Synthetic Student Responses: LLM-Extracted Features for IRT Difficulty Parameter Estimationcs.AI updates on arXiv.org arXiv:2602.00034v1 Announce Type: cross
Abstract: Educational assessment relies heavily on knowing question difficulty, traditionally determined through resource-intensive pre-testing with students. This creates significant barriers for both classroom teachers and assessment developers. We investigate whether Item Response Theory (IRT) difficulty parameters can be accurately estimated without student testing by modeling the response process and explore the relative contribution of different feature types to prediction accuracy. Our approach combines traditional linguistic features with pedagogical insights extracted using Large Language Models (LLMs), including solution step count, cognitive complexity, and potential misconceptions. We implement a two-stage process: first training a neural network to predict how students would respond to questions, then deriving difficulty parameters from these simulated response patterns. Using a dataset of over 250,000 student responses to mathematics questions, our model achieves a Pearson correlation of approximately 0.78 between predicted and actual difficulty parameters on completely unseen questions.
arXiv:2602.00034v1 Announce Type: cross
Abstract: Educational assessment relies heavily on knowing question difficulty, traditionally determined through resource-intensive pre-testing with students. This creates significant barriers for both classroom teachers and assessment developers. We investigate whether Item Response Theory (IRT) difficulty parameters can be accurately estimated without student testing by modeling the response process and explore the relative contribution of different feature types to prediction accuracy. Our approach combines traditional linguistic features with pedagogical insights extracted using Large Language Models (LLMs), including solution step count, cognitive complexity, and potential misconceptions. We implement a two-stage process: first training a neural network to predict how students would respond to questions, then deriving difficulty parameters from these simulated response patterns. Using a dataset of over 250,000 student responses to mathematics questions, our model achieves a Pearson correlation of approximately 0.78 between predicted and actual difficulty parameters on completely unseen questions. Read More
Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusioncs.AI updates on arXiv.org arXiv:2602.00152v1 Announce Type: cross
Abstract: The demand for accurate on-device pattern recognition in edge applications is intensifying, yet existing approaches struggle to reconcile accuracy with computational constraints. To address this challenge, a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules, namely the Hierarchical Parallel Pseudo-image Enhancement Fusion Network (HPPI-Net), is proposed for real-time, on-device Human Activity Recognition (HAR). Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy while utilizing only 22.3 KiB of RAM and 439.5 KiB of ROM after optimization. HPPI-Net employs a two-layer architecture. The first layer extracts preliminary features using Fast Fourier Transform (FFT) spectrograms, while the second layer selectively activates either a dedicated module for stationary activity recognition or a parallel LSTM-MobileNet network (PLMN) for dynamic states. PLMN fuses FFT, Wavelet, and Gabor spectrograms through three parallel LSTM encoders and refines the concatenated features using Efficient Channel Attention (ECA) and Depthwise Separable Convolution (DSC), thereby offering channel-level interpretability while substantially reducing multiply-accumulate operations. Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%. These results demonstrate that HPPI-Net achieves a favorable accuracy-efficiency trade-off and provides explainable predictions, establishing a practical solution for wearable, industrial, and smart home HAR on memory-constrained edge platforms.
arXiv:2602.00152v1 Announce Type: cross
Abstract: The demand for accurate on-device pattern recognition in edge applications is intensifying, yet existing approaches struggle to reconcile accuracy with computational constraints. To address this challenge, a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules, namely the Hierarchical Parallel Pseudo-image Enhancement Fusion Network (HPPI-Net), is proposed for real-time, on-device Human Activity Recognition (HAR). Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy while utilizing only 22.3 KiB of RAM and 439.5 KiB of ROM after optimization. HPPI-Net employs a two-layer architecture. The first layer extracts preliminary features using Fast Fourier Transform (FFT) spectrograms, while the second layer selectively activates either a dedicated module for stationary activity recognition or a parallel LSTM-MobileNet network (PLMN) for dynamic states. PLMN fuses FFT, Wavelet, and Gabor spectrograms through three parallel LSTM encoders and refines the concatenated features using Efficient Channel Attention (ECA) and Depthwise Separable Convolution (DSC), thereby offering channel-level interpretability while substantially reducing multiply-accumulate operations. Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%. These results demonstrate that HPPI-Net achieves a favorable accuracy-efficiency trade-off and provides explainable predictions, establishing a practical solution for wearable, industrial, and smart home HAR on memory-constrained edge platforms. Read More
EigenAI: Deterministic Inference, Verifiable Resultscs.AI updates on arXiv.org arXiv:2602.00182v1 Announce Type: cross
Abstract: EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem. At a high level, it combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol so that every inference result can be publicly audited, reproduced, and, if necessary, economically enforced. An untrusted operator runs inference on a fixed GPU architecture, signs and encrypts the request and response, and publishes the encrypted log to EigenDA. During a challenge window, any watcher may request re-execution through EigenVerify; the result is then deterministically recomputed inside a trusted execution environment (TEE) with a threshold-released decryption key, allowing a public challenge with private data. Because inference itself is bit-exact, verification reduces to a byte-equality check, and a single honest replica suffices to detect fraud. We show how this architecture yields sovereign agents — prediction-market judges, trading bots, and scientific assistants — that enjoy state-of-the-art performance while inheriting security from Ethereum’s validator base.
arXiv:2602.00182v1 Announce Type: cross
Abstract: EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem. At a high level, it combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol so that every inference result can be publicly audited, reproduced, and, if necessary, economically enforced. An untrusted operator runs inference on a fixed GPU architecture, signs and encrypts the request and response, and publishes the encrypted log to EigenDA. During a challenge window, any watcher may request re-execution through EigenVerify; the result is then deterministically recomputed inside a trusted execution environment (TEE) with a threshold-released decryption key, allowing a public challenge with private data. Because inference itself is bit-exact, verification reduces to a byte-equality check, and a single honest replica suffices to detect fraud. We show how this architecture yields sovereign agents — prediction-market judges, trading bots, and scientific assistants — that enjoy state-of-the-art performance while inheriting security from Ethereum’s validator base. Read More
Recent major cloud service outages have been hard to miss. High-profile incidents affecting providers such as AWS, Azure, and Cloudflare have disrupted large parts of the internet, taking down websites and services that many other systems depend on. The resulting ripple effects have halted applications and workflows that many organizations rely on every day. For […]
Silicon Darwinism: Why Scarcity Is the Source of True IntelligenceTowards Data Science We are confusing “size” with “smart.” The next leap in artificial intelligence will not come from a larger data center, but from a more constrained environment.
The post Silicon Darwinism: Why Scarcity Is the Source of True Intelligence appeared first on Towards Data Science.
We are confusing “size” with “smart.” The next leap in artificial intelligence will not come from a larger data center, but from a more constrained environment.
The post Silicon Darwinism: Why Scarcity Is the Source of True Intelligence appeared first on Towards Data Science. Read More
5 Android Apps for Code EditingKDnuggets From debugging to quick fixes, here are the top Android apps every developer should have on their phone.
From debugging to quick fixes, here are the top Android apps every developer should have on their phone. Read More
Klarna backs Google UCP to power AI agent paymentsAI News Klarna aims to address the lack of interoperability between conversational AI agents and backend payment systems by backing Google’s Universal Commerce Protocol (UCP), an open standard designed to unify how AI agents discover products and execute transactions. The partnership, which also sees Klarna supporting Google’s Agent Payments Protocol (AP2), places the Swedish fintech firm among
The post Klarna backs Google UCP to power AI agent payments appeared first on AI News.
Klarna aims to address the lack of interoperability between conversational AI agents and backend payment systems by backing Google’s Universal Commerce Protocol (UCP), an open standard designed to unify how AI agents discover products and execute transactions. The partnership, which also sees Klarna supporting Google’s Agent Payments Protocol (AP2), places the Swedish fintech firm among
The post Klarna backs Google UCP to power AI agent payments appeared first on AI News. Read More
How Clarus Care uses Amazon Bedrock to deliver conversational contact center interactionsArtificial Intelligence In this post, we illustrate how Clarus Care, a healthcare contact center solutions provider, worked with the AWS Generative AI Innovation Center (GenAIIC) team to develop a generative AI-powered contact center prototype. This solution enables conversational interaction and multi-intent resolution through an automated voicebot and chat interface. It also incorporates a scalable service model to support growth, human transfer capabilities–when requested or for urgent cases–and an analytics pipeline for performance insights.
In this post, we illustrate how Clarus Care, a healthcare contact center solutions provider, worked with the AWS Generative AI Innovation Center (GenAIIC) team to develop a generative AI-powered contact center prototype. This solution enables conversational interaction and multi-intent resolution through an automated voicebot and chat interface. It also incorporates a scalable service model to support growth, human transfer capabilities–when requested or for urgent cases–and an analytics pipeline for performance insights. Read More
Building Systems That Survive Real LifeTowards Data Science Sara Nobrega on the transition from data science to AI engineering, using LLMs as a bridge to DevOps, and the one engineering skill junior data scientists need to stay competitive.
The post Building Systems That Survive Real Life appeared first on Towards Data Science.
Sara Nobrega on the transition from data science to AI engineering, using LLMs as a bridge to DevOps, and the one engineering skill junior data scientists need to stay competitive.
The post Building Systems That Survive Real Life appeared first on Towards Data Science. Read More
Working with Billion-Row Datasets in Python (Using Vaex)KDnuggets Analyze billion-row datasets in Python using Vaex. Learn how out-of-core processing, lazy evaluation, and memory mapping enable fast analytics at scale.
Analyze billion-row datasets in Python using Vaex. Learn how out-of-core processing, lazy evaluation, and memory mapping enable fast analytics at scale. Read More
