Both hint conditions took more time-on-task than control, but ChatGPT and human tutor conditions did not differ in session time¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q3 i? Session times differed significantly by condition (p < 0.001); both hint conditions had higher times than control (p < 0.001) but were not separable from one another (p = 0.614). → Pardos ZA 2024

Evidence¶

Pardos ZA 2024¶

Pardos ZA, Bhandari S (2024) ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills. PLoS ONE 19(5): e0304013. https://doi.org/10.1371/journal.pone.0304013

q3 · i? · causal · r2

Time-on-task analysis of session times in the randomized experiment, using Kruskal-Wallis followed by Mann Whitney U tests. The article reports the two hint conditions "were not separable from one another (p = 0.614)"; no effect size is printed.

"Both hint conditions had higher times than the control (p «0.001) but were not separable from one another (p = 0.614)."

Discussion¶

Learner Variables¶

Time and Continuity — outcome: instruction changes it

Learning gains from ChatGPT-generated hints were not statistically significantly different from human tutor-authored hints, though ChatGPT gains were numerically higher in all subjects — related
Learners receiving ChatGPT-generated hints showed statistically significant learning gains compared to a no-hint control in an online mathematics tutoring experiment — related
Adaptive-condition students complete the posttest in significantly less time than Control students — related
BKT students completed posttest problems significantly faster than Control students, with DRL showing marginal advantages in time and solution optimality — related
Human-AI tutoring increases IXL time on task by 25% with no significant difference between proactive and reactive groups — related
Participants deprived of relevant relational knowledge in Stage 1 take longer on the subsequent network-reasoning task — related
Low-guidance set-ups took longer than high-guidance set-ups in the CVS instruction sessions — related

Page metadata

Field	Value
`type`	`claim`
`id`	`hint-conditions-time-on-task`
`title`	`Both hint conditions took more time-on-task than control, but ChatGPT and human tutor conditions did not differ in session time`
`description`	`Both hint conditions took more time-on-task than control, but ChatGPT and human tutor conditions did not differ in session time`
`status`	`review`
`evidence_strength`	`moderate`
`newest_evidence`	`2024`
`generated`	by `process:wiki-ingest` on `2026-10-10`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `pardos-za-2024`

Frontmatter is the page's machine-readable record — see the Schema & Guide.