2786 papers
HUE-OOD is a post-hoc framework that enhances out-of-distribution detection robustness across diverse benchmarks by combining predictive, representational, and evidential uncertainty signals through a parameter-free rank-based fusion strategy, requiring no modifications to pretrained classifiers.
This paper presents a two-stage integer-programming algorithm implemented on a low-code, open-source platform that replaced manual processes for a Tel Aviv short-term rental operator, resulting in a 3.5% revenue increase and a 90% reduction in processing time by optimizing booking allocation rather than pricing.
This paper proposes a pre-deployment validity framework that evaluates network topology through Graph Structural Differentiability and Prominence Isolation to determine whether structural signals are sufficient for effective graph-based intrusion detection, revealing that high structural inequality alone does not guarantee attack-selective performance and that temporal sensitivity must be considered before committing resources.
The paper proposes GapR, a fast and effective multi-boundary ranked-list truncation method that improves multi-hop retrieval performance and downstream answer quality by identifying multiple informative score boundaries rather than relying on a single largest gap, thereby balancing evidence coverage with computational efficiency.
This paper demonstrates through factorial experiments that collective AI outcomes arise from the specific interaction regime where structural and behavioral causes are separable and context-dependent, proving that effective AI assurance cannot target agents or networks in isolation but must instead focus on the dynamic causal structure of their interactions.
This paper establishes a rigorous, leakage-safe benchmarking protocol for credit default prediction that demonstrates gradient boosting ensembles significantly outperform logistic regression and TabNet on imbalanced financial data, while revealing that post-hoc threshold tuning renders synthetic resampling redundant and highlighting the critical need to validate explanation discordance between SHAP and LIME for model risk management.
This paper proposes a methodological trust-boundary security assurance framework that models LLM-integrated and agentic systems to translate evolving semantic threats into verifiable, testable security controls and evidence-based reporting.
This paper presents an automated disease prediction and prescription system that utilizes an RNN-LSTM model to accurately translate regional Kannada medical synonyms into English, thereby outperforming existing tools like Google Translate and Whisper in context recognition to assist healthcare professionals in managing high patient volumes.
This paper characterizes the evidence quality of public software incidents for assurance-oriented benchmark construction by analyzing a 40-case dataset to reveal significant gaps in reconstructability, pairing, and source provenance, ultimately releasing the AIRR-40 registry to support more rigorous, task-relative benchmarking.
biotrace2csv is a free, open-source command-line tool that automates the extraction of heart rate variability and physiological data from BioTrace+ PDF reports into CSV format, achieving 100% accuracy with manual extraction while reducing processing time by approximately 50-fold.