps and seven-dimension scores. Without that check, the central claim that the artifacts serve as reliable shared infrastructure cannot be assessed, and any reported retrieval or response improvements could be driven by other factors. The abstract supplies no sample sizes, metrics, or baseline details, so the data support remains thin. This work is for HCI and learning-analytics researchers who already think about team processes and agentic tools. A reader looking for a worked example of artifact-mediated human-AI common ground will find usable ideas even if the current evidence is preliminary. It deserves peer review so the extraction step can be properly tested and the evaluation expanded.

Referee Report

2 major / 1 minor

Summary. The manuscript presents CLARA, an agentic analytics system that extracts semantic artifacts from discussion transcripts—specifically concept maps for emergent ideas and relationships, plus collaboration quality assessments across seven dimensions. These artifacts are explored by users via a dashboard and simultaneously indexed into vector databases to support agent retrieval and reasoning, creating shared human-AI representations. The central claim is that this architecture yields reliable collaboration quality analysis and, by serving as knowledge infrastructure, improves retrieval performance and response quality relative to transcript-only baselines.

Significance. If the extraction accuracy and performance gains are substantiated, the work could meaningfully advance learning analytics by demonstrating how AI-generated semantic artifacts can scaffold human interpretation while grounding AI reasoning in shared representations. This addresses a gap between behavioral metrics and semantic dimensions of collaboration, with potential implications for collaborative learning platforms.

major comments (2)

[Abstract] Abstract: The claim that 'CLARA produces reliable collaboration quality analysis' lacks any reported evaluation details, including metrics, sample sizes, inter-rater agreement, expert validation, or error analysis for the LLM extraction of concept maps and seven-dimension assessments. This is load-bearing for the central claim, as unvalidated extraction errors or biases would prevent the artifacts from serving as reliable shared representations and would undermine attribution of any retrieval or response quality gains to the artifacts rather than the baseline transcripts.
[Abstract] Abstract: No baseline comparisons, statistical tests, or quantitative results are supplied to support the assertion of improved retrieval performance and response quality over transcript-only baselines. Without these, the performance advantage cannot be assessed or replicated.

minor comments (1)

[Abstract] The seven collaboration dimensions are referenced but not enumerated or defined, which would improve clarity for readers unfamiliar with the specific framework.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback, which highlights important aspects of how our evaluation claims are presented. We address each major comment below and have revised the manuscript to provide greater transparency on the evaluation details while preserving the core contributions.

read point-by-point responses

Referee: [Abstract] Abstract: The claim that 'CLARA produces reliable collaboration quality analysis' lacks any reported evaluation details, including metrics, sample sizes, inter-rater agreement, expert validation, or error analysis for the LLM extraction of concept maps and seven-dimension assessments. This is load-bearing for the central claim, as unvalidated extraction errors or biases would prevent the artifacts from serving as reliable shared representations and would undermine attribution of any retrieval or response quality gains to the artifacts rather than the baseline transcripts.

Authors: We agree that the abstract would be strengthened by summarizing key evaluation details. The full manuscript contains an evaluation study (with expert raters assessing collaboration quality on a corpus of discussion transcripts) that reports inter-rater agreement and validation procedures. We have revised the abstract to concisely include sample size, inter-rater agreement metrics, and a note on the validation approach. We have also expanded the main text with an explicit error analysis subsection addressing potential LLM biases in concept map and dimension extraction. revision: yes
Referee: [Abstract] Abstract: No baseline comparisons, statistical tests, or quantitative results are supplied to support the assertion of improved retrieval performance and response quality over transcript-only baselines. Without these, the performance advantage cannot be assessed or replicated.

Authors: The manuscript's evaluation section already presents quantitative comparisons against transcript-only baselines for both retrieval (e.g., precision/recall over vector indexes) and response quality (human-rated relevance). However, we acknowledge that explicit statistical tests and tabulated results were not foregrounded in the abstract. In the revision we have added specific quantitative deltas, baseline descriptions, and statistical significance tests (paired comparisons) to the abstract and evaluation section to support replicability and assessment of the claimed gains. revision: yes

Circularity Check

0 steps flagged

No significant circularity; claims grounded in independent evaluations

full rationale

The paper presents a system architecture for extracting concept maps and seven-dimension collaboration assessments from transcripts, then reports evaluation results showing improved retrieval and response quality over transcript-only baselines. No equations, self-definitional reductions, fitted parameters renamed as predictions, or load-bearing self-citations appear in the abstract or described derivation. The central claims rest on reported empirical comparisons that are external to the system's internal definitions, satisfying the criteria for a self-contained systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claims rest on assumptions about reliable AI semantic extraction from transcripts and the value of the generated artifacts as shared infrastructure; no free parameters or invented physical entities are described.

