Building Bridges: AI Custom Chatbots as Mediators between Mathematics and Physics

Lademann, Henze, Becker-Genschow · 2024 · physics-education-research · 10.48550/arxiv.2412.15747 · record lademann2024-building-bridges-ai-custom-chatbot
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. Claim type 'existence' was chosen for the paper's headline claim (these effects on learning experience occur), but the paper is genuinely mixed: the learning-performance arm is a null result ('No notable differences in the overall result of the performance test could be identified') and two subtask values even favoured the control group. A single facet cannot hold both, so the null component is flagged here. The one claim_relation targets a numbered reference [29] rather than a named author, because this arXiv extraction uses numeric citations throughout; the relation itself is explicit ('consistent with'), not inferred from a bare citation. Other self-relations in the discussion (e.g. the self-efficacy result and Canonigo's mathematics findings) came through the PDF extraction with the author name displaced into a neighbouring column, so they were left out rather than reconstructed. 2026-08-13 and 2026-08-14 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. 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.

Other fields define these differently the same word, defined another way in another discipline
cognitive load 3 fields · standard deviation 3 fields · transfer 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 3 concept tags on this paper, all 3 are grounded in a quoted sentence.

custom chatbots GPTs cognitive load The chatbot's encouraging, motivating tone raises situational interest relative to neutral textbook prose Accessible, conversational, human-like wording in the AI explanation lowers the processing demands of the material and so reduces cognitive load Encouraging tone and/or the lowered cognitive load raise students' confidence that they can solve the task themselves Because students never used the chatbot themselves, individual learning difficulties were never diagnosed or addressed, blunting any performance effect Large Language Models (LLMs) chatbots Retrieval Augmented Generation (RAG) multiple representations type of learning material conventional textbook material emotions situational interest intrinsic and extrinsic cognitive load self-efficacy expectation learning time Subject-specific interest learning performance transfer Cronbach's alpha Shapiro-Wilk normality test Shapiro-Wilk test Mann-Whitney U test effect size (Cohen's d) Cohen's d inter-rater reliability (weighted kappa) Cohen's weighted kappa standard deviation mean behavioural-experiment

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.48550/arxiv.2412.15747. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 1 · claim_type 1 · concept_edges 1 · concepts 3 · content_tags 35 · controls 1 · limitations 6 · mechanisms 4 · method 1 · phenomenon 1 · senses 3

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 1 relation here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	existence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	learning with AI-generated explanations of proportional relationships Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	behavioural-experiment Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: behavioural-experiment	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: The chatbot's encouraging, motivating tone raises situational interest relative to neutral textbook prose	`mechanisms[0]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Accessible, conversational, human-like wording in the AI explanation lowers the processing demands of the material and so reduces cognitive load	`mechanisms[1]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Encouraging tone and/or the lowered cognitive load raise students' confidence that they can solve the task themselves	`mechanisms[2]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. status: the paper's own words: It is possible that also in: Because students never used the chatbot themselves, individual learning difficulties were never diagnosed or addressed, blunting any performance effect	`mechanisms[3]`		the tagger's words
limitations	Generalizability is limited by sample size, the snapshot implementation period, and the single topic and target group chosen. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: 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]	`limitations[0]`		the tagger's words
limitations	Materials were delivered centrally, so students never interacted with the chatbot themselves and individual differences in use could not be captured. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: 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	`limitations[1]`		the tagger's words
limitations	The performance data are too thin to support a conclusion about learning outcomes. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the learning-outcome question specifically: IT IS NOT POSSIBLE TO PROVIDE A DEFINITIVE ANSWER TO RQ5 BASED ON THE DATA COLLECTED IN THIS STUDY	`limitations[2]`		the tagger's words
limitations	The primary outcome did not move, and the conclusion says so plainly while the abstract calls the same result indefinite. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: 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	`limitations[3]`	1.0	the tagger's words
limitations	Generalisability is constrained by three named factors, including the brief period, which the authors themselves call a snapshot. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: 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	`limitations[4]`	1.0	the tagger's words
limitations	The mechanism relied on to keep answers accurate is stated as a reduction in risk, not a guarantee. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: 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	`limitations[5]`	1.0	the tagger's words
controls	instructing students who did not complete a task to select GUESS, so those responses are dropped from the evaluation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: non-attempts entering the scored set and being read as wrong answers or as performance · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.85	the tagger's words
concepts	custom chatbots Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: custom chatbots	`concepts[0]`		the paper's words
concepts	GPTs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: GPTs	`concepts[1]`		the paper's words
concepts	cognitive load Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cognitive load	`concepts[2]`		the paper's words
senses	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 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	effect on learning outcomes - AS THE CONCLUSION PUTS IT: no notable differences in the performance test, and the influence remains unclear Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	custom chatbot - a configured instance of a vendor's LLM, which the paper notes OpenAI designates by a different name Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	replicates → previous research on emotions in chatbot-supported learning (reference [29]) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
concept_edges	custom chatbots —same-as→ GPTs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: custom chatbots · GPTs	`concept_edges[0]`		the tagger's words
content_tags	Cronbach's alpha Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Cronbach's alpha	`content_tags.statistics[0]`		the tagger's words
content_tags	Shapiro-Wilk normality test Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Shapiro-Wilk normality test	`content_tags.statistics[1]`		the tagger's words
content_tags	Mann-Whitney U test Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Mann-Whitney U test	`content_tags.statistics[2]`		the tagger's words
content_tags	effect size (Cohen's d) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: effect size (Cohen's d)	`content_tags.statistics[3]`		the tagger's words
content_tags	inter-rater reliability (weighted kappa) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inter-rater reliability (weighted kappa)	`content_tags.statistics[4]`		the tagger's words
content_tags	standard deviation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: standard deviation	`content_tags.statistics[5]`		the tagger's words
content_tags	mean Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: mean	`content_tags.statistics[6]`		the tagger's words
content_tags	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. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`		the tagger's words
content_tags	The two groups did not differ on the overall score of the performance test. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	On two values of the tabular subtask B the control group scored significantly higher than the AI-material group. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`		the tagger's words
content_tags	On subtask C the AI-material group scored significantly higher. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[3]`		the tagger's words
content_tags	The two groups were equivalent in prior interest in mathematics before the intervention. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[4]`		the tagger's words
content_tags	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 record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[5]`		the tagger's words
content_tags	Large Language Models (LLMs) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Large Language Models (LLMs)	`content_tags.definitions[0]`		the tagger's words
content_tags	chatbots Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: chatbots	`content_tags.definitions[1]`		the tagger's words
content_tags	Retrieval Augmented Generation (RAG) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Retrieval Augmented Generation (RAG)	`content_tags.definitions[2]`		the tagger's words
content_tags	multiple representations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: multiple representations	`content_tags.definitions[3]`		the tagger's words
content_tags	GPTs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: GPTs	`content_tags.definitions[4]`		the tagger's words
content_tags	type of learning material Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: type of learning material	`content_tags.variables[0]`		the tagger's words
content_tags	conventional textbook material Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: conventional textbook material	`content_tags.variables[1]`		the tagger's words
content_tags	emotions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: emotions	`content_tags.variables[2]`		the tagger's words
content_tags	situational interest Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: situational interest	`content_tags.variables[3]`		the tagger's words
content_tags	intrinsic and extrinsic cognitive load Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: intrinsic and extrinsic cognitive load	`content_tags.variables[4]`		the tagger's words
content_tags	self-efficacy expectation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: self-efficacy expectation	`content_tags.variables[5]`		the tagger's words
content_tags	learning time Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learning time	`content_tags.variables[7]`		the tagger's words
content_tags	Subject-specific interest Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Subject-specific interest	`content_tags.variables[9]`		the tagger's words
content_tags	learning performance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learning performance	`content_tags.variables[10]`		the tagger's words
content_tags	transfer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transfer	`content_tags.variables[11]`		the tagger's words
content_tags	N = 214 — number of sixth-grade German secondary-school students in the randomized controlled study Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	11.7 years (SD = 0.51) — mean age of the participating students Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	15 minutes — learning time allotted identically to both groups Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[2]`		the tagger's words
content_tags	30 minutes — time allowed for the performance test measuring learning and transfer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[3]`		the tagger's words
content_tags	= 0.8469 — mean weighted-kappa inter-rater agreement across the rating categories for subtask D Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[4]`		the tagger's words
content_tags	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 record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[5]`		the tagger's words
content_tags	GPT-4.0 — the OpenAI base model the custom chatbot was configured on Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[6]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.