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: 20150 →
Screen: 18986 →
Eligible: 2773 →
Included: 102
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 = 102 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 | 18044 | 2026-11-13 16:07 |
ref — reference lists of read works | 2079 | 2026-11-13 14:28 |
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 | 18044 | 2026-10-06 | 2026-11-13 |
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 | 9469 |
gemini-3.5-flash-lite | 8853 |
— | 730 |
| Analysis model | prompt | Analyses |
|---|---|---|
gemini-3.1-flash-lite | v2.1 | 275 |
gemini-3.6-flash | v2.1 | 265 |
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) | 18588 |
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): 16240 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 | 10505 | 2 (too few) | 0 | 0% |
| 2.0–4.0 | 4380 | 0 (too few) | 0 | — |
| 4.0–5.0 | 1355 | 2 (too few) | 0 | 0% |
| 5.0–6.0 ✓ | 1528 | 3 | 2 | 67% |
| 6.0–8.0 ✓ | 1184 | 23 | 8 | 35% |
| 8.0–10.0 ✓ | 37 | 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)
6.46 / 10
Analyzed papers: 754
Quality Stratification
🟢 High rigor (M ≥ 7.0): 355
🟡 Moderate rigor (4.0 ≤ M < 7.0): 373
🔴 Low rigor (M < 4.0): 26
| Study Design | Paper Count |
|---|---|
psychometric_modeling | 286 |
other | 55 |
theoretical | 27 |
rct | 17 |
assessment_design | 210 |
natural_experiment | 5 |
quasi_experiment | 61 |
review | 24 |
detector_evaluation | 48 |
survey | 7 |
experimental | 1 |
qualitative | 13 |
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=387, 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 (115)
#Psychometrics (71)
#Item Response Theory (60)
#academic integrity (52)
#assessment validity (52)
#Assessment Validity (51)
#item response theory (46)
#higher education (44)
#Automated Essay Scoring (43)
#automated essay scoring (40)
#Generative AI (32)
#Construct Validity (31)
#LLM as rater (27)
#construct validity (27)
#Large Language Models (25)
#Higher Education (24)
#IRT (24)
#large language models (24)
#LLM Evaluation (23)
#GPT-4 (22)
#generative AI (22)
#assessment redesign (20)
#Academic Integrity (19)
#Automated Scoring (19)
#prompt engineering (19)
#ChatGPT (18)
#LLM as Rater (17)
#Prompt Engineering (17)
#automated scoring (17)
#Assessment Redesign (16)
#assessment design (16)
#assessment_design (16)
#AI-resilient assessment (14)
#validity (14)
#LLMs as raters (13)
#automated assessment (13)
#differential item functioning (13)
#Computer Science Education (12)
#Computerized Adaptive Testing (12)
#LLM-as-a-judge (12)
#academic_integrity (12)
#benchmarking (12)
#formative assessment (12)
#inter-rater reliability (12)
#Automated Item Generation (11)
#Differential Item Functioning (11)
#Knowledge Tracing (11)
#LLMs as Test Takers (11)
#Quadratic Weighted Kappa (11)
#assessment-validity (11)
#assessment_validity (11)
#rater drift (11)
#AI-resistant assessment (10)
#Inter-Rater Reliability (10)
#LLM evaluation (10)
#automated item generation (10)
#automated_essay_scoring (10)
#computerized adaptive testing (10)
#item_response_theory (10)
#AI-Resilient Assessment (9)
| # | Status / Stage | Paper | LLM Score | Expert Review |
|---|---|---|---|---|
| 14101 | Not Article |
Base de datos - Tesis - Inmaculada Serrano Garcia
Figshare (2026) · doi:10.6084/m9.figshare.33139802 · v1.0 |
- | — |
| 14102 | No Fulltext |
Diagnosing LLM Benchmark: A Psychometric Analysis of Difficulty and Discrimination
Lecture notes in computer science (2026) · doi:10.1007/978-3-032-31673-8_10 · v1.0 |
6.3 (gemini-3.5-flash-lite) | — |
| 14103 | scored |
Consciousness Intelligence Awareness (CIA) Framework: A Structural Resolution of the Hard Problem of Consciousness
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.21773100 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14104 | scored |
Validation of a deep learning-based system for sleep staging, arousal detection, and respiratory event scoring in atrial fibrillation patients
Journal of Clinical Sleep Medicine (2026) · doi:10.1007/s44470-026-00145-0 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14105 | Not Article |
Development and psychometric validation of the Thai AI Literacy Scale for Nursing Students in Thailand: a cross-sectional observational study
Harvard Dataverse (2026) · doi:10.7910/dvn/1q5ivy · v1.0 |
- | — |
| 14106 | No Fulltext |
Evaluating Reliability and Bias of Large Language Models in Automated Essay Scoring
Computers in the Schools (2026) · doi:10.1080/07380569.2026.2712300 · v1.0 |
6.3 (gemini-3.5-flash-lite) | — |
| 14107 | Screened Out |
Assessing What Matters When AI Builds the Artifact in Engineering—An Integrative Micro-Credential Framework for Evaluative Judgment Based on Erroneous Worked Examples
arXiv/Crossref (2026) · doi:10.35542/osf.io/uqsr6_v1 · v1.0 |
4.7 (gemini-3.5-flash-lite) | — |
| 14108 | No Fulltext |
Large Language Models as Examinees and Graders in Simulated General Surgery Oral Board-Style Cases: A Psychometric Pilot Study
