{"total":37,"items":[{"citing_arxiv_id":"2605.23191","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation","primary_cat":"cs.LG","submitted_at":"2026-05-22T03:17:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RankElastor mitigates embedding collapse via spectrum-robust token mixing and GLU-based P-FFNs, yielding better performance and scaling on industrial recommendation datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22977","ref_index":146,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Absorbing Many-Body Correlations into Core-Optimized Orbitals","primary_cat":"quant-ph","submitted_at":"2026-05-21T19:15:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"COO co-optimizes orbitals with TrimCI to absorb many-body correlations into the basis, cutting determinant count by orders of magnitude for iron-sulfur clusters versus localized bases or DMRG.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20025","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration","primary_cat":"cs.AI","submitted_at":"2026-05-19T15:49:51+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19807","ref_index":145,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Reliable model selection in the presence of parameter non-identifiability","primary_cat":"stat.ME","submitted_at":"2026-05-19T13:06:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes adaptive multiple importance sampling for robust Bayesian model evidence estimation under parameter non-identifiability, shown to outperform deterministic methods on ecological case studies while being cheaper than MCMC.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18206","ref_index":95,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A tool to determine the degrees of freedom in tree-structured varying coefficient models","primary_cat":"stat.ME","submitted_at":"2026-05-18T10:45:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A formula approximating degrees of freedom for tree-structured varying coefficient models is proposed to improve BIC model selection over naive parameter counting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17554","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","primary_cat":"cs.AI","submitted_at":"2026-05-17T17:32:52+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15920","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unsupervised Domain Shift Detection with Interpretable Subspace Attribution","primary_cat":"stat.ML","submitted_at":"2026-05-15T12:58:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An unsupervised method detects domain shifts via localized density anomaly search in feature space, attributes the shift to a minimal subspace, and extracts balanced subsets from two unlabeled datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12089","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Power Studies For Two-Sample and Goodness-of-Fit Methods For Multivariate Data","primary_cat":"stat.ME","submitted_at":"2026-05-12T13:10:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"No single goodness-of-fit or two-sample test reliably detects deviations across all multivariate scenarios, so the authors recommend a small combination of methods that together cover the simulated cases.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09228","ref_index":108,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ProactBench: Beyond What The User Asked For","primary_cat":"cs.LG","submitted_at":"2026-05-09T23:56:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ProactBench measures LLM conversational proactivity in three phases using 198 multi-agent dialogues and finds recovery behavior hard to predict from existing benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10965","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Constraining Dark Energy Dynamics in Curved Spacetime with Current Observations","primary_cat":"physics.gen-ph","submitted_at":"2026-05-08T10:57:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Observational constraints on a dark energy EoS parametrization in curved spacetime yield α ≈ 0.35 (0.56) and Ω_k0 that changes sign with ANN data reconstruction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08251","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The finite-shot help-harm boundary of zero-noise extrapolation","primary_cat":"quant-ph","submitted_at":"2026-05-07T17:01:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Zero-noise extrapolation has a finite-shot help-harm boundary below which it increases local mean-squared error due to variance penalties outweighing bias reduction.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"ZNE estimates,∆ MSE, crossings,bq,bsobs, andbCfit. 9 Empirical validation with Qiskit Aer and IBM hardware The empirical component tests whether the help-harm boundary exponent separates by observ- able variance class under a reproducible Qiskit Aer pipeline using Qiskit [36], Mitiq-compatible folding conventions [37], and a raw-count bootstrap workflow [38, 39]. Aer provides the cen- tral exponent evidence becauseϵ, budgets, interpolation, and resampling are controlled; IBM Quantum runs provide traceable hardware consistency checks, not asymptotic exponent fits. 13 Table 3: Assumption checks for empirical tests. The first two rows are theorem-validating regimes; the remaining rows are robustness or limitation regimes."},{"citing_arxiv_id":"2605.06742","ref_index":83,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bayesian Modeling and Prediction of Generalized Contact Matrices","primary_cat":"stat.ME","submitted_at":"2026-05-07T14:30:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A Bayesian model for multi-feature contact matrices that uses tensor structures and contingency table theory to satisfy structural constraints and impute missing contact features, validated on simulations and US/German survey data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03326","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sequential Bayesian Monitoring for Recoverable and Drifting Processes","primary_cat":"stat.CO","submitted_at":"2026-05-05T03:33:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bayesian procedures are derived to compute the posterior probability that a recoverable process is currently in control or that a drifting latent parameter lies in an acceptable region.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01775","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Semi-Supervised Kernel Two-Sample Test","primary_cat":"stat.ML","submitted_at":"2026-05-03T08:26:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23478","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems","primary_cat":"cs.CL","submitted_at":"2026-04-26T00:08:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"JudgeSense benchmark shows LLM judge consistency does not reliably improve with model scale, with coherence most sensitive to prompt changes and factuality more stable.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18653","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How to quantify direct correlations between variables","primary_cat":"stat.ME","submitted_at":"2026-04-20T06:15:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Jensen-Shannon regularized analogues of KL-based direct-correlation measures are introduced, taking values in [0,1] and accompanied by alphabet-size-dependent upper bounds under the observed marginal p(x,z).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17698","ref_index":116,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability","primary_cat":"cs.LG","submitted_at":"2026-04-20T01:24:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14414","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Autocorrelation Blind Spot: Why 42% of Turn-Level Findings in LLM Conversation Analysis May Be Spurious","primary_cat":"cs.CL","submitted_at":"2026-04-15T20:54:39+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"42% of significant turn-level associations in LLM conversation analysis are spurious due to unaccounted autocorrelation, with a validated two-stage correction framework improving replication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12155","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Spatially Resolved Kinematics of SLACS Lens Galaxies. II: Breaking Degeneracies with Lensing and Dynamical Models","primary_cat":"astro-ph.GA","submitted_at":"2026-04-14T00:12:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Spatially resolved kinematics show SLACS lens galaxies have nearly isothermal total mass profiles (mean γ=2.04) with average mass-sheet parameter λ_int=1.01, consistent with no measurable bias from power-law assumptions in cosmography.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"PA and is now consistent with the oblate case. 8Knabel et al. All our baseline models explicitly include the MST parameter, i.e.𝜆 int is not fixed to 1. We performed tests with𝜆int =1 for the sake of comparison; unless otherwised stated, all models we discuss have freely fitted𝜆 int. In order to quantify model preference, we compare Bayesian information criteria (BIC) as defined in (G. Schwarz 1978): BIC=𝑘ln(𝑁) −2 ln ˆ𝐿\u0001, where𝑘is the number of free fit parameters,𝑁is the number of fitted data points, and −2 ln ˆ𝐿\u0001 =𝜒 2 best is the log-likelihood or𝜒 2 of the best fit- ting parameters as in Equation 4. We calculate the error on BIC𝜎 BIC from the sample𝜒 2 distribution. Given a dataset, a model with a lower BIC is considered to be a better fit"},{"citing_arxiv_id":"2604.11929","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fast and principled equation discovery from chaos to climate","primary_cat":"cs.LG","submitted_at":"2026-04-13T18:17:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Multiple candidate models are then generated by sweeping a sequence of thresholds over the resulting coefficients, retain- ing only terms whose magnitudes exceed each threshold. In the second stage, each candidate model is refitted by OLS regression to obtain unbiased coefficient estimates, and the optimal model is selected by minimizing the Bayesian Information Criterion (BIC) [27]. The two passes differ in their choice of adaptive weights: the first pass uses ridge-derived weights [28] to ensure robustness to multicollinearity, whereas the sec- ond uses OLS-derived weights to achieve asymptotic unbiasedness. Between passes, the design matrix is refined to include all functional terms up to the highest order of any variable with a nonzero coefficient identified in the first pass, thereby mitigating"},{"citing_arxiv_id":"2604.04849","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Latent Profiles of AI Risk Perception and Their Differential Association with Community Driving Safety Concerns: A Person-Centered Analysis","primary_cat":"cs.CY","submitted_at":"2026-04-06T16:50:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Four latent profiles of AI risk perception were identified in U.S. adults, with higher AI concern generally linked to greater perceived driving-hazard severity except for AI-versus-human driving comparisons.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"9%, and four substantively interpretable profiles. This solution was retained for all subsequent analyses. 4.3. Class Profiles and Interpretation Figure3displaystheitem-responseprobabilityprofilesforthefour-classsolution.Theweightedclassprevalences with 95% bootstrap confidence intervals are as follows: Class 1 (Moderate Skeptics), 17.5% [16.3, 18.7]; Class 2 (ConcernedPragmatists),42.8%[41.2,44.2];Class3(AIAmbivalent),10.6%[9.6,11.6];andClass4(ExtremeAlarm), 29.1% [27.8, 30.5]. Class1(ModerateSkeptics)ischaracterizedbymodal\"somewhatconcerned\"responsesacrossallsixAIconcern items,withitem-responseprobabilitiesforthiscategoryrangingfrom0.538to0.762.Membersofthisclassareroughly evenly divided between distrusting and being unsure about AI (probabilities of 0."