The Effect of High-Frequency, Automatically-marked Formative Assessments on Student Outcomes in A-Level Sciences

• URL: http://arxiv.org/abs/2607.23566v1
• Date: Sun, 26 Jul 2026 09:32:26 GMT
• Title: The Effect of High-Frequency, Automatically-marked Formative Assessments on Student Outcomes in A-Level Sciences
• Abstract summary: This study investigates the efficacy of deploying a quasi-automated, handwritten assessment platform to remove this bottleneck.<n>Students preparing for STEM A-levels were divided into control (experimental, human marking) and intervention (N = 72, automated marking) groups over a 16-week term.<n>Results indicate that the intervention group achieved a statistically significant improvement in final mock A-level marks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Traditional human marking in upper-secondary STEM education creates a structural bottleneck that restricts the frequency of formative mock examinations. This quasi-experimental, mixed-methods longitudinal study (N = 142) investigates the efficacy of deploying a fully automated, handwritten assessment marking platform to remove this bottleneck. Students preparing for STEM A-levels (Mathematics, Further Mathematics, Biology, Chemistry, Physics) were divided into control (N = 70, human marking) and intervention (N = 72, automated marking) groups over a 16-week term. Results indicate that the intervention group achieved a statistically significant improvement in final mock A-level marks (p < .01), scoring on average 16.8% higher than the control group. Furthermore, assessment turnaround time dropped from 11.2 days to < 0.1 days, enabling a fourfold increase in practice volume. The automated system's capacity for granular marginalia, specifically its Error Carried Forward (ECF) logic, accelerated the correction of procedural misconceptions and significantly boosted student self-efficacy. Practically, these findings validate that automated marking systems serve as high-speed formative loop accelerators, providing international schools with a highly scalable, low-cost intervention to elevate institutional exam outcomes without necessitating increases in staff headcount.

Related papers

• UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction [42.532335022354545]
  Anomaly detection in batch processes is hindered by transient dynamics, scarce fault labels, and reliance on singlemodality sensor data.<n>This work introduces UTOPYA, a multimodal framework that jointly addresses anomaly detection, time-series prediction, and phase classification in batch distillation.<n>A physics-informed regularisation scheme introduced in this work enforces temporal smoothness and thermodynamic monotonicity.
  arXiv  Detail & Related papers  (2026-05-18T10:28:15Z)
• Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs [51.56484100374058]
  guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency.<n>We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks.<n>Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR.
  arXiv  Detail & Related papers  (2026-03-29T18:52:01Z)
• Stabilising Learner Trajectories: A Doubly Robust Evaluation of AI-Guided Student Support using Activity Theory [1.2234742322758418]
  This study evaluates an AI-guided student support system at a large university using doubly robust score matching.<n>Results indicate that the intervention effectively stabilised precarious trajectories.<n>However, effects on the speed of qualification completion were positive but statistically constrained.
  arXiv  Detail & Related papers  (2025-12-11T22:28:12Z)
• Hybrid Instructor Ai Assessment In Academic Projects: Efficiency, Equity, And Methodological Lessons [0.0]
  This study presents the implementation of a generative artificial intelligence (AI) assisted assessment system, supervised by instructors, to grade 33 hydraulics reports.<n>The quantitative results revealed a noteworthy 88% reduction in grading time and a 733% increase in productivity.<n>The system proved to be equitable, exhibiting no bias related to report length, and highly reliable post-calibration.
  arXiv  Detail & Related papers  (2025-10-25T13:11:15Z)
• A Machine Learning-Based Framework to Shorten the Questionnaire for Assessing Autism Intervention [6.233625142245272]
  This study introduces a generalizable machine learning framework that seeks to shorten assessments while maintaining evaluative accuracy.<n>For progress monitoring, the framework identified 16 items that retained strong correlation with total score change and full subdomain coverage.<n>For point-in-time severity assessment, our model achieved over 80% classification accuracy using just 13 items.
  arXiv  Detail & Related papers  (2025-10-22T20:26:53Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent [58.05410015124021]
  We introduce AutoSGD: an SGD method that automatically determines whether to increase or decrease the learning rate at a given iteration.<n> Empirical results suggest strong performance of the method on a variety of traditional optimization problems and machine learning tasks.
  arXiv  Detail & Related papers  (2025-05-27T18:25:21Z)
• A Novel Multi-Task Teacher-Student Architecture with Self-Supervised Pretraining for 48-Hour Vasoactive-Inotropic Trend Analysis in Sepsis Mortality Prediction [0.0]
  We propose a novel Teacher-Student multitask framework with self-supervised sepsis pretraining via a Masked Autoencoder (MAE)<n>The teacher model performs mortality classification and severity-score regression, while the student distills robust time-series representations.<n>Compared to LSTM-based methods, our approach achieves an AUROC of 0.82 on MIMIC-IV 3.0 (9,476 patients), outperforming the baseline (0.74)<n>Our novel multitask and distillation strategies enable earlier identification of high-risk patients, improving prediction accuracy and disease management, offering new tools for ICU decision support.
  arXiv  Detail & Related papers  (2025-02-24T04:38:59Z)
• IFRA: a machine learning-based Instrumented Fall Risk Assessment Scale derived from Instrumented Timed Up and Go test in stroke patients [39.82556598631489]
  IFRA stands for Instrumented Fall Risk Assessment.<n>Features considered in the IFRA scale include gait speed, vertical acceleration during sit-to-walk transition, and turning angular velocity.<n>IFRA is the only scale to correctly assign more than half of the fallers to the high-risk stratum.
  arXiv  Detail & Related papers  (2025-01-16T15:20:22Z)
• Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection [70.86672569101536]
  Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression. This paper investigates the use of prompt-based fine-tuning of PLMs that consistently uses AD classification errors as the training objective function.
  arXiv  Detail & Related papers  (2022-10-29T09:18:41Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.