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: 19271 →
Screen: 18103 →
Eligible: 2666 →
Included: 96
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 = 96 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 | 17211 | 2026-11-11 16:08 |
ref — reference lists of read works | 2033 | 2026-11-11 14:25 |
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 | 17211 | 2026-10-06 | 2026-11-11 |
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 | 9007 |
gemini-3.5-flash-lite | 8456 |
— | 706 |
| Analysis model | prompt | Analyses |
|---|---|---|
gemini-3.1-flash-lite | v2.1 | 275 |
gemini-3.6-flash | v2.1 | 235 |
gemini-3.8-flash | v2.1 | 116 |
gemini-3.7-flash | v2.1 | 108 |
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) | 17705 |
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): 15464 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 | 9995 | 2 (too few) | 0 | 0% |
| 2.0–4.0 | 4173 | 0 (too few) | 0 | — |
| 4.0–5.0 | 1296 | 2 (too few) | 0 | 0% |
| 5.0–6.0 ✓ | 1469 | 3 | 2 | 67% |
| 6.0–8.0 ✓ | 1138 | 23 | 8 | 35% |
| 8.0–10.0 ✓ | 35 | 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)
6.49 / 10
Analyzed papers: 724
Quality Stratification
🟢 High rigor (M ≥ 7.0): 344
🟡 Moderate rigor (4.0 ≤ M < 7.0): 359
🔴 Low rigor (M < 4.0): 21
| Study Design | Paper Count |
|---|---|
psychometric_modeling | 276 |
other | 54 |
theoretical | 27 |
rct | 16 |
assessment_design | 196 |
natural_experiment | 5 |
quasi_experiment | 61 |
review | 22 |
detector_evaluation | 47 |
survey | 7 |
experimental | 1 |
qualitative | 12 |
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=366, 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 (113)
#Psychometrics (65)
#Item Response Theory (55)
#academic integrity (51)
#assessment validity (50)
#Assessment Validity (49)
#item response theory (45)
#higher education (42)
#Automated Essay Scoring (39)
#automated essay scoring (38)
#Generative AI (30)
#Construct Validity (27)
#construct validity (27)
#LLM as rater (25)
#Higher Education (24)
#IRT (24)
#Large Language Models (23)
#large language models (22)
#GPT-4 (21)
#LLM Evaluation (21)
#generative AI (21)
#Academic Integrity (19)
#Automated Scoring (19)
#assessment redesign (19)
#prompt engineering (19)
#ChatGPT (17)
#automated scoring (17)
#LLM as Rater (16)
#Prompt Engineering (16)
#assessment design (16)
#assessment_design (16)
#Assessment Redesign (15)
#AI-resilient assessment (14)
#validity (14)
#LLMs as raters (13)
#automated assessment (13)
#differential item functioning (13)
#Computer Science Education (12)
#LLM-as-a-judge (12)
#academic_integrity (12)
#benchmarking (12)
#inter-rater reliability (12)
#Automated Item Generation (11)
#LLMs as Test Takers (11)
#assessment-validity (11)
#assessment_validity (11)
#formative assessment (11)
#rater drift (11)
#AI-resistant assessment (10)
#Computerized Adaptive Testing (10)
#Inter-Rater Reliability (10)
#Knowledge Tracing (10)
#automated item generation (10)
#automated_essay_scoring (10)
#computerized adaptive testing (10)
#item_response_theory (10)
#DIF (9)
#LLM evaluation (9)
#Medical Education (9)
#concept drift (9)
| # | Status / Stage | Paper | LLM Score | Expert Review |
|---|---|---|---|---|
| 10001 | Screened Out |
Reimagining Literature Evaluation Pedagogy Through AI-Generated Podcasts: Pharmacy Students’ Perspectives and Critical Appraisal
Pharmacy (2026) · doi:10.3390/pharmacy14070145 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10002 | Screened Out |
PEAXAI: A probabilistic efficiency analysis using explainable artificial intelligence in R
SoftwareX (2026) · doi:10.1016/j.softx.2026.103089 · v1.0 |
3.1 (gemini-3.1-flash-lite) | — |
| 10003 | scored |
Global Research Trends in Surgical Management of Facial Paralysis: A Bibliometric Analysis
Facial Plastic Surgery (2026) · doi:10.1055/a-2969-4686 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10004 | abstract_only |
LASO-Σ: Adaptive Predictive Memory, Information Governance, and Continuous Machine Learning
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23074788 · v1.0 |
5.8 (gemini-3.1-flash-lite) | — |
| 10005 | No Fulltext |
Mechanism-aware benchmarking of large language models as learning aids in pediatric difficult airway training: true hallucinations vs. false contraindications
BMC Medical Education (2026) · doi:10.1186/s12909-026-10509-y · v1.0 |
5.6 (gemini-3.1-flash-lite) | — |
| 10006 | scored |
Large Language Models - an Overview
Figshare (2026) · doi:10.6084/m9.figshare.34037934 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10007 | Screened Out |
Generative-AI/LLM-Enabled E-Assessment in Higher Education: A Bibliometric Analysis of Research Trends, Collaboration Networks, and Thematic Evolution
Computers (2026) · doi:10.3390/computers15100665 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10008 | Screened Out |
CSIDic Implementation Strategy: A Conceptual Global Framework for Governed Agentic AI
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23077843 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 10009 | Screened Out |