axioms (1)

domain assumption AI models can extract accurate concept maps and collaboration quality assessments from discussion transcripts
This underpins artifact creation and is invoked to support both human dashboard use and AI retrieval improvements.

invented entities (1)

Collaboration assessment across seven dimensions no independent evidence
purpose: To characterize collaboration quality as an analytics artifact
Introduced as part of the system output but no independent validation or external evidence is mentioned in the abstract.

pith-pipeline@v0.9.0 · 5709 in / 1230 out tokens · 43783 ms · 2026-05-19T23:20:54.490351+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

Foundation/RealityFromDistinction reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

artifact-grounded responses... improves both retrieval performance and response quality over transcript-only baselines

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

24 extracted references · 24 canonical work pages

[1]

Perspectives on socially shared cognition pp

Clark, H.H., Brennan, S.E.: Grounding in communication. Perspectives on socially shared cognition pp. 127–149 (1991)

work page 1991
[2]

Cukurova, M., Zhou, Q., Spikol, D., Landolfi, L.: Modelling collaborative problem- solving competence with transparent learning analytics: is video data enough? In: Proceedings of the tenth international conference on learning analytics & knowl- edge. pp. 270–275 (2020)

work page 2020
[3]

Computers and Education: Artificial Intelligence7, 100299 (2024)

Dai, W., Tsai, Y.S., Lin, J., Aldino, A., Jin, H., Li, T., Gašević, D., Chen, G.: As- sessing the proficiency of large language models in automatic feedback generation: An evaluation study. Computers and Education: Artificial Intelligence7, 100299 (2024)

work page 2024
[4]

Computers & Education46(1), 6–28 (2006)

De Wever, B., Schellens, T., Valcke, M., Van Keer, H.: Content analysis schemes to analyze transcripts of online asynchronous discussion groups: A review. Computers & Education46(1), 6–28 (2006)

work page 2006
[5]

Journal of Learning Analytics 12(1), 253–270 (Mar 2025)

Feng, S., Gibson, D., Gašević, D.: Analyzing students’ emerging roles based on quantity and heterogeneity of individual contributions in small group online col- laborative learning using bipartite network analysis. Journal of Learning Analytics 12(1), 253–270 (Mar 2025). https://doi.org/10.18608/jla.2025.8431

work page doi:10.18608/jla.2025.8431 2025
[6]

Journal of Intelligence5(2), 10 (2017)

Graesser, A., Kuo, B.C., Liao, C.H.: Complex problem solving in assessments of collaborative problem solving. Journal of Intelligence5(2), 10 (2017)

work page 2017
[7]

In: European Conference on Technology Enhanced Learning

Kahrimanis, G., Meier, A., Chounta, I.A., Voyiatzaki, E., Spada, H., Rummel, N., Avouris, N.: Assessing collaboration quality in synchronous cscl problem-solving activities: Adaptation and empirical evaluation of a rating scheme. In: European Conference on Technology Enhanced Learning. pp. 267–272. Springer (2009) CLARA: An AI-Augmented Analytics Dashboar...

work page 2009
[8]

Sage pub- lications (2018)

Krippendorff, K.: Content analysis: An introduction to its methodology. Sage pub- lications (2018)

work page 2018
[9]

Educational Research Review33, 100387 (2021)

Lämsä, J., Hämäläinen, R., Koskinen, P., Viiri, J., Lampi, E.: What do we do when we analyse the temporal aspects of computer-supported collaborative learning? a systematic literature review. Educational Research Review33, 100387 (2021)

work page 2021
[10]

Advances in Neural Information Processing Systems 33, 9459–9474 (2020)

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.t., Rocktäschel, T., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33, 9459–9474 (2020)

work page 2020
[11]

Computers and Edu- cation: Artificial Intelligence p

Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., Wang, F.L.: Retrieval-augmented generation for educational application: A systematic survey. Computers and Edu- cation: Artificial Intelligence p. 100417 (2025)

work page 2025
[12]

International Journal of Computer- Supported Collaborative Learning2(1), 63–86 (2007)

Meier, A., Spada, H., Rummel, N.: A rating scheme for assessing the quality of computer-supported collaboration processes. International Journal of Computer- Supported Collaborative Learning2(1), 63–86 (2007)

work page 2007
[13]

Computers and Education: Artificial Intelligence6, 100234 (2024)

Pack, A., Barrett, A., Escalante, J.: Large language models and automated essay scoring of english language learner writing: Insights into validity and reliability. Computers and Education: Artificial Intelligence6, 100234 (2024)

work page 2024
[14]

In: Findings of the Association for Computational Linguistics: NAACL 2025

Parfenova, A., Marfurt, A., Pfeffer, J., Denzler, A.: Text annotation via inductive coding: Comparing human experts to llms in qualitative data analysis. In: Findings of the Association for Computational Linguistics: NAACL 2025. pp. 6456–6469 (2025)

work page 2025
[15]

