{"total":15,"items":[{"citing_arxiv_id":"2606.30961","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table","primary_cat":"physics.chem-ph","submitted_at":"2026-06-29T22:38:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ElemeNet is a unified ML software package for molecular property prediction across elements 1-100 with built-in uncertainty quantification and competitive benchmarks on diverse chemistry datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29237","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments","primary_cat":"cs.RO","submitted_at":"2026-06-28T06:51:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoPe propagates historical dynamic posteriors via SE(3) warping and bounded Bayesian fusion to maintain persistent motion state in monocular Gaussian SLAM.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17312","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty","primary_cat":"cs.AI","submitted_at":"2026-06-15T21:39:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Structural uncertainty from self-preference-induced rankings of LLM reasoning paths complements answer dispersion for identifying unreliable instances on logical tasks while collapsing on factual retrieval.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13172","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance","primary_cat":"cs.LG","submitted_at":"2026-06-11T10:42:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Proposes the VER framework as a diagnostic sequence for identifying explanatory insufficiency in learned representations, distinguishing it from standard errors and shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11870","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Modelling magnetic material properties with uncertainty-aware neural networks","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-10T09:47:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Uncertainty-aware neural networks using Gaussian negative log-likelihood and dropout are applied to predict intrinsic magnetic properties and coercivity via graph neural networks in permanent magnet research.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09881","ref_index":289,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03460","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From 3D Perception to Safety Reasoning: A Graph-Based Framework for Real-Time Underground Mine Monitoring","primary_cat":"cs.CV","submitted_at":"2026-06-02T10:37:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A graph-structured framework fuses 3D perception with rule-based, LLM, and memory reasoning to raise hazard coverage from 57% to 93% across 115 simulated underground mine scenarios.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02632","ref_index":51,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery","primary_cat":"stat.ML","submitted_at":"2026-05-30T15:21:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Mechanistic learning from ML is generically underdetermined in high-dimensional proxy regimes, with LLMs worsening the problem by collapsing many possible explanations into one fluent narrative.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20255","ref_index":21,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:02:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed differentials.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14308","ref_index":102,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reconstructing the Stripping History of the Sagittarius Stream with Neural Networks","primary_cat":"astro-ph.GA","submitted_at":"2026-05-14T03:21:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A neural network trained on simulations infers stripping times for Sagittarius stream stars from phase-space data, measuring a 0.3 dex/Gyr metallicity gradient and estimating ages for globular clusters such as Pal 12 and NGC 2419.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10378","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation","primary_cat":"stat.ML","submitted_at":"2026-05-11T11:21:49+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"MU is supported by the European Research Council under the European Union's Horizon 2020 research and innovation Programme (PBSP , Grant agreement n.950246) and partially supported by the STFC consolidated grant ST/X000664/1. 33 SciPost Physics Community Reports Submission References [1]F . James,Statistical Methods in Experimental Physics. World Scientific, 2nd ed., 2006. [2]R. Trotta,Bayes in the sky: Bayesian inference and model selection in cosmology, Contemp. Phys.49(2008) 71, arXiv:0803.4089[astro-ph]. [3]D. W . Hogg, J. Bovy , and D. Lang,Data analysis recipes: Fitting a model to data, arXiv:1008.4686[astro-ph.IM]. [4]G. Cowan, K. Cranmer, E. Gross, and O. Vitells,Asymptotic formulae for likelihood-based tests of new physics, Eur."},{"citing_arxiv_id":"2604.26491","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning","primary_cat":"astro-ph.GA","submitted_at":"2026-04-29T09:55:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TwinSpecNet uses empirical paired learning on spectral twins to denoise low-S/N APOGEE spectra and predict stellar parameters and abundances with lower scatter than the standard pipeline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.27098","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Ensemble-Based Uncertainty Estimation for Code Correctness Estimation","primary_cat":"cs.SE","submitted_at":"2026-03-28T02:37:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Ensemble Semantic Entropy improves correlation with code correctness over single-model methods and powers a cascading scaling system that cuts FLOPs by 64.9% while preserving performance on LiveCodeBench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.02345","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","primary_cat":"cs.LG","submitted_at":"2025-02-04T14:27:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2412.02818","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","primary_cat":"cs.RO","submitted_at":"2024-12-03T20:34:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}