Systematic Review Flow (PRISMA 2020)
Transparent flow of article identification, LLM screening, full-text eligibility assessment, and inclusion into living synthesis with expert validation.
✓ PRISMA funnel conservation verified (100% stage closure)
Zero data leakage: n_in = n_out + ∑n_excl + n_pending verified across identification, screening, eligibility, and synthesis.
ID: 14636 →
Screen: 13766 →
Eligible: 2108 →
Included: 66
Expert Validation & Taste Loop
Independent of the formal PRISMA selection rules: editorial verdicts by the curator to calibrate quality and active learning.
👍 10
Approved in digest
(14 total in corpus)
👎 29
Rejected with reason
(1 pre / 18 post analysis)
Breakdown of expert rejection reasons:
not_novel: 4
not_for_educators: 3
off_topic: 13
too_narrow: 2
duplicate: 5
other: 1
weak_method: 1
📋 Structured Review Summary (PRISMA 2020: Item 2)
Background: Living systematic review of Large Language Models (LLMs) and autonomous agents in higher education. Focuses on engineering countermeasures to academic dishonesty and redesign of assessment.
Objectives: Systematic identification, screening, and synthesis of empirical evidence regarding reliability, methodological rigor, and consensus challenges in higher education GenAI integration.
Eligibility Criteria: Scholarly works with open-access full text; topic relevance R ≥ 4.0; weighted final score ≥ 5.0.
Information Sources: Multi-register tracking: arXiv, Crossref, OpenAlex, Semantic Scholar, ERIC, plus forward/backward citation loops (depth 1–2).
Risk of Bias & Quality: Multi-criteria methodological rigor (M, 0–10). Screening reliability validated via dual evaluation: Gwet's AC1, stratified recall, and ROC AUC.
Synthesis & Included: Included n = 66 verified works into the living review with extracted claims, limitations, and empirical findings.
🎯 PICO / PECO Search & Eligibility Framework (PRISMA 2020: Items 4–5)
| Component | Protocol Definition | Inclusion / Exclusion Boundaries |
|---|---|---|
| P (Population) | Higher education: universities, colleges, undergraduate/graduate students, instructors, and examiners. | Included: higher/tertiary education. Excluded: purely K-12 primary education without transferability. |
| I / E (Intervention / Exposure) | Use of modern LLMs (GPT-4, Claude, Gemini, Llama) and agentic frameworks for exam solving, tutoring, or automated grading. | Included: empirical testing and deployment of LLMs. Excluded: legacy non-generative ML or symbolic AI. |
| C (Comparator) | Traditional non-AI assessments, human baselines, or comparative evaluation of engineering defenses (guardrails, multi-agent validation). | Included: baselines, cohort comparisons, or countermeasures. Excluded: purely speculative essays without comparator. |
| O (Outcomes) | Task performance, exam breach rates, countermeasure resilience, shift in assessment rubrics, cognitive learning outcomes. | Included: empirical accuracy, resilience, rubric difficulty, psychometrics. Excluded: unverified claims. |
| S (Study Design) | Empirical studies: controlled experiments (RCT), quasi-experiments, case studies, psychometric evaluations, benchmark audits. | Included: peer-reviewed/preprint research with empirical data. Excluded: opinion blogs, press releases. |
* Footnote *: Prefilter Mathematical Model, Indicators & Scoring Formula (Rubric v2.3)
Rubric Indicators & Parameters
| Symbol | Indicator Name | Weight / Value |
|---|---|---|
| M | Methodological Rigor | wM = 0.32 |
| E | Engineering Countermeasures | wE = 0.25 |
| C | Consensus Challenge | wC = 0.43 |
| N | Novelty | wN = 0.00 |
| R | Topic Relevance (0–10) | Rmin = 4.0, Rfull = 7.0 |
| Gate | Binary Scope Gate | PASS / FAIL |
| Поріг | Pass Threshold | Score ≥ 5.0 |
Relevance R is a multiplier, not a summand: papers with R < R_min receive 0, and high-quality off-topic papers cannot outrank topical ones.
Scoring Formulae (MathML Core)
1. Final Prefilter Score:
2. Weighted Quality Score (Q):
3. Logical Prefilter Screening Criterion:
Methods & reporting (PRISMA 2020 items 1–15, 23–27)
Review type, objective, eligibility (1, 3–5)
Living systematic review: a daily-updated, automation-assisted selection. It is a literature-selection tool, not a published review with meta-analysis.