Cureus (2026) · doi:10.7759/cureus.113882 · v1.0 |
6.2 (gemini-3.5-flash-lite) | — |
| 14109 | Screened Out |
Development and validation of a scale on the difficulties of AI technology integration in teaching for primary and secondary school teachers
Frontiers in Psychology (2026) · doi:10.3389/fpsyg.2026.1902647 · v1.0 |
2.3 (gemini-3.5-flash-lite) | — |
| 14110 | Screened Out |
Development and psychometric validation of the Thai AI Literacy Scale for Nursing Students in Thailand: a methodological study
Journal of Educational Evaluation for Health Professions (2026) · doi:10.3352/jeehp.2026.23.22 · v1.0 |
2.9 (gemini-3.5-flash-lite) | — |
| 14111 | abstract_only |
OLIY TA'LIM TALABALARIDA OG'ZAKI NUTQ KO'NIKMALARINI RIVOJLANTIRISHDA SUN'IY INTELLEKTNING O'RNI
Zamonaviy jamiyat va innovatsiyalar ilmiy-nazariy jurnali (2026) · doi:10.67547/fanistiqbollari.2026.724 · v1.0 |
5.6 (gemini-3.1-flash-lite) | — |
| 14112 | Screened Out |
DEVELOPING AN ETHICAL-PEDAGOGICAL FRAMEWORK FOR AI-ASSISTED MAH?RAH KIT?BAH LEARNING: A WAHDATUL ‘UL?M PERSPECTIVE
JALIE Journal of Applied Linguistics and Islamic Education (2026) · doi:10.33754/jalie.v10i2.1974 · v1.0 |
1.4 (gemini-3.1-flash-lite) | — |
| 14113 | scored |
Проблемы оценки электронных доказательств в цивилистическом процессе
Современное право. (2026) · doi:10.25799/ni.2026.39.62.014 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14114 | Screened Out |
Sustainable Education: STEM Students’ Use of Generative AI in Education: Perceived Usefulness and Intentions to Persist to Degree Completion
Sustainability (2026) · doi:10.3390/su181910128 · v1.0 |
2.8 (gemini-3.1-flash-lite) | — |
| 14115 | Screened Out |
Teaching UML Modeling in the Age of Generative AI: Combining Manual Modeling, Prompt Engineering and Model Evaluation
ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) (2026) · doi:10.1145/3837062.3838914 · v1.0 |
3.7 (gemini-3.1-flash-lite) | — |
| 14116 | scored |
Role of Training & Development in Building Sustainable Organization Culture: an Empirical Study of Manufacturing Industries
International Journal For Multidisciplinary Research (2026) · doi:10.36948/ijfmr.2026.v08i05.89044 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14117 | scored |
Boards in the Age of AI: Antecedents, Decisions, and Outcomes of Board-Level Artificial Intelligence Governance—A Systematic Review
Administrative Sciences (2026) · doi:10.3390/admsci16100489 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14118 | No Fulltext |
On the Non-Interchangeability of Deterministic and LLM-Based UML Evaluators
ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) (2026) · doi:10.1145/3837062.3839375 · v1.0 |
6.2 (gemini-3.1-flash-lite) | — |
| 14119 | scored |
An Automated Framework for Legacy Java Modernization Integrating Software Quality, Business Value, and GPT-4-Assisted Re-Engineering: An Empirical Evaluation
Applied Sciences (2026) · doi:10.3390/app16199845 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14120 | scored |
Government Auditing and Fiscal Transparency: A Systematic Literature Review of Digital, Institutional, and Regulatory Pathways to Public Accountability
Administrative Sciences (2026) · doi:10.3390/admsci16100487 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14121 | scored |
Towards an AI-augmented, human-centred smart digital ecosystem in occupational health and safety
Sigurnost (2026) · doi:10.31306/s.68.3.3 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14122 | scored |
Entrepreneuriat Social, Intelligence Artificielle et Employabilité des Diplômés au Maroc : Une Revue Systématique de la Littérature (PRISMA)
International Journal of Accounting, Finance, Auditing, Management and Economics (2026) · doi:10.5281/zenodo.22920449 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14123 | scored |
Towards LLM-Driven Transformation of Goal Models for AI-Enabled Socio-Technical Systems
ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) (2026) · doi:10.1145/3837062.3838906 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14124 | scored |
HemaSight AI: A Four-Stage Deep Learning Pipeline for Automated Leukemia Detection and Post-Transplant Monitoring
IJARCCE (2026) · doi:10.17148/ijarcce.2026.151008 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14125 | scored |
Meta-Analyzing the Impacts of Social Robots on Children’s Social and Emotional Development over Two Decades
Journal of Intelligence (2026) · doi:10.3390/jintelligence14100246 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14126 | scored |
Artificial intelligence and occupational medicine
Sigurnost (2026) · doi:10.31306/s.68.3.5 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14127 | scored |
Preservice Special Education Teachers’ Acceptance of an AI-Based Microteaching Evaluation and Feedback System: A Pre–Post UTAUT Mixed-Methods Study
Behavioral Sciences (2026) · doi:10.3390/bs16101818 · v1.0 |
5.3 (gemini-3.5-flash-lite) | — |
| 14128 | scored |
Can Performance Crises in Football Really Be Predicted Mathematically? Formal Claim Auditing, Epistemic Agency, and Operationalized Self-Research in High-Performance Sport
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23139236 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14129 | scored |
Jjodie: A Conversational Modeling Assistant with Script-Mediated (Meta)Model Manipulation
ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) (2026) · doi:10.1145/3837062.3838867 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14130 | Not Article |
Survey Dataset on AI Use, Risk Perceptions, and Educational Needs among Technology Students
Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23136793 · v1.0 |
- | — |
| 14131 | Screened Out |
Enhancing Software-Design Learning by Combining UML and LLM-Assisted Feedback in a Learning Platform
ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) (2026) · doi:10.1145/3837062.3838917 · v1.0 |
4.6 (gemini-3.5-flash-lite) | — |
| 14132 | scored |
Multimodal LLM Pipeline for Automated Analysis of Technical Graphical Documents
AI (2026) · doi:10.3390/ai7100403 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14133 | Screened Out |
Generative AI Steering and Human Authoring: Complementary Search-as-Learning Scaffolds in Cross-Session Aggregated Academic Search
arXiv (2026) · doi:10.48550/arxiv.2610.12755 · v1.0 |
3.1 (gemini-3.5-flash-lite) | — |
| 14134 | scored |
Embodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic Manipulation
arXiv (2026) · doi:10.48550/arxiv.2610.14106 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14135 | Screened Out |
From Instructional Intent to Classroom-Ready Lessons: Investigating Teacher-AI Collaboration in Lesson Authoring for Secondary Computing Education
arXiv (2026) · doi:10.48550/arxiv.2610.12834 · v1.0 |
3.1 (gemini-3.5-flash-lite) | — |
| 14136 | scored |
COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
arXiv (2026) · doi:10.48550/arxiv.2610.12837 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14137 | scored |
Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization
arXiv (2026) · doi:10.48550/arxiv.2610.12855 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14138 | scored |
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
arXiv (2026) · doi:10.48550/arxiv.2610.12933 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14139 | scored |
SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents
arXiv (2026) · doi:10.48550/arxiv.2610.12975 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14140 | scored |
What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
arXiv (2026) · doi:10.48550/arxiv.2610.12995 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14141 | scored |
The Silent Failures in Agentic Data Science
arXiv (2026) · doi:10.48550/arxiv.2610.14115 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14142 | scored |
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
arXiv (2026) · doi:10.48550/arxiv.2610.14118 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14143 | scored |
Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
arXiv (2026) · doi:10.48550/arxiv.2610.14123 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14144 | scored |
Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study
arXiv (2026) · doi:10.48550/arxiv.2610.14238 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 14145 | Screened Out |
Assessing Differential Item Functioning in Performance Assessment: Review and Recommendations
Educational Measurement Issues and Practice (2000) · doi:10.1111/j.1745-3992.2000.tb00033.x · v1.0 |
3.4 (gemini-3.5-flash-lite) | — |
| 14146 | scored |
Data-Driven Maturity Models Development Framework: An Item Response Theory Approach With Digital Transformation Case
IEEE Access (2026) · doi:10.1109/access.2026.3721216 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14147 | scored |
Validating a Critical Success Factor Instrument for Digital Facilities Management Implementation in Malaysia Using the Rasch Measurement Model
International journal of research and scientific innovation (2026) · doi:10.51244/ijrsi.2026.1306000512 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14148 | scored |
WISC-III scores: Evidence of gender-related differential item functioning in Sudan
Journal of Psychology in Africa (2026) · doi:10.32604/jpa.2026.070232 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14149 | scored |
Rasch-Based Validation of Agreement and Usage Instruments for Integrated Project Quality Management Systems in Construction Projects
International Journal of Research and Innovation in Social Science (2026) · doi:10.47772/ijriss.2026.100600662 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 14150 | scored |
Serenity in the Child-to-Youth Transition among Indonesian Students: A Rasch Validation and Gender Differences in the Brief Serenity Scale
Revista de Psicología Clínica con Niños y Adolescentes (2026) · doi:10.21134/rpcna.2026.13.3.4 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |