{"total":16,"items":[{"citing_arxiv_id":"2605.11328","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Epistemic Uncertainty for Test-Time Discovery","primary_cat":"cs.LG","submitted_at":"2026-05-11T23:26:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10654","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights","primary_cat":"cs.LG","submitted_at":"2026-05-11T14:38:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and drug discovery tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08448","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification","primary_cat":"cs.AI","submitted_at":"2026-05-08T20:15:40+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LG-CoTrain, an LLM-guided co-training method, outperforms classical semi-supervised baselines for crisis tweet classification in low-resource settings with 5-25 labeled examples per class.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07808","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Minimax Rate of Second-Order Calibration","primary_cat":"cs.LG","submitted_at":"2026-05-08T14:41:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"The minimax rate of estimating second-order calibration error is Õ(1/√n) with a matching Ω(1/√n) lower bound, enabled by analyticity from the sech kernel and yielding the first finite-sample guarantee for second-order Platt scaling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06413","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors","primary_cat":"stat.ML","submitted_at":"2026-05-07T15:22:35+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Decoupled PFNs use controllable synthetic priors to train separate latent-signal and noise heads, making epistemic-aleatoric decomposition identifiable and improving acquisition in noisy settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05703","ref_index":29,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems","primary_cat":"cs.MA","submitted_at":"2026-05-07T05:48:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An ensemble-based information-theoretic active learning method using ensemble Kalman inversion selects valuable tasks to optimize communication structures in LLM multi-agent systems more reliably than random sampling under limited training budgets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23099","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","primary_cat":"cs.LG","submitted_at":"2026-04-25T01:33:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ProEval is a proactive framework using pre-trained GPs, Bayesian quadrature, and superlevel set sampling to estimate performance and find failures in generative AI with 8-65x fewer samples than baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20256","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings","primary_cat":"cs.CL","submitted_at":"2026-04-22T07:05:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RADS applies reinforcement learning to pick informative samples for transfer learning, improving performance over uncertainty and diversity sampling in low-resource imbalanced clinical settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20210","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vibrotactile Preference Learning: Uncertainty-Aware Preference Learning for Personalized Vibration Feedback","primary_cat":"cs.HC","submitted_at":"2026-04-22T05:51:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VPL learns individualized vibrotactile preferences efficiently via uncertainty-aware Gaussian process models and active query selection in a 13-participant user study on an Xbox controller.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19335","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When Active Learning Falls Short: An Empirical Study on Chemical Reaction Extraction","primary_cat":"cs.LG","submitted_at":"2026-04-21T11:10:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Active learning for chemical reaction extraction frequently produces non-monotonic learning curves and fails to deliver stable gains over random sampling because of strong pretraining, structured CRF decoding, and label sparsity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15173","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Boundary-Centric Active Learning for Temporal Action Segmentation","primary_cat":"cs.CV","submitted_at":"2026-04-16T15:50:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"B-ACT improves label efficiency in temporal action segmentation by selecting only boundary frames for annotation via a two-stage uncertainty-driven process that fuses neighborhood uncertainty, class ambiguity, and temporal dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15373","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control","primary_cat":"cs.MA","submitted_at":"2026-04-15T16:07:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"InfoChess proposes a symmetric adversarial game focused purely on information control and probabilistic king-location inference, with RL agents outperforming heuristic baselines and gameplay dissected via belief entropy, cross-entropy, and predictive scores.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13899","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection","primary_cat":"cs.CL","submitted_at":"2026-04-15T14:10:58+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLM annotation can replace human labels for hostility detection with comparable F1 at much lower cost, but active learning adds little value and error structures differ systematically.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12999","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Agentic Discovery with Active Hypothesis Exploration for Visual Recognition","primary_cat":"cs.CV","submitted_at":"2026-04-14T17:34:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HypoExplore uses LLMs for hypothesis-driven evolutionary search with a Trajectory Tree and Hypothesis Memory Bank to discover lightweight vision architectures, reaching 94.11% accuracy on CIFAR-10 from an 18.91% baseline and generalizing to other datasets including state-of-the-art on MedMNIST.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08977","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Testing the Assumptions of Active Learning for Translation Tasks with Few Samples","primary_cat":"cs.CL","submitted_at":"2026-04-10T05:30:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02019","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Feature Weighting Improves Pool-Based Sequential Active Learning for Regression","primary_cat":"cs.LG","submitted_at":"2026-04-02T13:22:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Feature weighting derived from ridge regression coefficients improves sample selection in pool-based sequential active learning for both single-task and multi-task regression.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}