Digital Readiness, Artificial Intelligence Use, and Student Learning Outcomes in Indonesia: Evidence from PISA 2025
Indonesian Journal of Multidisciplinary on Social and Technology (2026) · doi:10.69693/ijmst.v4i3.14033 · v1.0 |
3.0 (gemini-3.1-flash-lite) | — |
| 10010 | scored |
Technology and Economic Transformation in Sri Lanka
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23076736 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10011 | Not Article |
Dataset — Artificial Intelligence in Sports Science Education: Insights from Spanish Students
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23077654 · v1.0 |
- | — |
| 10012 | Screened Out |
GOVERNING AI-ASSISTED ASSESSMENT IN MARKETING EDUCATION: A ROLE-BASED TYPOLOGY AND PRATICAL GUIDELINES
Marketing Education Review (2026) · doi:10.1080/10528008.2026.2740715 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 10013 | Screened Out |
DEVELOPMENT OF THE EDUCATIONAL ARTIFICIAL INTELLIGENCE USE CONCERNS SCALE
Turkish Online Journal of Distance Education (2026) · doi:10.17718/tojde.1905615 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10014 | scored |
Petrochemical Process Safety: A Comprehensive Review of Hazard Identification, Risk Assessment, and Emerging Safety Technologies
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23075901 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10015 | scored |
Bridging the Digital Divide: Reimagining Inclusive Science Education through Digital Access and Artificial Intelligence in India
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23079392 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10016 | scored |
From Similarity Ranking to Definitive Verdict: LLM-Enhanced Source-to-Binary Function Localization
Proceedings of the ACM on Programming Languages (2026) · doi:10.1145/3839539 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10017 | scored |
Temporal Changes in Inflammatory Markers and Laboratory Parameters in Relation to Risk of Neonatal Sepsis
Journal of Clinical Medicine (2026) · doi:10.3390/jcm15197625 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 10018 | scored |
AI-Driven Credit Scoring and Financial Inclusion in Kenya: Balancing Innovation with Governance Safeguards
Journal of Finance and Accounting (2026) · doi:10.53819/81018102t2612 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10019 | scored |
The Effectiveness of Artificial Intelligence (AI) in Teachers' Digital Archiving on Microsoft 365 via OneDrive and SharePoint Cloud Storage Platforms at SMPN 01 Tilamuta
Journal of Education and Teaching Learning (2026) · doi:10.59211/mjpjetl.v4i2.429 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10020 | scored |
Empowering Lightweight Language Models for Security Code Review via Context-Aware Distillation
Proceedings of the ACM on software engineering. (2026) · doi:10.1145/3832293 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10021 | scored |
Educación aumentada
Revista Multidisciplinar Ciencia y Descubrimiento (2026) · doi:10.63816/hm0cw931 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10022 | Screened Out |
Artificial intelligence in university physics education: a systematic review of empirical studies
Frontiers in Education (2026) · doi:10.3389/feduc.2026.1964629 · v1.0 |
3.0 (gemini-3.5-flash-lite) | — |
| 10023 | Screened Out |
Exploring learners’ well-being in AI-supported English learning from a self-determination theory perspective
Learning and Motivation (2026) · doi:10.1016/j.lmot.2026.102353 · v1.0 |
2.1 (gemini-3.5-flash-lite) | — |
| 10024 | In Buffer |
Measuring undergraduate students' reliance on generative AI during problem-solving: Scale development and validation
arXiv (2026) · doi:10.1016/j.compedu.2025.105329 · v1.0 |
3.3 (gemini-3.6-flash) | — |
| 10025 | scored |
IndoNutriQA: An Indonesian Clinical Nutrition Question Answering Benchmark
arXiv (2026) · doi:10.48550/arxiv.2610.31256 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10026 | In Buffer |
What the submission does not show: Complexifying cognitive offloading in students' mathematical work with LLMs
arXiv (2026) · doi:10.48550/arxiv.2610.31335 · v1.0 |
6.5 (gemini-3.6-flash) | — |
| 10027 | In Buffer |
Supporting or Replacing Students' Reasoning? Cognitive Offloading in AI-Assisted Proof Learning
arXiv (2026) · doi:10.48550/arxiv.2610.31481 · v1.0 |
6.6 (gemini-3.6-flash) | — |
| 10028 | scored |
Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
arXiv (2026) · doi:10.48550/arxiv.2610.31573 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10029 | In Buffer |
Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination
arXiv (2026) · doi:10.48550/arxiv.2610.31586 · v1.0 |
5.4 (gemini-3.6-flash) | — |
| 10030 | scored |
VERA: A Responsible AI Dashboard for Assessing LLM Deployments in Light of the EU AI Act
arXiv (2026) · doi:10.48550/arxiv.2610.31588 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10031 | scored |
How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions
arXiv (2026) · doi:10.48550/arxiv.2610.31606 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10032 | scored |
Cost-Aware Abstention for LLM-Based IT Ticket Classification
arXiv (2026) · doi:10.48550/arxiv.2610.31657 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10033 | scored |
Estimation of Standard Error, Linking Error, and Total Error for Robust and Nonrobust Linking Methods in the Two-Parameter Logistic Model
Stats (2024) · doi:10.3390/stats7030036 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10034 | scored |
VALIDATION OF THE INDONESIAN VERSION OF THE PARTNER’S EMOTIONAL DEPENDENCY SCALE (SED): A RASCH MODEL APPROACH
Jurnal Psikologi (2024) · doi:10.14710/jp.22.2.102-117 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 10035 | Screened Out |
Racism in obstetric care: a psychometric study of the Gendered Racial Microaggressions Scale among Global Majority birthing people in obstetric contexts
BMC Pregnancy and Childbirth (2024) · doi:10.1186/s12884-024-06642-5 · v1.0 |
3.4 (gemini-3.1-flash-lite) | — |
| 10036 | abstract_only |
Robustness of Computer Adaptive Tests to the Presence of Item Preknowledge: A Simulation Study
Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi (2024) · doi:10.21031/epod.1470949 · v1.0 |
8.0 (gemini-3.1-flash-lite) | — |
| 10037 | Screened Out |
Measurement bias in caregiver-report of early childhood behavior problems across demographic factors in an ECHO-wide diverse sample
Carolina Digital Repository (University of North Carolina at Chapel Hill) (2024) · doi:10.17615/jf8z-ex26 · v1.0 |
3.7 (gemini-3.1-flash-lite) | — |
| 10038 | Screened Out |
The eTIMSS and TIMSS Measurement Invariance Study: Multigroup Factor Analyses and Differential Item Functioning Analyses with the 2019 Cycle
Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi (2024) · doi:10.21031/epod.1426739 · v1.0 |
3.8 (gemini-3.1-flash-lite) | — |
| 10039 | Screened Out |
Comparing Differential Item Functioning Based On Multilevel Mixture Item Response Theory, Mixture Item Response Theory And Manifest Groups
Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi (2024) · doi:10.21031/epod.1457880 · v1.0 |
4.2 (gemini-3.1-flash-lite) | — |
| 10040 | Screened Out |
Verification of suitability of park golf course servicescape measurement scale applying Rasch rating scale model
Korean Journal of Sports Science (2024) · doi:10.35159/kjss.2024.6.33.3.698 · v1.0 |
1.1 (gemini-3.1-flash-lite) | — |
| 10041 | Screened Out |
Differential Item Functioning of the region-based national examination equipment
REID (Research and Evaluation in Education) (2024) · doi:10.21831/reid.v10i1.73270 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10042 | Screened Out |
A psychometric evaluation of an item bank for an English reading comprehension tool using Rasch analysis
REID (Research and Evaluation in Education) (2024) · doi:10.21831/reid.v10i1.65284 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10043 | Screened Out |
The Effectiveness of the Likelihood Ratio Test and Multiple Indicators Multiple Causes Method in Detecting Differential Item Functioning According to Sample Size, Percentage of Items with DIF, and Ability Distribution
Jordan Journal of Applied Science-Humanities Series (2024) · doi:10.35192/jjoas-h.v40i2.804 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10044 | Screened Out |
Effectiveness of Multiple Indicators and Multiple Causes Model (MIMIC) in Detecting the Differential Item Functioning of a Test in Terms of Sample Size and Test Length
Jordan Journal of Applied Science-Humanities Series (2024) · doi:10.35192/jjoas-h.v40i1.793 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 10045 | Screened Out |
National Eligibility cum Entrance Test - Testing for the Future
Journal of Medical Evidence (2024) · doi:10.4103/jme.jme_140_24 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 10046 | Screened Out |
The Chinese Version of the Couples Satisfaction Index: Psychometric Assessment and Differential Item Functioning Analysis with Item Response Theory
SAGE Open (2024) · doi:10.1177/21582440241271087 · v1.0 |
1.8 (gemini-3.1-flash-lite) | — |
| 10047 | No Fulltext |
A Hierarchical Rater Model Approach for Integrating Automated Essay Scoring Models
Zeitschrift für Psychologie (2024) · doi:10.1027/2151-2604/a000567 · v1.0 |
6.7 (gemini-3.1-flash-lite) | — |
| 10048 | Screened Out |
Patient satisfaction and value based purchasing in hospitals, Odisha, India
Bulletin of the World Health Organization (2024) · doi:10.2471/blt.24.290519 · v1.0 |
3.0 (gemini-3.1-flash-lite) | — |
| 10049 | Screened Out |
Rasch analysis of the modified Fatigue Severity Scale in neuromuscular disorders and comparison between sex, age and diagnoses
Muscle & Nerve (2024) · doi:10.1002/mus.28186 · v1.0 |
1.8 (gemini-3.1-flash-lite) | — |
| 10050 | scored |
Impact of Tripod Joint Pressing Load Variation on Drive Shaft Rattling in Passenger Car
SAE technical papers on CD-ROM/SAE technical paper series (2025) · doi:10.4271/2025-01-0097 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |