Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0220
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-14T07:27:11.350603Z
status: published
lens: g_space
sector: education
headline: The effects of AI-based visual instruction on the reading comprehension of students with dyslexia in Saudi Arabia: a single-case experimental study
dek: Students with learning disabilities (LD), particularly dyslexia, often face significant challenges in reading comprehension that traditional instruction may not fully address. Generative Artificial Intelligence (GenAI) offers emerging opportunities to provide personalised and visual instructional support to bridge these gaps. This study investigated the effectiveness of a GenAI-based visual instruction to support the reading comprehension skills of students with dyslexia. A single-case experimental design using…
gain_title: Three elementary students with dyslexia improved from low baseline reading comprehension to mastery and maintained gains after GenAI-based visual instruction using ChatGPT-generated visuals aligned to their Arabic coursebook.
problem_title: (none)
trace_subject: (none)
gain_reading: Three elementary students with dyslexia improved from low baseline reading comprehension to mastery and maintained gains after GenAI-based visual instruction using ChatGPT-generated visuals aligned to their Arabic coursebook.
gain_evidence: all three students showed sustained performance at or above mastery | All participants started with an initial low and stable baseline (0%–10%)
problem_reading: (none)
problem_evidence: (none)
quick_read: In a 2026 single-case study in Yanbu, Saudi Arabia, three male elementary students aged 9-11 with dyslexia received GenAI-based visual instruction using ChatGPT-generated visual explanations aligned to their Grade 4 Arabic coursebook. After starting at 0%-10% on comprehension quizzes, they reached 80% or higher across three consecutive sessions and sustained that level in maintenance probes weeks later.

The result matters because it suggests low-cost generative visuals can supplement traditional instruction for a population that often struggles with text-only materials, but the evidence remains preliminary. With only three participants from one school, all male and assessed on coursebook-specific paragraphs, it is unclear whether gains transfer to other texts, languages, ages, or classroom contexts.
limitation: Findings are preliminary and limited to three male students aged 9-11 from one public elementary school in Yanbu, using a single-case design, which constrains generalizability to broader dyslexia populations and settings.
tag: Evidence-backed gain
key_points: Single-case multiple-probe design with three male students aged 9-11 diagnosed with dyslexia in a public elementary school in Yanbu city, Saudi Arabia. | Intervention used ChatGPT-generated visual explanations aligned with the Grade 4 Arabic language coursebook and five-point quizzes on coursebook paragraphs. | Mastery defined as 80% or higher on assessments in three consecutive sessions, with maintenance probes conducted several weeks after intervention.
rundown: Researchers implemented a multiple-probe across participants design with three boys aged 9-11 diagnosed with dyslexia at a public elementary school in Yanbu. The intervention delivered ChatGPT-generated visual explanations tied to Grade 4 Arabic language coursebook paragraphs, assessed with five-point quizzes.

Visual analysis showed a strong functional relation with minimal or no phase overlap between baseline and treatment. Two students showed immediate level changes, the third an accelerating trend, and all maintained performance at or above the 80% mastery criterion weeks later.
sources:
- peer_reviewed | Frontiers in Education | https://doi.org/10.3389/feduc.2026.1727782 | 2026-04-01
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

f1e7857711754b7e5933a55515b0df6bba993293433efe27ae0559f65d260f39

previous

0000000000000000000000000000000000000000000000000000000000000000