Topic (given to the model): Validity of educational assessment under generative AI and how to keep it (AI-resistant / AI-resilient assessment). Core: how generative AI changes what grades and test scores mean (validity arguments in the sense of Kane and Messick), assessment redesign, and quantitative methods that detect or model the distortion in assessment and learning data: item response theory, differential item functioning between humans and LLMs, item parameter drift, rater drift, item compromise and preknowledge, score shifts under unsupervised or online conditions (proctored vs unproctored exams, cheating, grade inflation), change-point and concept-drift detection, LLMs as test takers or raters, computerized adaptive testing and automated test assembly. Computational, statistical and engineering work is preferred, but a solid conceptual or empirical education study of assessment under generative AI belongs here too. Detectors of AI-generated text and watermarking are only adjacent to the topic. The audience is university educators and researchers: work about primary and secondary school (K-12) is off topic unless its findings or methods clearly transfer to higher education.
- Include: a scholarly article with topic relevance R ≥ 4.0, final score ≥ 5.0; a legal open-access full text that was actually read.
- Exclude: non-articles (datasets, code, errata), duplicates and preprints of published works, retracted works, K-12 with no transfer to higher education, works without full text (paywall, fetch errors), expert-rejected works (👎, reason recorded).
- Manual additions (origin = manual) bypass score screening but go through eligibility assessment.
Information sources & last searched (6)
| Channel | Records | Last record |
|---|---|---|
search — arXiv, OpenAlex, Semantic Scholar, ERIC | 12920 | 2026-11-01 10:22 |
ref — reference lists of read works | 1689 | 2026-11-01 10:22 |
manual — added manually | 27 | 2026-10-07 12:05 |
Citation candidates take metadata from OpenAlex; Crossref/Unpaywall supply DOIs, versions and open PDFs.
Search strategy (7)
Current search version: v1.0. A work matches if its title/abstract hits a term from EVERY group of at least one query (OR within a group; case-insensitive, word boundaries).
Queries (groups):
education × ai; psychometrics × ai; integrity × education; drift × education; drift × psychometrics
education: education, educational, student, learner, teacher, lecturer, classroom, university, higher education, school, curriculum, assessment, exam, examination, examinee, test taker, test score, grading, homework, coursework, online course, essay, academic integrity, academic misconduct, plagiarism, cheating, e-learning, MOOC
ai: generative AI, GenAI, large language model, LLM, ChatGPT, GPT-4, chatbot, AI-generated, AI-assisted, AI-resistant, AI-resilient, AI tool, artificial intelligence
integrity: proctoring, proctored, unproctored, non-proctored, remote proctoring, online exam, online test, online testing, exam integrity, testing integrity, academic integrity, academic dishonesty, cheating, contract cheating, grade inflation
psychometrics: item response theory, IRT, Rasch, psychometric, educational measurement, educational testing, differential item functioning, computerized adaptive testing, adaptive testing, automated test assembly, knowledge tracing, automated scoring, automated essay scoring, validity argument, construct validity, assessment validity, predictive validity
drift: parameter drift, dynamic item response, item parameter drift, rater drift, severity drift, concept drift, change point, change-point detection, item compromise, preknowledge, item exposure, test security, aberrant response, person-fit, differential item functioning
Semantic Scholar phrases: assessment validity generative AI; AI-resilient assessment higher education; AI-resistant assessment design; generative AI exam performance natural experiment; differential item functioning large language models humans; LLM as test taker item response theory; proctored versus unproctored online exam scores; generative AI grade inflation; item parameter drift detection; item compromise preknowledge detection; concept drift knowledge tracing; change point detection educational testing
arXiv: cs.CY, cs.CL, cs.HC, cs.AI, cs.LG, stat.AP, stat.ME. Result caps per query: OpenAlex 50, Semantic Scholar 25, ERIC 25. Citation searching: depth 1 from read and 👍 works, depth 2 from 👍 only; neighbours of 👍 works bypass the lexical filter.
| Search version | Records (search) | First | Last |
|---|---|---|---|
v1.0 | 12920 | 2026-10-06 | 2026-11-01 |
Selection process & automation (8, 9, 11)
- Abstract screening: a single automated reviewer — an LLM (gemini-3.1-flash-lite, gemini-3.5-flash-lite), batches of 20, models alternate; every evaluation is stored (prefilter_evaluations) with model and rubric version.
- Full-text analysis and data collection: gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, prompt
v2.1. Only after PDF→Markdown conversion; the model is never called without full text. - Verification: code checks every quote against the text (exact match after normalisation); unconfirmed claims are discarded.
- Human: no independent second reviewer. The owner gives 👍/👎 verdicts on a sample (50% near threshold, 30% top, 20% random); they steer the queue and few-shot examples but do not change the score.
