phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | learning with AI-generated explanations of proportional relationships— “The study assesses the impact of AI-generated learning materials on the learning experiences and performance of sixthgrade students, with a particular focus on proportional relationships in mathematical and physical contexts.” | |
| claim-type | existence— “The results demonstrated that while AI-generated materials had an indefinite impact on learning outcomes, they significantly enhanced positive-activating emotions, situational interest, and self-efficacy, while reducing intrinsic and extrinsic cognitive load.” | |
| method — evidence | — “The randomized controlled study with N = 214 students compared traditional textbook materials with explanations generated by a custom chatbot.” | |
| mechanism | The chatbot's encouraging, motivating tone raises situational interest relative to neutral textbook prose— “One potential explanation for this outcome is the nature of the custom chatbot's tone, which is designed to be encouraging and motivating.” | mechanisms[0] |
| mechanism | Accessible, conversational, human-like wording in the AI explanation lowers the processing demands of the material and so reduces cognitive load— “One to potential explanation for this outcome is the use of accessible language and a conversational and humanlike tone in the chatbot's responses.” | mechanisms[1] |
| mechanism | Encouraging tone and/or the lowered cognitive load raise students' confidence that they can solve the task themselves— “A reason for this may be the encouraging tone of the AI-generated text or the reduced cognitive load, or a combination of both.” | mechanisms[2] |
| mechanism | Because students never used the chatbot themselves, individual learning difficulties were never diagnosed or addressed, blunting any performance effect— “It is possible that the lack of independent use of the chatbot in this study may have contributed to the observed outcomes, as it prevented the identification and addressing of individual learning difficulties.” | mechanisms[3] |
| replicates | previous research on emotions in chatbot-supported learning (reference [29])— “This finding is consistent with the results of previous research [29].” | claim_relations[0] |
| sense | effect on learning outcomes - AS THE ABSTRACT PUTS IT: an indefinite impact, stated in the same sentence as the significant gains in emotion, interest and self-efficacy— “The results demonstrated that while AI-generated materials had an indefinite impact on learning outcomes, they significantly enhanced positive-activating emotions, situational interest, and self-efficacy, while reducing intrinsic and extrinsic cognitive load.” | senses[0] |
| sense | effect on learning outcomes - AS THE CONCLUSION PUTS IT: no notable differences in the performance test, and the influence remains unclear— “Nevertheless, the influence on learning outcomes remains unclear. No notable differences in the overall result of the performance test could be identified.” | senses[1] |
| sense | custom chatbot - a configured instance of a vendor's LLM, which the paper notes OpenAI designates by a different name— “The custom chatbots at OpenAI are designated as GPTs.” | senses[2] |
| control | instructing students who did not complete a task to select GUESS, so those responses are dropped from the evaluation — held — rules out non-attempts entering the scored set and being read as wrong answers or as performance— “In the interest of ensuring the integrity of the evaluation process, students who have not completed a task are instructed to select “guess” to exclude their responses from being considered during the subsequent evaluation.” | controls[0] |
| edge | custom chatbots —same-as→ GPTs— “The custom chatbots at OpenAI are designated as GPTs.” | concept_edges[0] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — the generalisation of every result: THE SIZE OF THE SAMPLE AND THE BRIEF IMPLEMENTATION PERIOD (SNAPSHOT) AS WELL AS THE NECESSITY OF SELECTING A PA[rticular topic and group]— “The generalizability of the results is constrained by different factors: the size of the sample and the brief implementation period (snapshot) as well as the necessity of selecting a particular topic for a specific target group.” | limitations[0] |
| for which use | limitation — what the intervention actually was: THE LEARNING MATERIALS WERE PROVIDED IN A CENTRALIZED MANNER, WHICH RESULTED IN THE LACK OF CONSIDERATION FOR INDIVIDUAL DIFFERENCES IN UTILIZATION - the students did not use the chatbot themselves— “Additionally, the learning materials were provided in a centralized manner, which resulted in the lack of consideration for individual differences in utilization and the potential for interaction with the chatbot.” | limitations[1] |
| for which use | limitation — the learning-outcome question specifically: IT IS NOT POSSIBLE TO PROVIDE A DEFINITIVE ANSWER TO RQ5 BASED ON THE DATA COLLECTED IN THIS STUDY— “It is not possible to provide a definitive answer to RQ5 based on the data collected in this study.” | limitations[2] |
| for which use | limitation — the claim that AI-generated materials improve learning: the conclusion states no notable differences were identified in the performance test and that the influence remains unclear— “Nevertheless, the influence on learning outcomes remains unclear. No notable differences in the overall result of the performance test could be identified.” | limitations[3] |
| for which use | limitation — extending these results to AI-generated materials in general: the authors name sample size, a brief implementation period they call a snapshot, and the particular topic and target group— “The generalizability of the results is constrained by different factors: the size of the sample and the brief implementation period (snapshot) as well as the necessity of selecting a particular topic for a specific target group.” | limitations[4] |
| for which use | limitation — retrieval-augmented generation as a fix for factual error in these materials: the paper states it reduces the risk of hallucinations rather than removing it— “The reliance on external documents reduces the risk of hallucinations” | limitations[5] |
| evidential status | mechanism — the paper's own words: It is possible that— “It is possible that the lack of independent use of the chatbot in this study may have contributed to the observed outcomes, as it prevented the identification and addressing of individual learning difficulties.” | mechanisms[3] |
