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: 19329 →
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 | 9624 |
gemini-3.5-flash-lite | 9033 |
— | 738 |
| Analysis model | prompt | Analyses |
|---|---|---|
gemini-3.1-flash-lite | v2.1 | 275 |
gemini-3.6-flash | v2.1 | 273 |
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) | 18931 |
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): 16549 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 | 10701 | 2 (too few) | 0 | 0% |
| 2.0–4.0 | 4473 | 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: 764
Quality Stratification
🟢 High rigor (M ≥ 7.0): 356
🟡 Moderate rigor (4.0 ≤ M < 7.0): 381
🔴 Low rigor (M < 4.0): 27
| Study Design | Paper Count |
|---|---|
psychometric_modeling | 289 |
other | 55 |
theoretical | 27 |
rct | 17 |
assessment_design | 214 |
natural_experiment | 5 |
quasi_experiment | 61 |
review | 25 |
detector_evaluation | 50 |
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=393, 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 (53)
#academic integrity (53)
#assessment validity (52)
#Automated Essay Scoring (46)
#item response theory (46)
#higher education (45)
#automated essay scoring (40)
#Construct Validity (32)
#Generative AI (32)
#LLM as rater (28)
#construct validity (27)
#Large Language Models (26)
#Higher Education (24)
#IRT (24)
#LLM Evaluation (24)
#large language models (24)
#GPT-4 (22)
#generative AI (22)
#assessment redesign (21)
#Academic Integrity (20)
#Automated Scoring (20)
#ChatGPT (20)
#prompt engineering (20)
#LLM as Rater (17)
#Prompt Engineering (17)
#automated scoring (17)
#Assessment Redesign (16)
#assessment design (16)
#assessment_design (16)
#validity (15)
#AI-resilient assessment (14)
#Computer Science Education (13)
#LLMs as raters (13)
#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 |
|---|---|---|---|---|
| 18551 | Screened Out |
PasteTrace: A Single Source Plagiarism Detection Tool For Introductory Programming Courses
arXiv (2025) · doi:10.48550/arxiv.2506.17355 · v1.0 |
4.6 (gemini-3.5-flash-lite) | — |
| 18552 | Screened Out |
Unpacking Generative AI in Education: Computational Modeling of Teacher and Student Perspectives in Social Media Discourse
arXiv (2025) · doi:10.1109/tcss.2025.3630587 · v1.0 |
4.1 (gemini-3.5-flash-lite) | — |
| 18553 | Screened Out |
"How can we learn and use AI at the same time?": Participatory Design of GenAI with High School Students
arXiv (2025) · doi:10.1145/3713043.3727057 · v1.0 |
2.2 (gemini-3.5-flash-lite) | — |
| 18554 | Screened Out |
A Review of Generative AI in Computer Science Education: Challenges and Opportunities in Accuracy, Authenticity, and Assessment
arXiv (2025) · doi:10.48550/arxiv.2507.11543 · v1.0 |
3.0 (gemini-3.5-flash-lite) | — |
| 18555 | Screened Out |
Assessing Classical Machine Learning and Transformer-based Approaches for Detecting AI-Generated Research Text
arXiv (2025) · doi:10.48550/arxiv.2509.20375 · v1.0 |
2.6 (gemini-3.1-flash-lite) | — |
| 18556 | Screened Out |
Generative AI performance in core undergraduate mathematics: a curriculum-level case study
arXiv (2025) · doi:10.48550/arxiv.2509.13359 · v1.0 |
4.6 (gemini-3.1-flash-lite) | — |
| 18557 | Screened Out |
Detecting AI-Assisted Cheating in Online Exams through Behavior Analytics
arXiv (2025) · doi:10.48550/arxiv.2510.18881 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 18558 | Screened Out |
Enhancing Engagement and Learning in Computing Education: Automated Moodle-Based Problem-Solving Assessments
arXiv (2025) · doi:10.48550/arxiv.2508.17191 · v1.0 |
3.4 (gemini-3.1-flash-lite) | — |
| 18559 | Screened Out |
Opportunities and Challenges of Integrating ChatGPT in Education: Sentiment Analysis and Topic Modeling