- Data items (10): summary, method/data/sample, claims, limitations, study design (assessment_design, psychometric_modeling, natural_experiment, detector_evaluation, survey, rct, quasi_experiment, qualitative, theoretical, review, other), tags, rubric criteria.
- Risk of bias (11): not assessed formally (RoB, GRADE not applied); criterion M (methodological rigor, 0–10) is a ranking score, not a RoB tool. No effect measures or meta-analysis (12, 13d–f, 15): synthesis is qualitative, via article analyses and tags.
| Screening model | Scored |
|---|---|
gemini-3.1-flash-lite | 6838 |
gemini-3.5-flash-lite | 6450 |
— | 544 |
| Analysis model | prompt | Analyses |
|---|---|---|
gemini-3.1-flash-lite | v2.1 | 275 |
gemini-3.6-flash | v2.1 | 120 |
gemini-3.8-flash | v2.1 | 97 |
gemini-3.7-flash | v2.1 | 91 |
Scoring rubric v2.3 (0–10 anchors)
The model scores 0–10 per criterion; the anchors below are embedded in the prompt. Formula and weights are in the footnote above. Changing anchors or weights without a new version is blocked by a hash check.
| Criterion | Weight | 2 | 5 | 8 |
|---|---|---|---|---|
| Topic relevance (R) | × min(1, R/7.0) | No link to education or assessment: image, audio or model watermarking, model IP protection, general NLP benchmarks, AI in industry. | Adjacent: generative AI in education without an assessment focus; academic integrity with no evidence on assessment outcomes; detectors of AI-generated text or of student AI use; general psychometrics (adaptive testing, test assembly, IRT) with no drift, validity or AI angle. | Core: validity of assessment under generative AI (what grades and scores mean when AI is available); how grades shift under unsupervised conditions or cheating (proctored vs unproctored exams, grade inflation); AI-resistant or AI-resilient assessment design; quantitative methods that detect or model distorted assessment or learning data (DIF between humans and LLMs, item parameter or rater drift, item compromise/preknowledge, change-point or concept-drift detection, LLMs as test takers or raters). |
| Methodological rigor (M) | 0.32 | Vague evaluation, convenience sample of a few dozen, self-report only, no control group or baseline. | Clear dataset or sample (hundreds), standard metrics or validated instruments, comparison with baselines or a control group. | Randomized/controlled or preregistered, large or multi-site/multilingual data, adversarial or robustness checks, effect sizes with uncertainty. |
| Engineering countermeasures (E) | 0.25 | No method or countermeasure: describes impact, attitudes or policy only. | A concrete method or countermeasure with an evaluation: statistical test or model, detector, scoring procedure, or an assessment design tried on real cohorts. | A rigorous, reusable method: formal model with guarantees or error control, open code, validated on both real and simulated data. |
| Consensus challenge (C) | 0.43 | Reconfirms standard wisdom. | Nuances the consensus (e.g. detectors fail under mild paraphrasing; AI use does not harm an outcome it is assumed to harm). | Directly refutes high-profile claims with rigorous evidence. |
| Novelty (N) | 0.00 | Replicates well-known findings (another survey of student attitudes to ChatGPT, another test of one detector on a handful of prompts). | New dataset, benchmark, population or setting, or a previously untried technique. | Fundamentally new attack or defence, a theoretical/impossibility result, or a finding that changes how the field frames the problem. |
The model interpolates between anchors. The deep-analysis score is computed by code with the same formula from criteria_breakdown.
| Rubric version | Papers scored |
|---|---|
v2.0 | 261 |
v2.1 | 183 |
v2.2 | 20 |
v2.3 (current) | 13368 |
Screening Validation: Reliability & Agreement Metrics
Reference standard: expert verdicts. Full PRISMA systematic review metrics computed: recall, specificity, NPV, F₁, F₂, ROC AUC, DOR, paradox-immune Gwet's AC₁, and continuous score agreement.
| Measure | Value | Meaning |
|---|---|---|
| Seed-set recall | 50% (1/2), 95% CI 9–91% | Share of manually added 👍 works (bypassing screening) scoring ≥ threshold 5.0. Unbiased sensitivity estimate on this set. |
| Estimated corpus recall | 100% (100–100%) | Post-stratified by score band from judged works; conservative interval. Relevant works missed ≈ 0 (0–0). Not measured (too few verdicts in band): 11685 screened-out works. |
| Sensitivity / Recall | 100% (12/12), 95% CI 76–100% | Share of relevant works passed by screening: TP / (TP + FN). |
| Specificity | 20% (4/20), 95% CI 8–42% | Share of irrelevant works rejected by screening: TN / (TN + FP). |
| Precision / PPV | 43% (12/28), 95% CI 27–61% | Share of expert-approved among screening passes: TP / (TP + FP). |
| Negative Predictive Value (NPV) | 100% (4/4), 95% CI 51–100% | Share of truly irrelevant among screened-out works: TN / (TN + FN). Protects against losing relevant papers. |
| F-scores (F₁ and F₂) | F₁: 0.60 · F₂: 0.79 | F₂ weights recall twice as much as precision — critical safety metric against false exclusions in PRISMA. |
| Balanced Accuracy | 60.0% | Arithmetic mean of sensitivity and specificity, unaffected by class imbalance. |
| Diagnostic Odds Ratio (DOR) | 6.82 | DOR = (TP · TN) / (FP · FN) with Haldane-Anscombe correction. Overall discriminative capability of screening. |
| ROC AUC | 0.65 (95% CI 0.43–0.84) | Probability a 👍 work outscores a 👎 one (0.5 = chance). CI computed via DeLong / Bootstrap. |
| Inter-Rater Agreement (Gwet's AC₁ & Cohen's κ) | — | Gwet's AC₁ is paradox-immune inter-rater agreement on double-scored works, robust to severe class imbalance (80-90% screening rejection). |
| Continuous Score Agreement |
MAD: — r Пірсона: — |
Mean Absolute Difference (MAD) and Pearson r between scores of screening models on shared papers. |
| Score band | Works | Judged | 👍 | 👍 rate |
|---|---|---|---|---|
| 0.0–2.0 | 7533 | 2 (too few) | 0 | 0% |
| 2.0–4.0 | 3164 | 0 (too few) | 0 | — |
| 4.0–5.0 | 988 | 2 (too few) | 0 | 0% |
| 5.0–6.0 ✓ | 1140 | 3 | 2 | 67% |
| 6.0–8.0 ✓ | 915 | 23 | 8 | 35% |
| 8.0–10.0 ✓ | 29 | 2 (too few) | 2 | 100% |
| Screening model | Seed recall | AUC | Sens / Spec | Prec / NPV | F₁ / AC₁ | 👍 / 👎 (TP/FP/FN/TN) |
|---|---|---|---|---|---|---|
gemini-3.1-flash-lite |
50% (1/2), 95% CI 9–91% | 0.63 | 100% (12/12), 95% CI 76–100% / 16% (3/19), 95% CI 6–38% | 43% (12/28), 95% CI 27–61% / 100% (3/3), 95% CI 44–100% | 0.60 / 0.05 | 12 / 19 (12/16/0/3) |
gemini-3.5-flash-lite |
— | — | — / 100% (1/1), 95% CI 21–100% | — / 100% (1/1), 95% CI 21–100% | — / 1.00 | 0 / 1 (0/0/0/1) |
— |
— | — | — / — | — / — | — / — | 0 / 0 (0/0/0/0) |
To narrow intervals, judge works from lower score bands: /admin/taste includes 20% random picks. Metrics update automatically with each verdict.
Methodological Rigor & Study Designs (11, 18)
Methodological rigor M (0–10) is evaluated during full-text analysis. Study design distribution reflects verified empirical classifications.
Mean Rigor (M)
6.67 / 10
Analyzed papers: 573
Quality Stratification
🟢 High rigor (M ≥ 7.0): 306
🟡 Moderate rigor (4.0 ≤ M < 7.0): 254
🔴 Low rigor (M < 4.0): 13
| Study Design | Paper Count |
|---|---|
psychometric_modeling | 223 |
other | 40 |
theoretical | 25 |
rct | 13 |
assessment_design | 150 |
natural_experiment | 4 |
quasi_experiment | 53 |
detector_evaluation | 38 |
review | 12 |
survey | 5 |
experimental | 1 |
qualitative | 9 |
PRISMA 2020 27-Item Compliance Checklist
Full audit of compliance with PRISMA 2020 checklist (Page et al., 2021) for automated systematic reviews.
