White-box method ReXTrust achieves highest AUC (peak 93.0) on Gut-VLM across five VLMs, outperforming alternatives by statistically significant margins while black-box and some gray-box methods collapse on certain models.
hub
A Handwritten Text Recognition Dataset for Ajami Manuscripts in Fulfulde and Hausa
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
dataset 1
citation-polarity summary
years
2026 14representative citing papers
Jet bundles with Cartan distributions are characterized as polarised N^r_π-contact manifolds of jet type via a recognition theorem in k-contact geometry.
SmellBench is the first benchmark showing LLM agents resolve 47.7% of architectural code smells while accurately spotting false positives, but aggressive repairs often introduce new smells and degrade overall quality.
HARMES is the first large-scale dataset to combine wrist IMU, environmental, and audio sensors for recognizing 15 household activities across over 80 hours of data from 20 participants.
A sequential diffusion framework generates controllable abdominal anatomies with a Volume Control Scalar that decouples organ size from body habitus, achieving Dice scores around 0.83 and reducing distributional mismatch by 73.6% in a hepatomegaly example.
Introduces 2-HRFA and B2-HRFA for picture languages, proves incomparability with CFMG, proper subset relations with RPDA and RFA, and examines closure properties.
KG-TRACE fuses genomic features with RotatE KG embeddings via an epistemic trust gate for AMR prediction, reporting 0.976 AUROC on isoniazid resistance in the CRyPTIC cohort plus 92.5% symbolic coverage via a new Biological Grounding Ratio metric.
A new multi-surface evidence framework for post-quantum TLS observability that combines passive, active, certificate, and registry data to assess endpoint capabilities across TLS 1.2/1.3 scenarios and outperforms prior analyzers in controlled tests and public campaigns.
OpenCLAW-Nexus uses a single discounted Beta-reputation model to unify reputation-based node selection, Rep-FedAvg aggregation, and reputation-aware BFT consensus, achieving Byzantine resilience in decentralized FL with 72.6% accuracy on non-IID CIFAR-10 under 20% attacks.
RGNet implements renormalization-group-style hierarchical coarse-graining inside a neural network to produce multi-scale representations that improve fault prediction on the imbalanced AI4I dataset.
A survey catalogs text and speech resources for Hausa and Fongbe, documenting sizes, domains, licensing, and gaps including limited Fongbe text diversity and missing Hausa speech corpora.
Humans perform at chance levels when distinguishing generative AI content from human content in text, images, and voice.
Proposes hierarchical SDN-MEC architecture for Pods4Rail claiming lower edge controller latencies than prior literature, with defined workflows for regional policy and local failover.
citing papers explorer
-
A Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy
White-box method ReXTrust achieves highest AUC (peak 93.0) on Gut-VLM across five VLMs, outperforming alternatives by statistically significant margins while black-box and some gray-box methods collapse on certain models.
-
Jet Bundles as Higher-Order Polarised $k$-Contact Manifolds
Jet bundles with Cartan distributions are characterized as polarised N^r_π-contact manifolds of jet type via a recognition theorem in k-contact geometry.
-
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair
SmellBench is the first benchmark showing LLM agents resolve 47.7% of architectural code smells while accurately spotting false positives, but aggressive repairs often introduce new smells and degrade overall quality.
-
HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound
HARMES is the first large-scale dataset to combine wrist IMU, environmental, and audio sensors for recognizing 15 household activities across over 80 hours of data from 20 participants.
-
AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation
A sequential diffusion framework generates controllable abdominal anatomies with a Volume Control Scalar that decouples organ size from body habitus, achieving Dice scores around 0.83 and reducing distributional mismatch by 73.6% in a hepatomegaly example.
-
2-Head 2D Returning Finite Automata
Introduces 2-HRFA and B2-HRFA for picture languages, proves incomparability with CFMG, proper subset relations with RPDA and RFA, and examines closure properties.
-
KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
KG-TRACE fuses genomic features with RotatE KG embeddings via an epistemic trust gate for AMR prediction, reporting 0.976 AUROC on isoniazid resistance in the CRyPTIC cohort plus 92.5% symbolic coverage via a new Biological Grounding Ratio metric.
-
Observability for Post-Quantum TLS Readiness: A Multi-Surface Evidence Framework
A new multi-surface evidence framework for post-quantum TLS observability that combines passive, active, certificate, and registry data to assess endpoint capabilities across TLS 1.2/1.3 scenarios and outperforms prior analyzers in controlled tests and public campaigns.
-
OpenCLAW-Nexus: A Self-Reinforcing Trust Framework for Byzantine-Resilient Decentralized Federated Learning
OpenCLAW-Nexus uses a single discounted Beta-reputation model to unify reputation-based node selection, Rep-FedAvg aggregation, and reputation-aware BFT consensus, achieving Byzantine resilience in decentralized FL with 72.6% accuracy on non-IID CIFAR-10 under 20% attacks.
-
Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance
RGNet implements renormalization-group-style hierarchical coarse-graining inside a neural network to produce multi-scale representations that improve fault prediction on the imbalanced AI4I dataset.
-
A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development
A survey catalogs text and speech resources for Hausa and Fongbe, documenting sizes, domains, licensing, and gaps including limited Fongbe text diversity and missing Hausa speech corpora.
-
Is it Cake or is it AI? A Systematic Review of Human Uncertainty in Distinguishing Generative Artificial Intelligence Content
Humans perform at chance levels when distinguishing generative AI content from human content in text, images, and voice.
-
Distributed SDN-Based Communication Architecture for the Pods4Rail System
Proposes hierarchical SDN-MEC architecture for Pods4Rail claiming lower edge controller latencies than prior literature, with defined workflows for regional policy and local failover.
- Beyond Silicon: Materials, Mechanisms, and Methods for Physical Neural Computing