Overall, I like the theoretically-grounded framework for assessment of argumentation ability proposed in the paper. However, I have a couple of suggestions to further strengthen this work:

(i) It is not clear from the reading of the paper how this work differs both theoretically and practically/methodologically from prior research on argumentation in learning. The rationale for why a particular argumentation framework (among others) was chosen as the basis for development of the learning materials is unclear. Please refer to this recent work to clarify your theoretical/methodological stance

Schwarz, B. B., & Baker, M. J. (2016). Dialogue, argumentation and education: History, theory and practice. Cambridge University Press.

(ii) From my understanding, it seems that the online environment had different kinds of built-in cognitive and metacognitive scaffolding, and that students in the experimental group were also paired based on a macro- collaboration script (jigsaw, opposing opinions). On the other hand, control group students (most probably) did not have any such scaffolding.

Findings of the paper suggest greater improvement in content knowledge, argumentation skills, and modes of argumentation in the experimental group. Since both groups followed the IPadE learning paradigm, it seems to me then that the reason for the pattern of the results is confounded between (i) affordances of online versus offline/face-to-face learning, (ii) the differential impact of particular aspects of online scaffolding tools on your outcome variables.

I see no (very little) tangential discussion of these two critical aspects of your study in the paper. Most of the initial sections motivate need for developing and analyzing argumentation skills as something that is critical to today's schooling (which is fine, but can be dramatically shortened). Rather the paper should closely tie together related "relevant" prior work, and tie it to the design rationales for the learning materials. I would also suggest to add a clear and separate description of the experimental and control group design features.

(iii) What are the mechanisms/mediating processes due to which students in the experimental group outperformed the control group? Are these processes related to the activity design (choice of learning topic, task setup, presence of scaffolding), participation structure (individual work followed by collaborative work), or the social surround (framing of the activity within the classroom norms)? There is no discussion about the pattern of obtained results, and I would encourage the authors to re-look at the process-data to obtain "testable hypotheses" for the effects reported.

(iv) Finally, it is also not very clear from the writing, what aspect of "personalization" did the online argumentation tool (for students in the experimental condition) have, and hoe did you study/test the impact of personalization in this work?