| № | Section / Item | Checklist Description | Status | Implementation |
|---|---|---|---|---|
| 1 | Title | Identify as living systematic review | ✓ Впроваджено | Page title, report metadata |
| 2 | Abstract | Structured summary (background, objectives, methods, results) | ✓ Впроваджено | #prisma-abstract block above |
| 3 | Rationale | Rationale in context of existing knowledge | ✓ Впроваджено | Topic description and rationale |
| 4 | Objectives | Explicit objectives using PICO / PECO | ✓ Впроваджено | #pico-framework table above |
| 5 | Eligibility criteria | Inclusion/exclusion criteria, language, dates | ✓ Впроваджено | Thresholds R, Score, Open Access |
| 6 | Information sources | Databases, registers, search dates | ✓ Впроваджено | arXiv, Crossref, OpenAlex, Semantic Scholar, ERIC, citations |
| 7 | Search strategy | Full search strategy, boolean filters, versions | ✓ Впроваджено | search_version, term groups, API limits |
| 8 | Selection process | Selection process, automation, independent screening | ✓ Впроваджено | LLM screening rotation + editorial taste loop |
| 9 | Data collection | Data collection from full-text reports | ✓ Впроваджено | PDF → MD parser, deep prompt v2.1 |
| 10a-b | Data items | List of outcomes and study characteristics | ✓ Впроваджено | Summary, sample, design, claims, countermeasures |
| 11 | Study risk of bias | Assessment of study methodological quality | ✓ Впроваджено | Rigor criterion M (0–10), quality distribution |
| 12 | Effect measures | Effect measures for outcomes | — Обґрунтовано N/A | Qualitative synthesis without meta-analytic pooled effects |
| 13a-f | Synthesis methods | Synthesis criteria and grouping methods | ✓ Впроваджено | Tag-based clustering, comparative study cards |
| 14 | Reporting bias | Assessment of reporting/publication bias | ✓ Впроваджено | Analysis of paywall exclusions & open access skew |
| 15 | Certainty assessment | Certainty assessment of body of evidence | ✓ Впроваджено | Automated quote grounding against full-text Markdown |
| 16 | Study selection | Selection results (flow diagram, counts) | ✓ Впроваджено | 100% stage conservation closure verified |
| 17 | Study characteristics | Characteristics of included studies table | ✓ Впроваджено | Interactive table with DOI, venue, year, tags |
| 18 | Risk of bias in studies | Risk of bias findings across studies | ✓ Впроваджено | Methodological rigor M & study designs table |
| 19 | Results of individual studies | Results for each individual study | ✓ Впроваджено | Public paper pages /doi/{doi} with full analysis |
| 20a-d | Results of syntheses | Results of syntheses & sub-groups | ✓ Впроваджено | Daily living editions, RSS feed, tag filters |
| 21 | Reporting biases | Results of reporting biases assessment | ✓ Впроваджено | Paywall n=313, retracted n=0 |
| 22 | Certainty of evidence | Summary of evidence certainty | ✓ Впроваджено | Gwet's AC₁, Cohen's κ, stratified recall, ROC AUC |
| 23a-d | Discussion | Discussion, limitations, implications | ✓ Впроваджено | Limitations section (23b, 23c) in methods |
| 24a-c | Registration & protocol | Registration, protocol availability, amendments | ✓ Впроваджено | Public repo, version history of search & rubric |
| 25 | Support | Financial & non-financial support | ✓ Впроваджено | Free API tiers declared in methods |
| 26 | Competing interests | Competing interests statement | ✓ Впроваджено | Declared in methods section |
| 27 | Data & code availability | Availability of data, analytical code, materials | ✓ Впроваджено | Export to CSV / JSON buttons, open-source code |
Limitations (23b, 23c)
- Open access only: paywalled papers never reach the synthesis, so the sample skews to open and preprint work.
- Screening ranks by quality and novelty rather than pure eligibility, so the sample skews towards counter-consensus work. Validity is measured against one expert (see above); a single LLM reviewer, model bias and version differences remain possible.
- The lexical filter and result caps can miss works with other terminology; sources skew English-language.
- Records scored under an older rubric version are not rescored automatically (see version table).
- Free Gemini quota: daily limits slow analysis; some selected works wait in the queue.
Registration, protocol, amendments, support, data (24–27)
- Registration: not registered. The protocol is the configuration (topic, queries, rubric, thresholds) in the project repository; it is reproduced in this block.
- Amendments: search versions (search_version) and rubric versions (rubric_version), tables above.
- Funding: none declared, free API tiers are used. Competing interests: none declared.
- Data: analyses and metadata are on article pages, RSS and sitemap; full texts are private (copyright) and not published.
Filter by Tags
Select one or more tags to refine the flow numbers and article corpus.
#psychometrics (98)
#Psychometrics (53)
#Item Response Theory (42)
#academic integrity (42)
#item response theory (35)
#higher education (31)
#assessment validity (30)
#Assessment Validity (29)
#Automated Essay Scoring (25)
#construct validity (25)
#IRT (24)
#Generative AI (22)
#automated essay scoring (22)
#Construct Validity (20)
#generative AI (18)
#LLM as rater (17)
#assessment_design (16)
#Academic Integrity (15)
#Automated Scoring (15)
#Higher Education (15)
#Large Language Models (15)
#assessment redesign (15)
#AI-resilient assessment (13)
#LLM Evaluation (13)
#assessment design (13)
#automated assessment (13)
#validity (13)
#LLM as Rater (12)
#automated scoring (12)
#large language models (12)
#academic_integrity (11)
#assessment-validity (11)
#assessment_validity (11)
#benchmarking (11)
#ChatGPT (10)
#GPT-4 (10)
#LLM-as-a-judge (10)
#LLMs as raters (10)
#Prompt Engineering (10)
#differential item functioning (10)
#item_response_theory (10)
#prompt engineering (10)
#DIF (9)
#Inter-Rater Reliability (9)
#LLM evaluation (9)
#LLMs as Test Takers (9)
#concept drift (9)
#rater drift (9)
#AI-resistant assessment (8)
#Assessment Design (8)
#Assessment Redesign (8)
#Automated Item Generation (8)
#Computerized Adaptive Testing (8)
#Knowledge Tracing (8)
#computerized adaptive testing (8)
#construct_validity (8)
#AI-Resilient Assessment (7)
#Computer Science Education (7)
#Differential Item Functioning (7)
#Validity (7)
| # | Status / Stage | Paper | LLM Score | Expert Review |
|---|---|---|---|---|
| 251 | Screened Out |
From Repositories to Practice: LLM-Based Personalization in Programming Education
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) (2026) · doi:10.4230/oasics.icpec.2026.9 · v1.0 |
3.5 (gemini-3.5-flash-lite) | — |
| 252 | scored |
Large Language Models as Psychometric Raters:Validating an AI-Based Conversational AssessmentTool for Self-Esteem
SSRN Electronic Journal (2026) · doi:10.2139/ssrn.7152638 · v1.0 |
0.0 (Flash Lite) | — |
| 253 | scored |
Development and Validation of the ChatGPT-Based Socratic Opponent Self-Assessment for Pre-Service Teachers
SSRN Electronic Journal (2026) · doi:10.2139/ssrn.7155486 · v1.0 |
0.0 (Flash Lite) | — |
| 254 | scored |
We Are Required to Re-Think the World of AI
Informing Science and IT Education Conference (2026) · doi:10.28945/5794 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 255 | Screened Out |
ChatGPT in education: Analysing trust, perception, and review of cognitive impact across social media and educational institutions
AIP conference proceedings (2026) · doi:10.1063/5.0348154 · v1.0 |
2.3 (gemini-3.1-flash-lite) | — |
| 256 | In Buffer |
PBAT: A Profile-based Adaptive Testing Framework Powered by LLMs
International Journal of Information and Education Technology (2026) · doi:10.18178/ijiet.2026.16.7.2641 · v1.0 |
2.7 (gemini-3.7-flash) | — |
| 257 | scored |
Ethical Dimensions of Artificial Intelligence Chatbots Use in Rare Disease Diagnosis: A Scoping Review
Canadian Journal of Bioethics (2026) · doi:10.7202/1126619ar · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 258 | scored |
AIVA: A Web-Based AI Powered Virtual Interview and Evaluation System
Best Journal of Innovation in Science Research and Development (2026) · doi:10.67249/739042 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 259 | Screened Out |
RAQAMLI TA’LIM SHAROITIDA GENERATIV SUN’IY INTELLEKTGA ASOSLANGAN ADAPTIV PEDAGOGIK MODELNI LOYIHALASH VA METODIK TA’MINOTI
arXiv/Crossref (2026) · doi:10.65164/wrs8cq25 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 260 | Screened Out |
AI and the future of teachers: predicting stakeholders’ expectations of teacher job loss from AI-related institutional conditions
Frontiers in Artificial Intelligence (2026) · doi:10.3389/frai.2026.1933015 · v1.0 |
3.3 (gemini-3.1-flash-lite) | — |
| 261 | scored |
Prosocial Motives to Serve in Rural Areas: An Exploratory Study Among Health Profession Education Students
Education in Medicine Journal (2026) · doi:10.21315/eimj2026.18.3.11 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 262 | scored |
Research Progress on Genotoxicity and Molecular Mechanisms of Environmental Endocrine Disruptors
Toxics (2026) · doi:10.3390/toxics14100882 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 263 | Screened Out |
From Digital Divide to AI Divide: A Sociological Study of Educational Inequality in Indian Higher Education
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23055690 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 264 | scored |
The instructional justification of formal concept entry in science education: a concept genesis framework
Frontiers in Education (2026) · doi:10.3389/feduc.2026.1958667 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 265 | scored |
Wildlife Conservation: A Bibliometric Analysis
West Science Nature and Technology (2026) · doi:10.58812/wsnt.v4i03.3143 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 266 | Not Article |
Generative, Adaptive, and Human-Centered AI: Mapping Indonesian-Affiliated Research on Educational Innovation
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23049432 · v1.0 |
- | — |
| 267 | Screened Out |
A Hybrid AI-Assisted Framework for Anxiety Support: System Description and Exploratory Findings Among University Students
Behavioral Sciences (2026) · doi:10.3390/bs16101781 · v1.0 |
1.9 (gemini-3.1-flash-lite) | — |
| 268 | scored |
Quantrix–Claude MCP bridge: Model Context Protocol server and embedded HTTP server for AI-assisted analysis of Quantrix Modeler financial models (2025)
Institutional Research Information System (Università degli Studi di Trento) (2026) · doi:10.5281/zenodo.23064177 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 269 | Screened Out |
Exploring ChatGPT’s Potential in Argumentative Genre-Based Reading-to-Write Instruction
Foreign Languages Education (2026) · doi:10.15334/fle.2026.33.3.1 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 270 | scored |
AI-enhanced CT assessment of pancreatic attenuation and visceral fat area: correlation with HbA1c-defined glycemic status
Romanian Medical Journal (2026) · doi:10.37897/rmj.2026.3.6 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 271 | scored |
Artificial Intelligence in Pregnancy Risk Stratification for Women with Congenital Heart Disease: Beyond CARPREG, ZAHARA, and Modified WHO Risk Scores
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23067603 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 272 | scored |
CoARA-ERIP proposal to develop three UNESCO Open Science Toolkit contributions on research assessment: Guidance, Factsheet, and Checklist
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23064328 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 273 | scored |
Research Trends and Thematic Evolution of Gamification in Mathematics Learning: A Scopus-Based Bibliometric Analysis, 2020–2025
Noumerico Journal of Technology in Mathematics Education (2026) · doi:10.33367/jtme.v4i2.9922 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 274 | Screened Out |
Responsible use of generative AI in Chinese vocational education: eye-tracking evidence on source verification and immediate near-transfer across three information-seeking conditions
Frontiers in Psychology (2026) · doi:10.3389/fpsyg.2026.1946196 · v1.0 |
4.6 (gemini-3.5-flash-lite) | — |
| 275 | scored |
Disruption or Transformation? A Bibliometric Study of Generative AI in Education
KIRŞEHİR EĞİTİM FAKÜLTESİ DERGİSİ (2026) · doi:10.29299/kefad.1912127 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 276 | scored |
Digital pharmaka and the crisis of subjectivation: a longitudinal phenomenological study on the educational use of technology in higher education through the philosophy of Bernard Stiegler
Frontiers in Psychology (2026) · doi:10.3389/fpsyg.2026.1989076 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 277 | scored |
Digital transformation of language education in higher education: the potential of immersive technologies
THE TIDINGS of the Baltic State Fishing Fleet Academy Psychological and pedagogical sciences (Theory and methods of professional education) (2026) · doi:10.46845/2071-5331-2026-3-77-201-206 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 278 | scored |
AI-Powered Chatbots for Optimizing Food Waste Management and Redistribution
IISE Annual Conference & Expo (2026) · doi:10.21872/annual2025_9080 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 279 | scored |
The Role of Artificial Intelligence in Customer Service Delivery: Evidence from Metbank
Futures The Zimbabwe Ezekiel Guti University Journal of Leadership Governance and Development (2026) · doi:10.71458/1tw7xa13 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 280 | scored |
Beyond the clicker: rethinking student response systems as pedagogical infrastructure for healthcare professions education
Frontiers in Medicine (2026) · doi:10.3389/fmed.2026.1967058 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 281 | scored |
ChatGPT in Radiation Oncology: Redefining Patient Education through Artificial Intelligence
Indonesian Journal of Cancer (2026) · doi:10.33371/ijoc.v20i3.1471 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 282 | Screened Out |
EMPOWER-UP: psychometric evaluation of a generic questionnaire for assessing empowerment in relational decision-making and problem-solving among adults with long-term health conditions
Research Square (2025) · doi:10.21203/rs.3.rs-3772053/v2 · v1.0 |
4.3 (gemini-3.1-flash-lite) | — |
| 283 | scored |
A multimodal strategy for assessing oxygenator degradation during extracorporeal membrane oxygenation (ECMO): an in vitro evaluation
at - Automatisierungstechnik (2026) · doi:10.1515/auto-2026-0045 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 284 | scored |
Empirical scaling relationships and a catastrophic damage-transition threshold surface for composite laminates under repeated low-velocity impact
Composites and Advanced Materials (2026) · doi:10.1177/26349833261496289 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 285 | Screened Out |
Calibrated and Explainable Early-Warning Systems for Risk Escalation in Streaming Data and Systems
Journal of Intelligent Decision Making and Information Science (2026) · doi:10.17762/jidmis.v3.2700 · v1.0 |
4.8 (gemini-3.1-flash-lite) | — |
| 286 | scored |
МОРАЛЬНО-ЕТИЧНЕ ВИХОВАННЯ ТА РОЗВИТОК БЛАГОДІЙНИЦТВА І ВОЛОНТЕРСТВА В ПЕДАГОГІЧНИХ КОЛЕДЖАХ УКРАЇНИ (1991 – 2025 РОКИ)
Педагогічна наука і освіта XXI століття. (2026) · doi:10.35619/pse.vi6.176 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 287 | Screened Out |
INTEGRATION OF DIGITAL TOOLS AND AI INTO FOREIGN LANGUAGE TEACHING AT HIGHER EDUCATION INSTITUTIONS
Актуальні питання у сучасній науці (2026) · doi:10.52058/2786-6300-2026-5(47)-2784-2792 · v1.0 |
1.4 (gemini-3.1-flash-lite) | — |
| 288 | scored |
Additional file 1 of Educating for academic integrity: effectiveness of a digital resource on plagiarism awareness among postgraduate bioscience students
Figshare (2026) · doi:10.6084/m9.figshare.32672247 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 289 | Screened Out |
Undergraduate international students’ perceptions of AI-generated feedback: A mixed-methods study at a Canadian university
Journal of Applied Learning & Teaching (2026) · doi:10.37074/jalt.2026.9.2.4 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 290 | Screened Out |
Integration of Artificial Intelligence Into the Educational Process: Pedagogical Opportunities and Risks
Bulletin of Science and Practice (2026) · doi:10.33619/2414-2948/127/73 · v1.0 |
1.4 (gemini-3.1-flash-lite) | — |
| 291 | Not Article |
Harmonised 42-institution public-document coding dataset for visible public generative AI governance in higher education
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.20702850 · v1.0 |
- | — |
| 292 | Not Article |
Educating for academic integrity: effectiveness of a digital resource on plagiarism awareness among postgraduate bioscience students
Figshare (2026) · doi:10.6084/m9.figshare.c.8535900 · v1.0 |
- | — |
| 293 | scored |
ОСОБЛИВОСТІ УПРАВЛІНСЬКОЇ ПРАКТИКИ БАГАТОПРОФІЛЬНОГО ЗАКЛАДУ ОСВІТИ В УМОВАХ ЗМІН
Педагогічна наука і освіта XXI століття. (2026) · doi:10.35619/pse.vi6.185 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 294 | scored |
DEVELOPING ACADEMIC WRITING SKILLS AMONG UNIVERSITY STUDENTS
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.20697254 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 295 | Screened Out |
The digital facilitator
Journal of Interdisciplinary Studies in Education (2026) · doi:10.32674/nq9swx67 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 296 | Screened Out |
THE INTEGRATION OF ARTIFICIAL INTELLIGENCE INTO THE EDUCATION SYSTEM: AN ANALYSIS OF THE EFFECT OF AI TOOLS ON LEARNING QUALITY AND THE WORK OF TEACHERS
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.20705294 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 297 | scored |
Symbiotic Escherichia coli strains can better colonize host stinkbugs and outcompete natural symbiotic bacteria, but confer less fitness benefit
mBio (2026) · doi:10.1128/mbio.00951-26 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 298 | In Buffer |
Structured AI workflows in Saudi EMI research writing
Journal of International Students (2026) · doi:10.32674/e7jdhc67 · v1.0 |
4.0 (gemini-3.8-flash) | — |
| 299 | Screened Out |
ГЕНЕРАТИВНИЙ ШТУЧНИЙ ІНТЕЛЕКТ ЯК ЗАСІБ РОЗВИТКУ КРИТИЧНОГО МИСЛЕННЯ СТУДЕНТІВ
Педагогічна наука і освіта XXI століття. (2026) · doi:10.35619/pse.vi6.161 · v1.0 |
4.3 (gemini-3.5-flash-lite) | — |
| 300 | Screened Out |
Policy alignment and trustworthy AI governance in higher education
Journal of Interdisciplinary Studies in Education (2026) · doi:10.32674/eqphhh11 · v1.0 |
2.0 (gemini-3.5-flash-lite) | — |