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: 20521 →
Screen: 19341 →
Eligible: 2807 →
Included: 105
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 = 105 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 | 18382 | 2026-11-14 16:12 |
ref — reference lists of read works | 2112 | 2026-11-14 14:30 |
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 | 18382 | 2026-10-06 | 2026-11-14 |
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 | 9635 |
gemini-3.5-flash-lite | 9033 |
— | 739 |
| Analysis model | prompt | Analyses |
|---|---|---|
gemini-3.6-flash | v2.1 | 278 |
gemini-3.1-flash-lite | v2.1 | 275 |
gemini-3.8-flash | v2.1 | 117 |
gemini-3.7-flash | v2.1 | 109 |
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) | 18943 |
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): 16561 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 | 10708 | 2 (too few) | 0 | 0% |
| 2.0–4.0 | 4478 | 0 (too few) | 0 | — |
| 4.0–5.0 | 1375 | 2 (too few) | 0 | 0% |
| 5.0–6.0 ✓ | 1549 | 3 | 2 | 67% |
| 6.0–8.0 ✓ | 1197 | 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)
6.44 / 10
Analyzed papers: 769
Quality Stratification
🟢 High rigor (M ≥ 7.0): 356
🟡 Moderate rigor (4.0 ≤ M < 7.0): 386
🔴 Low rigor (M < 4.0): 27
| Study Design | Paper Count |
|---|---|
psychometric_modeling | 289 |
other | 55 |
theoretical | 27 |
rct | 17 |
assessment_design | 215 |
quasi_experiment | 63 |
natural_experiment | 5 |
review | 25 |
detector_evaluation | 51 |
survey | 8 |
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=397, 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 (117)
#Psychometrics (71)
#Item Response Theory (61)
#Assessment Validity (54)
#academic integrity (53)
#assessment validity (53)
#Automated Essay Scoring (46)
#item response theory (46)
#higher education (45)
#automated essay scoring (41)
#Generative AI (34)
#Construct Validity (33)
#LLM as rater (28)
#construct validity (27)
#Large Language Models (26)
#Higher Education (25)
#GPT-4 (24)
#IRT (24)
#LLM Evaluation (24)
#large language models (24)
#Academic Integrity (22)
#generative AI (22)
#assessment redesign (21)
#prompt engineering (21)
#Automated Scoring (20)
#ChatGPT (20)
#Assessment Redesign (17)
#LLM as Rater (17)
#Prompt Engineering (17)
#automated scoring (17)
#assessment design (16)
#assessment_design (16)
#validity (15)
#AI-resilient assessment (14)
#Computer Science Education (14)
#LLMs as raters (14)
#automated assessment (13)
#differential item functioning (13)
#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)
#Medical Education (10)
#automated item generation (10)
#automated_essay_scoring (10)
#computerized adaptive testing (10)
#item_response_theory (10)
| # | Status / Stage | Paper | LLM Score | Expert Review |
|---|---|---|---|---|
| 19851 | In Buffer |
When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
arXiv (2026) · doi:10.48550/arxiv.2609.01519 · v1.0 |
7.5 (gemini-3.1-flash-lite) |
👎 Rejected
off_topic Стаття не по темі |
| 19852 | scored |
SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents
arXiv (2026) · doi:10.48550/arxiv.2609.00434 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 19853 | Included |
Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation
arXiv (2026) · doi:10.48550/arxiv.2608.29887 · v1.0 |
7.5 (gemini-3.1-flash-lite) | — |
| 19854 | Included |
LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora
arXiv (2026) · doi:10.48550/arxiv.2608.29517 · v1.0 |
8.7 (gemini-3.1-flash-lite) |
👍 Approved
strong_evidence Доречно буде до статті про взаємо оцінювання |
| 19855 | In Buffer |
A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
arXiv (2026) · doi:10.48550/arxiv.2608.28407 · v1.0 |
5.7 (gemini-3.1-flash-lite) | — |
| 19856 | In Buffer |
Integrating Network Psychometrics and LLMs: The Ising-Embeddings-Model applied to Reliability Auditing
arXiv (2026) · doi:10.48550/arxiv.2608.26790 · v1.0 |
6.3 (gemini-3.1-flash-lite) | — |
| 19857 | scored |
Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference
arXiv (2026) · doi:10.48550/arxiv.2608.26674 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 19858 | In Buffer |
GenAIT: Development and Validation of an Objective Generative AI Literacy Test for High School Students
arXiv (2026) · doi:10.48550/arxiv.2608.25815 · v1.0 |
5.7 (gemini-3.1-flash-lite) | — |
| 19859 | Included |
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments
arXiv (2026) · doi:10.48550/arxiv.2608.24825 · v1.0 |