arXiv (2025) · doi:10.1080/08832323.2025.2536255 · v1.0 |
1.9 (gemini-3.1-flash-lite) | — |
| 18560 | Screened Out |
Predicting ChatGPT Use in Assignments: Implications for AI-Aware Assessment Design
arXiv (2025) · doi:10.48550/arxiv.2508.12013 · v1.0 |
4.8 (gemini-3.1-flash-lite) | — |
| 18561 | Screened Out |
CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection
arXiv (2025) · doi:10.48550/arxiv.2508.11933 · v1.0 |
3.5 (gemini-3.1-flash-lite) | — |
| 18562 | scored |
Navigating the New Landscape: A Conceptual Model for Project-Based Assessment (PBA) in the Age of GenAI
arXiv (2025) · doi:10.48550/arxiv.2508.11709 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18563 | Screened Out |
AINL-Eval 2025 Shared Task: Detection of AI-Generated Scientific Abstracts in Russian
arXiv (2025) · doi:10.48550/arxiv.2508.09622 · v1.0 |
3.2 (gemini-3.1-flash-lite) | — |
| 18564 | Screened Out |
Analytics of Adaptive Online Testing in Practice Over a Decade
arXiv (2025) · doi:10.48550/arxiv.2508.08643 · v1.0 |
2.6 (gemini-3.1-flash-lite) | — |
| 18565 | scored |
TritonRL: Training LLMs to Think and Code Triton Without Cheating
arXiv (2025) · doi:10.48550/arxiv.2510.17891 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18566 | scored |
ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation
arXiv (2025) · doi:10.48550/arxiv.2510.16549 · v1.0 |
5.2 (gemini-3.1-flash-lite) | — |
| 18567 | Screened Out |
Generate Logical Equivalence Questions
arXiv (2025) · doi:10.48550/arxiv.2510.12001 · v1.0 |
3.7 (gemini-3.1-flash-lite) | — |
| 18568 | scored |
Quantum Agents for Algorithmic Discovery
arXiv (2025) · doi:10.48550/arxiv.2510.08159 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18569 | scored |
Benchmarking is Broken -- Don't Let AI be its Own Judge
arXiv (2025) · doi:10.48550/arxiv.2510.07575 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18570 | Screened Out |
Beyond the Benefits: A Systematic Review of the Harms and Consequences of Generative AI in Computing Education
arXiv (2025) · doi:10.1145/3769994.3770036 · v1.0 |
2.5 (gemini-3.1-flash-lite) | — |
| 18571 | Screened Out |
Teaching with AI: A Systematic Review of Chatbots, Generative Tools, and Tutoring Systems in Programming Education
arXiv (2025) · doi:10.26803/ijlter.25.1.1 · v1.0 |
2.3 (gemini-3.1-flash-lite) | — |
| 18572 | abstract_only |
Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
arXiv (2025) · doi:10.48550/arxiv.2510.01367 · v1.0 |
6.1 (gemini-3.1-flash-lite) | — |
| 18573 | Screened Out |
Adversarial Reinforcement Learning Framework for ESP Cheater Simulation
arXiv (2025) · doi:10.48550/arxiv.2509.24274 · v1.0 |
4.0 (gemini-3.1-flash-lite) | — |
| 18574 | Screened Out |
Artificial Intelligence-Powered Assessment Framework for Skill-Oriented Engineering Lab Education
arXiv (2025) · doi:10.48550/arxiv.2509.25258 · v1.0 |
4.2 (gemini-3.1-flash-lite) | — |
| 18575 | In Buffer |
AiAWE: An Open-Source LLM Automated Writing Evaluation System Using LoRA-Adapted Instruction-Tuned Models
arXiv (2026) · doi:10.48550/arxiv.2606.12801 · v1.0 |
4.8 (gemini-3.6-flash) | — |
| 18576 | abstract_only |
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
arXiv (2026) · doi:10.48550/arxiv.2606.12730 · v1.0 |
5.8 (gemini-3.1-flash-lite) | — |
| 18577 | scored |
ChargeBD: Character-Aware Heterogeneous Agent Reasoning for Guided Engineering in Battery Development
arXiv (2026) · doi:10.48550/arxiv.2606.12057 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18578 | abstract_only |
The GenAI Skill Bypass: Mapping Divergent Pathways of University Students and Staff AI Literacy
arXiv (2026) · doi:10.48550/arxiv.2607.05411 · v1.0 |
6.1 (gemini-3.1-flash-lite) | — |
| 18579 | No Fulltext |
Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional Judgment
arXiv (2026) · doi:10.48550/arxiv.2606.11678 · v1.0 |
6.1 (gemini-3.1-flash-lite) | — |
| 18580 | abstract_only |
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
arXiv (2026) · doi:10.48550/arxiv.2606.10479 · v1.0 |
6.6 (gemini-3.1-flash-lite) | — |
| 18581 | scored |
The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring
arXiv (2026) · doi:10.48550/arxiv.2606.10327 · v1.0 |
5.0 (gemini-3.1-flash-lite) | — |
| 18582 | scored |
The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
arXiv (2026) · doi:10.48550/arxiv.2606.07422 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18583 | Screened Out |
DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios
arXiv (2026) · doi:10.1145/3770855.3817874 · v1.0 |
3.7 (gemini-3.1-flash-lite) | — |
| 18584 | abstract_only |
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
arXiv (2026) · doi:10.18653/v1/2026.acl-long.1901 · v1.0 |
5.3 (gemini-3.1-flash-lite) | — |
| 18585 | scored |
Position: Reasoning is a Learnable Rule-Based Process
arXiv (2026) · doi:10.48550/arxiv.2608.12325 · v1.0 |
0.0 (gemini-3.1-flash-lite) | — |
| 18586 | Included |
Auditing LLM Benchmarks with Item Response Theory
arXiv (2026) · doi:10.48550/arxiv.2605.30504 · v1.0 |
7.3 (gemini-3.6-flash) | — |
| 18587 | Screened Out |
ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation
arXiv (2026) · doi:10.48550/arxiv.2605.29791 · v1.0 |
4.6 (gemini-3.1-flash-lite) | — |
| 18588 | Screened Out |
NICE: A Theory-Grounded Diagnostic Benchmark for Social Intelligence of LLMs
arXiv (2026) · doi:10.48550/arxiv.2605.29685 · v1.0 |
2.8 (gemini-3.1-flash-lite) | — |
| 18589 | abstract_only |
FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification
arXiv (2026) · doi:10.48550/arxiv.2605.29586 · v1.0 |
6.1 (gemini-3.1-flash-lite) | — |
| 18590 | In Buffer |
Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization
arXiv (2026) · doi:10.48550/arxiv.2605.29274 · v1.0 |
6.2 (gemini-3.6-flash) | — |
| 18591 | In Buffer |
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
arXiv (2026) · doi:10.48550/arxiv.2606.28186 · v1.0 |
6.8 (gemini-3.7-flash) | — |
| 18592 | Included |
Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores
arXiv (2026) · doi:10.48550/arxiv.2608.26137 · v1.0 |
7.4 (gemini-3.8-flash) | — |
| 18593 | scored |
CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection
arXiv (2026) · doi:10.48550/arxiv.2608.00014 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 18594 | scored |
InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy
arXiv (2026) · doi:10.48550/arxiv.2606.25984 · v1.0 |
0.0 (gemini-3.5-flash-lite) | — |
| 18595 | In Buffer |
Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games
arXiv (2026) · doi:10.48550/arxiv.2606.25358 · v1.0 |
3.0 (gemini-3.6-flash) | — |
| 18596 | In Buffer |
The Easy Trap: Why LLMs Underestimate Misconception-Driven Difficulty
arXiv (2026) · doi:10.48550/arxiv.2607.26067 · v1.0 |
5.7 (gemini-3.8-flash) | — |
| 18597 | In Buffer |
Latent Confidence Alignment for LLM Self-Assessment
arXiv (2026) · doi:10.48550/arxiv.2606.21937 · v1.0 |
6.5 (gemini-3.6-flash) | — |
| 18598 | In Buffer |
AgentCAT: Simulating Computerized Adaptive Testing via Multi-Agent Large Language Models
arXiv (2026) · doi:10.48550/arxiv.2606.21832 · v1.0 |
3.7 (gemini-3.7-flash) | — |
| 18599 | Screened Out |
PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback
arXiv (2026) · doi:10.48550/arxiv.2606.20287 · v1.0 |
3.5 (gemini-3.5-flash-lite) | — |
| 18600 | abstract_only |
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact
arXiv (2026) · doi:10.48550/arxiv.2606.20205 · v1.0 |
6.9 (gemini-3.1-flash-lite) | — |