| replication | untested | |
| limitation | Generalizability is limited by sample size, the snapshot implementation period, and the single topic and target group chosen.— “The generalizability of the results is constrained by different factors: the size of the sample and the brief implementation period (snapshot) as well as the necessity of selecting a particular topic for a specific target group.” | limitations[0] |
| limitation | Materials were delivered centrally, so students never interacted with the chatbot themselves and individual differences in use could not be captured.— “Additionally, the learning materials were provided in a centralized manner, which resulted in the lack of consideration for individual differences in utilization and the potential for interaction with the chatbot.” | limitations[1] |
| limitation | The performance data are too thin to support a conclusion about learning outcomes.— “It is not possible to provide a definitive answer to RQ5 based on the data collected in this study.” | limitations[2] |
| limitation | The primary outcome did not move, and the conclusion says so plainly while the abstract calls the same result indefinite.— “Nevertheless, the influence on learning outcomes remains unclear. No notable… | limitations[3] |
| limitation | Generalisability is constrained by three named factors, including the brief period, which the authors themselves call a snapshot. | limitations[4] |
| limitation | The mechanism relied on to keep answers accurate is stated as a reduction in risk, not a guarantee. | limitations[5] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | Sixth-graders who learned from a custom-chatbot-generated explanation reported more positive-activating emotions, more situational interest and higher self-efficacy, and lower intrinsic and extrinsic cognitive load, than those who learned from textbook material, while learning outcomes showed no clear effect. | content_tags.findings[0] |
| finding | The two groups did not differ on the overall score of the performance test. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[1] |
| finding | On two values of the tabular subtask B the control group scored significantly higher than the AI-material group. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[2] |
| finding | On subtask C the AI-material group scored significantly higher. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[3] |
| finding | The two groups were equivalent in prior interest in mathematics before the intervention. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[4] |
| finding | The reduction in cognitive load in the experimental group did not carry over into any measurable performance gain on the achievement test. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[5] |
| quantity | N = 214 — number of sixth-grade German secondary-school students in the randomized controlled study Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[0] |
| quantity | 11.7 years (SD = 0.51) — mean age of the participating students Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[1] |
| quantity | 15 minutes — learning time allotted identically to both groups Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[2] |
| quantity | 30 minutes — time allowed for the performance test measuring learning and transfer Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[3] |
| quantity | = 0.8469 — mean weighted-kappa inter-rater agreement across the rating categories for subtask D Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[4] |
| quantity | M = 2.24; SD = 0.88 vs M = 2.38; SD = 0.95 — last-term mathematics report-card grades of the control group versus the experimental group (German scale, 1 = best) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[5] |
| quantity | GPT-4.0 — the OpenAI base model the custom chatbot was configured on Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[6] |
| variable | type of learning material (independent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[0] |
| variable | conventional textbook material (independent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[1] |
| variable | emotions (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[2] |
| variable | situational interest (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[3] |
| variable | intrinsic and extrinsic cognitive load (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[4] |
| variable | self-efficacy expectation (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[5] |
| variable | learning time (control) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[7] |
| variable | Subject-specific interest (control) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[9] |
| variable | learning performance (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[10] |
| variable | transfer (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[11] |
| definition | Large Language Models (LLMs) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[0] |
| definition | chatbots Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[1] |
| definition | Retrieval Augmented Generation (RAG) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[2] |
| definition | multiple representations Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[3] |
| definition | GPTs Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[4] |
| concept | custom chatbots Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[0] |
| concept | GPTs Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[1] |
| concept | cognitive load Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[2] |
| Cronbach's alpha α | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[0] |
| Shapiro-Wilk normality test p | as written: Shapiro-Wilk test Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
| Mann-Whitney U test | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[2] |
| effect size (Cohen's d) d | as written: Cohen's d Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[3] |
| inter-rater reliability (weighted kappa) kappa | as written: Cohen's weighted kappa Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[4] |
| standard deviation SD | as written: SD Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[5] |
| mean M | as written: M Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[6] |
When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824