7.5 (gemini-3.1-flash-lite) | — |
| 19860 | Included |
A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation
arXiv (2026) · doi:10.48550/arxiv.2608.24419 · v1.0 |
8.0 (gemini-3.1-flash-lite) |
👍 Approved
fresh_idea |
| 19861 | In Buffer |
Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing
arXiv (2026) · doi:10.48550/arxiv.2608.24005 · v1.0 |
6.5 (gemini-3.1-flash-lite) | — |
| 19862 | In Buffer |
Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring
arXiv (2026) · doi:10.48550/arxiv.2608.23814 · v1.0 |
6.5 (gemini-3.1-flash-lite) | — |
| 19863 | In Buffer |
From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning
arXiv (2026) · doi:10.48550/arxiv.2608.22566 · v1.0 |
6.3 (gemini-3.1-flash-lite) | — |
| 19864 | In Buffer |
LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model
arXiv (2026) · doi:10.48550/arxiv.2608.22295 · v1.0 |
6.8 (gemini-3.1-flash-lite) | — |
| 19865 | scored |
Who Trusts AI with Their Emotions? Trust Formation and Sociodemographic Variation in LLM Use for Emotional Support
arXiv (2026) · doi:10.48550/arxiv.2608.21220 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 19866 | scored |
Are LLMs becoming similarly creative? Evidence from three years of models
arXiv (2026) · doi:10.48550/arxiv.2608.19437 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 19867 | In Buffer |
Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular Example Pilot
arXiv (2026) · doi:10.48550/arxiv.2608.15382 · v1.0 |
6.0 (gemini-3.1-flash-lite) | — |
| 19868 | Screened Out |
Understanding Generative AI Use in Programming MOOCs: The Role of Course Context and Learner Characteristics
arXiv (2026) · doi:10.48550/arxiv.2610.04447 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 19869 | In Buffer |
LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games
arXiv (2026) · doi:10.48550/arxiv.2610.04441 · v1.0 |
6.9 (gemini-3.1-flash-lite) | — |
| 19870 | scored |
Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media
arXiv (2026) · doi:10.48550/arxiv.2610.04401 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19871 | In Buffer |
Anticipating the Consequences of Curriculum Decisions with Large Language Models
arXiv (2026) · doi:10.48550/arxiv.2610.04604 · v1.0 |
6.6 (gemini-3.1-flash-lite) | — |
| 19872 | Included |
DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation
arXiv (2026) · doi:10.48550/arxiv.2610.04596 · v1.0 |
7.0 (gemini-3.1-flash-lite) | — |
| 19873 | In Buffer |
DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
arXiv (2026) · doi:10.48550/arxiv.2610.04825 · v1.0 |
6.8 (gemini-3.1-flash-lite) | — |
| 19874 | Screened Out |
Assessing law students in a GenAI world to create knowledgeable future lawyers
International Journal of the Legal Profession (2024) · doi:10.1080/09695958.2024.2379785 · v1.0 |
2.6 (gemini-3.1-flash-lite) | — |
| 19875 | Screened Out |
ChatGPT in public policy teaching and assessment: An examination of opportunities and challenges
Australian Journal of Public Administration (2024) · doi:10.1111/1467-8500.12647 · v1.0 |
2.0 (gemini-3.1-flash-lite) | — |
| 19876 | scored |
Graduate Employability in the AI-Driven Economy
Academy of Management Proceedings (2024) · doi:10.5465/amproc.2024.15967abstract · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19877 | Screened Out |
Interplay of rationality and morality in using ChatGPT for academic misconduct
Behaviour and Information Technology (2024) · doi:10.1080/0144929x.2024.2325023 · v1.0 |
2.7 (gemini-3.1-flash-lite) | — |
| 19878 | scored |
Communicating Clear Guidance: Advice for Generative AI Policy Development in Higher Education
Business and Professional Communication Quarterly (2024) · doi:10.1177/23294906241254786 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19879 | scored |
Graduate Teacher Education Students Use and Evaluate ChatGPT as an Essay-Writing Tool
Online Learning (2024) · doi:10.24059/olj.v28i2.4373 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19880 | Screened Out |
Using Generative Artificial Intelligence Tools to Explain and Enhance Experiential Learning for Authentic Assessment
Education Sciences (2024) · doi:10.3390/educsci14010083 · v1.0 |
1.8 (gemini-3.1-flash-lite) | — |
| 19881 | scored |
What we measure … and what we should measure in medical education
Medical Education (2018) · doi:10.1111/medu.13652 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19882 | scored |
ChatGPT and higher education assessments: More opportunities than concerns?
Journal of Applied Learning & Teaching (2023) · doi:10.37074/jalt.2023.6.2.32 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19883 | Screened Out |
Rethinking Higher Education Teaching and Assessment In-Line with AI Innovations: A Systematic Review and Meta-Analysis
African Journal of Empirical Research (2024) · doi:10.51867/ajernet.5.3.30 · v1.0 |
2.1 (gemini-3.1-flash-lite) | — |
| 19884 | scored |
Generative AI in Education: Pedagogical, Theoretical, and Methodological Perspectives
International Journal of Technology in Education (2024) · doi:10.46328/ijte.845 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19885 | In Buffer |
Race with the machines: Assessing the capability of generative AI in solving authentic assessments
Australasian Journal of Educational Technology (2023) · doi:10.14742/ajet.8902 · v1.0 |
5.0 (gemini-3.1-flash-lite) | — |
| 19886 | scored |
INSTITUTIONAL POLICIES ON ARTIFICIAL INTELLIGENCE IN UNIVERSITY LEARNING, TEACHING AND RESEARCH
Information Technologies and Learning Tools (2023) · doi:10.33407/itlt.v97i5.5395 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19887 | scored |
AI-Driven transformations in higher education: Opportunities and challenges
Zenodo (CERN European Organization for Nuclear Research) (2023) · doi:10.5281/zenodo.8164415 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19888 | Screened Out |
Speculative futures on ChatGPT and generative artificial intelligence (AI): A collective reflection from the educational landscape
Dublin City University Open Access Institutional Repository (Dublin City University) (2023) · doi:10.5281/zenodo.7636568 · v1.0 |
1.4 (gemini-3.5-flash-lite) | — |
| 19889 | Screened Out |
The Potential and Concerns of Using AI in Scientific Research: ChatGPT Performance Evaluation
JMIR Medical Education (2023) · doi:10.2196/47049 · v1.0 |
3.2 (gemini-3.5-flash-lite) | — |
| 19890 | Screened Out |
Implementing Artificial Intelligence in Higher Education: Pros and Cons from the Perspectives of Academics
Societies (2023) · doi:10.3390/soc13050118 · v1.0 |
2.5 (gemini-3.5-flash-lite) | — |
| 19891 | Screened Out |
On the Limits of Artificial Intelligence (AI) in Education
Nordisk tidsskrift for pedagogikk og kritikk (2024) · doi:10.23865/ntpk.v10.6062 · v1.0 |
1.9 (gemini-3.5-flash-lite) | — |
| 19892 | scored |
Guidance for generative AI in education and research
UNESCO eBooks (2023) · doi:10.54675/ewzm9535 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19893 | Screened Out |
Managing the Strategic Transformation of Higher Education through Artificial Intelligence
Administrative Sciences (2023) · doi:10.3390/admsci13090196 · v1.0 |
1.6 (gemini-3.5-flash-lite) | — |
| 19894 | scored |
What Is Academic Integrity?
Sage eBooks (2022) · doi:10.4135/9781071887233 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19895 | scored |
Promoting Academic Integrity in Institutions of Higher Learning: What 30 Years of Research (1990-2020) in Australasia Has Taught Us
Journal of College and Character (2022) · doi:10.1080/2194587x.2021.2017972 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19896 | scored |
Faculty and student perceptions on college cheating: evidence from Turkey
Educational Studies (2010) · doi:10.1080/03055698.2010.506321 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19897 | scored |
An analysis of university academic integrity policies in New Zealand
Journal of Further and Higher Education (2022) · doi:10.1080/0309877x.2022.2130195 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19898 | scored |
Can Students' Academic Integrity Be Improved? Attitudes and Behaviors Before and After Implementation of an Academic Integrity Policy
Teaching Business Ethics (2001) · doi:10.1023/a:1026551002367 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 19899 | scored |
The role of authentic assessment to preserve academic integrity and promote skill development and employability
Studies in Higher Education (2019) · doi:10.1080/03075079.2019.1582015 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 19900 | scored |
Core elements of exemplary academic integrity policy in Australian higher education
International Journal for Educational Integrity (2011) · doi:10.21913/ijei.v7i2.759 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |