{"total":18,"items":[{"citing_arxiv_id":"2605.07598","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimal Recourse Summaries via Bi-Objective Decision Tree Learning","primary_cat":"cs.LG","submitted_at":"2026-05-08T11:16:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SOGAR learns Pareto-optimal recourse summaries by solving a bi-objective decision tree problem, yielding stable low-cost effective group actions that outperform prior methods on effectiveness and cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04000","ref_index":38,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mitigating False Positives in Static Memory Safety Analysis of Rust Programs via Reinforcement Learning","primary_cat":"cs.SE","submitted_at":"2026-05-05T17:21:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Reinforcement learning on MIR features combined with cargo-fuzz validation reduces false positives in Rust static memory safety analysis, raising precision from 25.6% to 59.0% and accuracy to 65.2%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02593","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gradient Boosted Risk Scores","primary_cat":"cs.LG","submitted_at":"2026-05-04T13:44:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Gradient boosting produces risk scores with competitive accuracy but 60% fewer rules on classification tasks and 16% fewer on time-to-event tasks than regression-based methods like AutoScore.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01604","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework","primary_cat":"cs.AI","submitted_at":"2026-05-02T21:02:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper presents a taxonomy of seven production-specific failure modes for agentic AI, demonstrates that existing metrics fail to detect four of them entirely, and proposes the PAEF five-dimension framework for continuous production evaluation with an open-source implementation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01153","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Toward a Unified Framework for Collaborative Design of Human-AI Interaction","primary_cat":"cs.HC","submitted_at":"2026-05-01T23:09:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A framework unifies multimodal intent interpretation, interaction-centric explainability, and agency-preserving controls as interdependent requirements for trustworthy Human-AI collaboration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00510","ref_index":92,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems","primary_cat":"cs.LG","submitted_at":"2026-05-01T08:36:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27354","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations","primary_cat":"cs.AI","submitted_at":"2026-04-30T03:12:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Cognitive models of user reasoning strategies with XAI methods on tabular data fit human forward-simulation decisions better than ML baselines and support hypothesis testing without new user studies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27017","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution","primary_cat":"eess.IV","submitted_at":"2026-04-29T12:21:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Cross-modal averaging maps ECG model attributions to CineECG 3D space, raising Dice overlap with expert annotations from 0.47 to 0.56 on 20 cases while filtering attribution noise.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25741","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Characterisation of the Clouds' young stellar Bridge using Gaia DR3","primary_cat":"astro-ph.GA","submitted_at":"2026-04-28T15:07:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A new sample of young candidate Bridge stars is identified and shown to align with gas structures, with kinematics implying a ~125 Myr crossing time consistent with the last LMC-SMC interaction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22096","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Who Audits the Auditor? Tamper-Proof Fraud Detection with Blockchain-Anchored Explainable ML","primary_cat":"cs.CR","submitted_at":"2026-04-23T22:00:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A blockchain-anchored explainable ML system delivers tamper-evident fraud detection with F1 of 0.895 and sub-25ms latency on Layer-2 networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21184","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Predicting the thermodynamics in the chromosphere from the translation of SDO data into the IRIS$^{2}$ inversion results using a visual transformer model","primary_cat":"astro-ph.SR","submitted_at":"2026-04-23T01:00:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A visual transformer model trained on IRIS inversions predicts chromospheric temperature and density from SDO data with correlations around 0.8 on 80% of test cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20934","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SDNGuardStack: An Explainable Ensemble Learning Framework for High-Accuracy Intrusion Detection in Software-Defined Networks","primary_cat":"cs.CR","submitted_at":"2026-04-22T11:52:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"SDNGuardStack ensemble learning model reports 99.98% accuracy and 0.9998 Cohen's kappa on the InSDN dataset for SDN intrusion detection while providing SHAP-based explanations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06678","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","primary_cat":"cs.LG","submitted_at":"2026-04-22T08:30:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A conditional Wasserstein GAN generates plausible future SWI drought trajectories for French insurance risk management under climate change.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20331","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Surrogate modeling for interpreting black-box LLMs in medical predictions","primary_cat":"cs.CL","submitted_at":"2026-04-22T08:26:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A surrogate modeling method approximates LLM-encoded medical knowledge via prompting to quantify variable influence and flag inaccuracies and racial biases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13462","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning from Change: Predictive Models for Incident Prevention in a Regulated IT Environment","primary_cat":"cs.SE","submitted_at":"2026-04-15T04:33:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"LightGBM with team-level features outperforms a bank's existing rule-based change risk process on a one-year dataset while using SHAP for regulatory explainability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11775","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:43:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An optimized KernelSHAP method for 3D medical image segmentation restricts computation to ROI and receptive fields, uses patch logit caching for 15-30% savings, and compares organ units versus supervoxels for clinically interpretable attributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11507","ref_index":88,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers","primary_cat":"math.OC","submitted_at":"2026-04-13T14:11:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10386","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection","primary_cat":"cs.AI","submitted_at":"2026-04-12T00:16:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TrajOnco uses a chain-of-agents LLM architecture with memory to perform temporal reasoning on longitudinal EHR, achieving 0.64-0.80 AUROC for 1-year multi-cancer risk prediction in zero-shot mode on matched cohorts while matching supervised ML on lung cancer and outperforming single-agent baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}