In: Proceedings of the 15th International Learning Analytics and Knowledge Conference

Scarlatos, A., Baker, R.S., Lan, A.: Exploring knowledge tracing in tutor-student dialogues using llms. In: Proceedings of the 15th International Learning Analytics and Knowledge Conference. pp. 249–259 (2025)

work page 2025
[16]

In: Educational Media and Technology Year- book: Volume 40, pp

Schneider, B., Pea, R.: Real-time mutual gaze perception enhances collaborative learning and collaboration quality. In: Educational Media and Technology Year- book: Volume 40, pp. 99–125. Springer (2016)

work page 2016
[17]

In: What we know about CSCL: And implementing it in higher education, pp

Stahl, G.: Building collaborative knowing: Elements of a social theory of cscl. In: What we know about CSCL: And implementing it in higher education, pp. 53–85. Springer (2004)

work page 2004
[18]

Strijbos, J.W., Martens, R.L., Prins, F.J., Jochems, W.M.: Content analysis: What are they talking about? Computers & Education46(1), 29–48 (2006)

work page 2006
[19]

Computers and Education: Artificial Intelligence p

Wang, Y., Huang, J., Du, L., Guo, Y., Liu, Y., Wang, R.: Evaluating large language models as raters in large-scale writing assessments: A psychometric framework for reliability and validity. Computers and Education: Artificial Intelligence p. 100481 (2025)

work page 2025
[20]

International Journal of Computer-Supported Collaborative Learning6(3), 445–470 (2011)

Wise, A.F., Chiu, M.M.: Analyzing temporal patterns of knowledge construction in a role-based online discussion. International Journal of Computer-Supported Collaborative Learning6(3), 445–470 (2011)

work page 2011
[21]

Journal of Learning Analytics8(1), 30–48 (2021)

Worsley, M., Anderson, K., Melo, N., Jang, J.: Designing analytics for collabora- tion literacy and student empowerment. Journal of Learning Analytics8(1), 30–48 (2021)

work page 2021
[22]

In: CrossMMLA@ LAK

Worsley, M., Ochoa, X.: Towards collaboration literacy development through mul- timodal learning analytics. In: CrossMMLA@ LAK. pp. 53–63 (2020)

work page 2020
[23]

In: The Eleventh Interna- tional Conference on Learning Representations (2023)

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K.R., Cao, Y.: React: Synergizing reasoning and acting in language models. In: The Eleventh Interna- tional Conference on Learning Representations (2023)

work page 2023
[24]

Advances in Neural Information Processing Systems36, 46595–46623 (2023)

Zheng, L., Chiang, W.L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems36, 46595–46623 (2023)

work page 2023

[1] [1]

Perspectives on socially shared cognition pp

Clark, H.H., Brennan, S.E.: Grounding in communication. Perspectives on socially shared cognition pp. 127–149 (1991)

work page 1991

[2] [2]

Cukurova, M., Zhou, Q., Spikol, D., Landolfi, L.: Modelling collaborative problem- solving competence with transparent learning analytics: is video data enough? In: Proceedings of the tenth international conference on learning analytics & knowl- edge. pp. 270–275 (2020)

work page 2020

[3] [3]

Computers and Education: Artificial Intelligence7, 100299 (2024)

Dai, W., Tsai, Y.S., Lin, J., Aldino, A., Jin, H., Li, T., Gašević, D., Chen, G.: As- sessing the proficiency of large language models in automatic feedback generation: An evaluation study. Computers and Education: Artificial Intelligence7, 100299 (2024)

work page 2024

[4] [4]

Computers & Education46(1), 6–28 (2006)

De Wever, B., Schellens, T., Valcke, M., Van Keer, H.: Content analysis schemes to analyze transcripts of online asynchronous discussion groups: A review. Computers & Education46(1), 6–28 (2006)

work page 2006

[5] [5]

Journal of Learning Analytics 12(1), 253–270 (Mar 2025)

Feng, S., Gibson, D., Gašević, D.: Analyzing students’ emerging roles based on quantity and heterogeneity of individual contributions in small group online col- laborative learning using bipartite network analysis. Journal of Learning Analytics 12(1), 253–270 (Mar 2025). https://doi.org/10.18608/jla.2025.8431

work page doi:10.18608/jla.2025.8431 2025

[6] [6]

Journal of Intelligence5(2), 10 (2017)

Graesser, A., Kuo, B.C., Liao, C.H.: Complex problem solving in assessments of collaborative problem solving. Journal of Intelligence5(2), 10 (2017)

work page 2017

[7] [7]

In: European Conference on Technology Enhanced Learning

Kahrimanis, G., Meier, A., Chounta, I.A., Voyiatzaki, E., Spada, H., Rummel, N., Avouris, N.: Assessing collaboration quality in synchronous cscl problem-solving activities: Adaptation and empirical evaluation of a rating scheme. In: European Conference on Technology Enhanced Learning. pp. 267–272. Springer (2009) CLARA: An AI-Augmented Analytics Dashboar...

work page 2009

[8] [8]

Sage pub- lications (2018)

Krippendorff, K.: Content analysis: An introduction to its methodology. Sage pub- lications (2018)

work page 2018

[9] [9]

Educational Research Review33, 100387 (2021)

Lämsä, J., Hämäläinen, R., Koskinen, P., Viiri, J., Lampi, E.: What do we do when we analyse the temporal aspects of computer-supported collaborative learning? a systematic literature review. Educational Research Review33, 100387 (2021)

work page 2021

[10] [10]

Advances in Neural Information Processing Systems 33, 9459–9474 (2020)

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.t., Rocktäschel, T., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33, 9459–9474 (2020)

work page 2020

[11] [11]

Computers and Edu- cation: Artificial Intelligence p

Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., Wang, F.L.: Retrieval-augmented generation for educational application: A systematic survey. Computers and Edu- cation: Artificial Intelligence p. 100417 (2025)

work page 2025

[12] [12]

International Journal of Computer- Supported Collaborative Learning2(1), 63–86 (2007)

Meier, A., Spada, H., Rummel, N.: A rating scheme for assessing the quality of computer-supported collaboration processes. International Journal of Computer- Supported Collaborative Learning2(1), 63–86 (2007)

work page 2007

[13] [13]

Computers and Education: Artificial Intelligence6, 100234 (2024)

Pack, A., Barrett, A., Escalante, J.: Large language models and automated essay scoring of english language learner writing: Insights into validity and reliability. Computers and Education: Artificial Intelligence6, 100234 (2024)

work page 2024

[14] [14]

In: Findings of the Association for Computational Linguistics: NAACL 2025

Parfenova, A., Marfurt, A., Pfeffer, J., Denzler, A.: Text annotation via inductive coding: Comparing human experts to llms in qualitative data analysis. In: Findings of the Association for Computational Linguistics: NAACL 2025. pp. 6456–6469 (2025)

work page 2025

[15] [15]

In: Proceedings of the 15th International Learning Analytics and Knowledge Conference

Scarlatos, A., Baker, R.S., Lan, A.: Exploring knowledge tracing in tutor-student dialogues using llms. In: Proceedings of the 15th International Learning Analytics and Knowledge Conference. pp. 249–259 (2025)

work page 2025

[16] [16]

In: Educational Media and Technology Year- book: Volume 40, pp

Schneider, B., Pea, R.: Real-time mutual gaze perception enhances collaborative learning and collaboration quality. In: Educational Media and Technology Year- book: Volume 40, pp. 99–125. Springer (2016)

work page 2016

[17] [17]

In: What we know about CSCL: And implementing it in higher education, pp

Stahl, G.: Building collaborative knowing: Elements of a social theory of cscl. In: What we know about CSCL: And implementing it in higher education, pp. 53–85. Springer (2004)

work page 2004

[18] [18]

Strijbos, J.W., Martens, R.L., Prins, F.J., Jochems, W.M.: Content analysis: What are they talking about? Computers & Education46(1), 29–48 (2006)

work page 2006

[19] [19]

Computers and Education: Artificial Intelligence p

Wang, Y., Huang, J., Du, L., Guo, Y., Liu, Y., Wang, R.: Evaluating large language models as raters in large-scale writing assessments: A psychometric framework for reliability and validity. Computers and Education: Artificial Intelligence p. 100481 (2025)

work page 2025

[20] [20]

International Journal of Computer-Supported Collaborative Learning6(3), 445–470 (2011)

Wise, A.F., Chiu, M.M.: Analyzing temporal patterns of knowledge construction in a role-based online discussion. International Journal of Computer-Supported Collaborative Learning6(3), 445–470 (2011)

work page 2011

[21] [21]

Journal of Learning Analytics8(1), 30–48 (2021)

Worsley, M., Anderson, K., Melo, N., Jang, J.: Designing analytics for collabora- tion literacy and student empowerment. Journal of Learning Analytics8(1), 30–48 (2021)

work page 2021

[22] [22]

In: CrossMMLA@ LAK

Worsley, M., Ochoa, X.: Towards collaboration literacy development through mul- timodal learning analytics. In: CrossMMLA@ LAK. pp. 53–63 (2020)

work page 2020

[23] [23]

In: The Eleventh Interna- tional Conference on Learning Representations (2023)

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K.R., Cao, Y.: React: Synergizing reasoning and acting in language models. In: The Eleventh Interna- tional Conference on Learning Representations (2023)

work page 2023

[24] [24]

Advances in Neural Information Processing Systems36, 46595–46623 (2023)

Zheng, L., Chiang, W.L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems36, 46595–46623 (2023)

work page 2023