Shap
PulseAugur coverage of Shap — every cluster mentioning Shap across labs, papers, and developer communities, ranked by signal.
- used by alphaXiv 90%
- used by Local Interpretable Model Agnostic Explanations 70%
- used by ScienceCast 70%
- used by Gotit.pub 70%
- instance of alphaXiv 70%
- used by Shapley Additive Explanations 70%
- used by Integrated Gradients 70%
- used by SpaceXAI 70%
- used by logistic regression model 70%
- used by Grad-CAM++ 70%
- used by optuna 70%
- used by CatalyzeX 70%
15 day(s) with sentiment data
-
New multi-agent system tailors AI explanations for diverse audiences
Researchers have developed XstrAI, a novel multi-agent framework designed to generate audience-aware narratives for explaining AI model predictions, particularly in the medical field. This system treats feature-attribut…
-
AI framework maps flood and landslide risks with spatial awareness
Researchers have developed a novel framework to map flood and landslide susceptibility and risk across regions like Kerala, India, and Nepal. This framework utilizes a spatial heterogeneity-aware approach, comparing two…
-
AI credit models show significant income bias, even when income is hidden
A new research paper published on arXiv details significant income-based disparities in automated credit default prediction models. The study, which analyzed a large dataset from LendingClub Bank, found that high-income…
-
LLM explanations for credit risk fail despite predictive model gains
Researchers have developed a multi-scale stacking ensemble for credit risk prediction that integrates gradient-boosting learners and a residual network, achieving a test ROC-AUC of 0.9539. While this ensemble shows a sm…
-
New AI method detects market manipulation via velocity analysis
Researchers have developed a new method for detecting intraday market manipulation by analyzing the velocity of market state changes rather than just price levels. This approach, detailed in a paper submitted to arXiv, …
-
New intrusion detection system for medical IoT environments
Researchers have developed a novel intrusion detection system for Internet of Medical Things (IoMT) environments, focusing on feature selection to overcome resource limitations. The system employs a Pearson correlation …
-
Machine learning predicts asphalt concrete strength using SHAP analysis
Researchers have developed a machine learning framework to predict the splitting strength of asphalt concrete, utilizing 296 samples and 14 input variables. Six models were compared, with TabPFN demonstrating the best p…
-
New framework fools AI explainability auditors by embedding evasion logic
Researchers have developed a new framework called "Crushing the Evidence" that can fool white-box explainable AI (XAI) auditors. This dual-penalty evasion technique embeds evasion logic directly into model parameters, a…
-
New Bengali Sentiment Analysis Framework Employs Continual Learning and LoRA
Researchers have developed SentiBanglaBERT, a novel two-stage framework for sentiment classification in Bengali, a low-resource language. This approach utilizes domain-adaptive continual pretraining and parameter-effici…
-
New paper links SHAP model interpretation to functional ANOVA decomposition
A new paper published on arXiv explores the statistical underpinnings of SHAP (SHapley Additive exPlanations), a popular method for interpreting machine learning models. The research connects SHAP approximations to the …
-
New framework enables reproducible benchmarking of competing risks survival models
Researchers have developed an open-source framework for benchmarking competing risks survival models, addressing a gap in systematic evaluation and adoption of these statistical and machine learning methods. The framewo…
-
New framework analyzes AI model failures when clinical data is missing
Researchers have developed a new framework to analyze the failure modes of multimodal clinical AI models. This framework, named Loud or Silent, assesses how model accuracy changes when specific modalities are removed, d…
-
BERT model automates mpox research classification with 97% accuracy
Researchers have developed an automated system using BERT to classify mpox research articles into key topics like outbreaks, vaccination, and epidemiology. This multilabel classification approach achieved 97.05% accurac…
-
Quantum-inspired CNNs show mixed results against classical CNNs in medical imaging
Researchers have compared the performance and explainability of a Hybrid Quantum-inspired Convolutional Neural Network (HQiCNN) against a standard Convolutional Neural Network (CNN) for medical image classification. The…
-
New 'interior interpretability' method probes Transformer models
Researchers have introduced a new concept called "interior interpretability" to better understand the internal workings of Transformer models. This approach uses attention rollout, viewing it as an operator that mediate…
-
LLMs boosted for clinical prediction via knowledge injection · arXiv paper
Researchers have developed a novel knowledge-injection framework designed to enhance the zero-shot adaptation of large language models for specialized tasks like delirium prediction in clinical settings. This method aug…
-
New AI framework predicts EV charging station faults using climate data
Researchers have developed FGDSE, a novel interpretable causal-ensemble framework designed to enhance the resilience of electric vehicle (EV) charging infrastructure in sustainable cities. This system aims to shift main…
-
New framework combines synthetic data and federated learning for clinical risk prediction
Researchers have developed SynPre-FL, a novel framework that integrates synthetic data generation with federated learning for privacy-preserving clinical risk prediction. This approach uses an autoencoder-diffusion mode…
-
Phishing detection models vulnerable to adversarial attacks, study finds
A new study published on arXiv compares the effectiveness of two machine learning models, TF-IDF + Logistic Regression and a fine-tuned DistilBERT transformer, in detecting phishing emails. While both models achieved ov…
-
Interpretable ML accurately predicts respiratory disease, highlights PM2.5 impact
A new study published on arXiv explores the use of interpretable machine learning models to predict respiratory disease rates and air quality. The research found that PM2.5 concentration was the most significant predict…