{"total":20,"items":[{"citing_arxiv_id":"2607.05393","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification","primary_cat":"astro-ph.IM","submitted_at":"2026-07-06T17:59:58+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A dual-network asymmetric co-teaching framework trained on injected transients and contaminated survey data achieves human-label-free real-bogus classification with calibrated uncertainty.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25045","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Machine Learning Approaches for Improved Scalability of Metallic Magnetic Calorimeters","primary_cat":"physics.ins-det","submitted_at":"2026-06-23T18:02:25+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper demonstrates two ML pipelines — clustering-based artifact rejection and a CVAE-plus-regressor trained on simulations — that classify MMC pulses and extract energy spectra comparable to FIR filtering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23080","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Attribution Contract: Feature Attribution for Generative Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-21T22:27:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper proposes the Attribution Contract as a framework to resolve conceptual ambiguities in applying feature attribution to autoregressive and diffusion language models by explicitly specifying what is being explained.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12442","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It","primary_cat":"cs.CY","submitted_at":"2026-05-19T10:50:36+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Control is defined as setting plausible goals and reliably achieving them; on this definition, ordinary AI can already erode human control without superintelligence or takeover.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12809","ref_index":173,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:01:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05283","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:30:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A cycle-consistent GAN generates counterfactual medical images to attribute classification decisions more comprehensively than standard saliency methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03808","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","primary_cat":"cs.AI","submitted_at":"2026-05-05T14:35:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"agents. Doing this requires adapting the rich literature on human-centered interpretable machine learning [18-20], which has yielded interpretable models such as decision trees, generalized additive models, and rule lists [8]. This field has traditionally quantified interpretability in terms of concepts such as simulatability, sparsity, and modularity [21, 8, 9], ideally followed by quantitative evaluation with human experiments [22, 20]. In our setting, we replace these human experiments with tests that measure whether an LLM can accurately simulate the model's behavior in terms of predictions, feature effects, and counterfactuals solely by reading its string representation. These LLM-based tests provide a key practical advantage: they enable computing anagent interpretability scorefor any"},{"citing_arxiv_id":"2605.00018","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"What Physics do Data-Driven MoCap-to-Radar Models Learn?","primary_cat":"cs.LG","submitted_at":"2026-04-19T01:41:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Data-driven MoCap-to-radar models often fail to learn underlying physics despite low reconstruction error, with temporal attention proving critical for transformers to achieve physical consistency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.24176","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions","primary_cat":"cs.CY","submitted_at":"2026-02-27T16:58:27+00:00","verdict":"REJECT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"After nearly a decade, the legacy of the XAI program is increasingly questioned, with critics arguing that challenges have outweighed achievements. It is described as being \"in trouble\" [6], and some scholars suggest it should be \"stopped\" for high-stakes decisions [21] or has no role in the future of human-centric AI approaches [22]; others view it as myth [23] or consider it already \"dead\" [24]. A study by Hoffman[25] demonstrates that most XAIs provide shallow and inadequate explanations. Through a systematic analysis of 34 XAI systems published during 2019-2021, selected from an initial pool of 165 articles using strict criteria requiring actual machine-generated explanations, they classify \"explanations\" of AI systems into seven categories: (1) basic surface features, (2) success instances,"},{"citing_arxiv_id":"2602.09520","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rashomon Sets and Model Multiplicity in Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-02-10T08:25:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.05534","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima","primary_cat":"cs.LG","submitted_at":"2025-12-05T08:47:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A piecewise biconvex optimization framework unifies sparse dictionary learning variants, explains their pathologies via spurious optima, and enables feature anchoring to restore identifiability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.13510","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On the definition and importance of interpretability in scientific machine learning","primary_cat":"cs.LG","submitted_at":"2025-05-16T20:16:14+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Interpretability in SciML requires mechanistic understanding rather than sparsity, and prior knowledge is often essential for interpretable scientific discovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.16771","ref_index":36,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation","primary_cat":"cs.SE","submitted_at":"2025-03-21T01:00:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CodeQ aggregates token rationales into code categories to enable global interpretability of LLMs, claiming over 50% entropy reduction and revealing model preference for syntactic cues plus human misalignment in a 37-person study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.10739","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Visual Interaction with Deep Learning Models through Collaborative Semantic Inference","primary_cat":"cs.HC","submitted_at":"2019-07-24T21:37:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes the CSI framework for co-designing visual interactions and deep learning models to expose and allow semantic control over intermediate reasoning processes, shown in a summarization case study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.04105","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On the Semantic Interpretability of Artificial Intelligence Models","primary_cat":"cs.AI","submitted_at":"2019-07-09T12:01:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"This survey classifies semantic interpretability methods in AI models by nature and feature introduction, reviews user impact, and identifies remaining gaps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.04669","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Optimal Explanations of Linear Models","primary_cat":"cs.LG","submitted_at":"2019-07-08T06:59:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An optimization framework decomposes linear models into increasing-complexity sequences using coordinate updates to generate parametrized interpretability metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.03419","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Price of Interpretability","primary_cat":"cs.LG","submitted_at":"2019-07-08T06:42:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces a framework for constructing ML models via interpretable steps, generalizes standard proxies into a parametrized family of measures, and quantifies the accuracy-interpretability tradeoff via practical algorithms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.03324","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Human-Grounded Evaluation of SHAP for Alert Processing","primary_cat":"cs.LG","submitted_at":"2019-07-07T17:50:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Human-grounded evaluation finds no significant performance improvement from adding SHAP explanations to model confidence scores in alert processing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.09293","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Generating Counterfactual and Contrastive Explanations using SHAP","primary_cat":"cs.LG","submitted_at":"2019-06-21T19:13:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Model-agnostic SHAP-based pipeline for contrastive explanations and counterfactual datapoints, evaluated on IRIS, Wine Quality, and Mobile Features datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.03869","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Unexplainability and Incomprehensibility of Artificial Intelligence","primary_cat":"cs.CY","submitted_at":"2019-06-20T21:19:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}