},{"citing_arxiv_id":"2603.29184","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Cell-induced densification and tether formation in fibrous extracellular matrices with biomimetic physics-informed neural networks","primary_cat":"cs.LG","submitted_at":"2026-03-31T02:50:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bio-PINNs with a near-to-far curriculum and deformation-uncertainty proxy recover cell-induced densified phases and tether morphologies more reliably than standard adaptive PINN baselines in single-cell and multicellular settings.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":": Micro-structure in linear elasticity. Archive for Rational Mechanics and Analysis16, 51-78 (1964) https://doi.org/10.1007/BF00248490 [36] Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordi- nary and partial differential equations. IEEE Transactions on Neural Networks 9(5), 987-1000 (1998) https://doi.org/10.1109/72.712178 [37] Efron, B.: Bootstrap methods: Another look at the jackknife. The Annals of Statistics7(1), 1-26 (1979) https://doi.org/10.1214/aos/1176344552 [38] Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol."},{"citing_arxiv_id":"2512.03760","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A decay-adjusted spatio-temporal model to account for the impact of mass drug administration on neglected tropical disease prevalence","primary_cat":"stat.AP","submitted_at":"2025-12-03T13:06:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new decay-adjusted spatio-temporal model improves estimation of neglected tropical disease prevalence by explicitly accounting for the waning impact of mass drug administration in sparse survey data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.01929","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Nested Sampling for ARIMA Model Selection in Astronomical Time-Series Analysis","primary_cat":"astro-ph.IM","submitted_at":"2025-12-01T17:45:00+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.20183","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-fidelity Gaussian process regression for noisy outputs and non-nested experimental designs: a comparison between the recursive and non-recursive formulations","primary_cat":"stat.AP","submitted_at":"2025-11-25T11:06:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Recursive multi-fidelity GP regression with EM optimization trains faster than the coupled non-recursive Kennedy-O'Hagan approach on noisy non-nested data while delivering comparable predictions and uncertainty estimates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.04346","ref_index":48,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Environment-Aware Indoor LoRaWAN Path Loss: Parametric Regression Comparisons, Shadow Fading, and Calibrated Fade Margins","primary_cat":"cs.NI","submitted_at":"2025-10-05T20:14:48+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Environment-conditioned parametric regression on 12-month indoor LoRaWAN data reduces cross-validated RMSE from 8.23 dB to 7.38 dB and lowers the fade margin needed for 99% reliability from ~28 dB to 25.73 dB.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.17428","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-09-22T07:21:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QWHA proposes Walsh-Hadamard Transform adapters with adaptive initialization for quantization-aware PEFT, claiming better low-bit accuracy and faster training than low-rank or other FT-based baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.18488","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"INLA-RF: A Hybrid Modeling Strategy for Spatio-Temporal Environmental Data","primary_cat":"stat.ME","submitted_at":"2025-07-24T15:01:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A hybrid INLA-RF framework integrates Bayesian spatio-temporal modeling with random forests through two iterative algorithms to improve predictions and uncertainty quantification for environmental data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.13920","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem","primary_cat":"cs.LG","submitted_at":"2025-07-18T13:50:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Causal Process Models reframe dynamic causal graph discovery as multi-agent reinforcement learning to build sparse time-varying graphs only at active interactions, outperforming dense baselines on physical prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.13742","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Understanding Task Representations in Neural Networks via Bayesian Ablation","primary_cat":"cs.LG","submitted_at":"2025-05-19T21:36:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A Bayesian ablation framework combined with information-theoretic metrics is introduced to analyze causal roles, distributedness, manifold complexity, and polysemanticity of task representations in neural networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.17773","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","primary_cat":"stat.ME","submitted_at":"2025-02-25T02:07:29+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2401.18059","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:30:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Should a local cluster's combined context ever exceed the summarization model's token threshold, our algorithm recursively applies clustering within the cluster, ensuring that the context remains within the token threshold. To determine the optimal number of clusters, we employ the Bayesian Information Criterion (BIC) for model selection. BIC not only penalizes model complexity but also rewards goodness of fit (Schwarz, 1978). The BIC for a given GMM is BIC = ln(N )k − 2 ln(ˆL), where N is the number of text segments (or data points), k is the number of model parameters, and ˆL is the maximized value of the likelihood function of the model. In the context of GMM, the number of parameters k is a function of the dimensionality of the input vectors and the number of clusters."},{"citing_arxiv_id":"2306.10430","ref_index":49,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Variational Sequential Optimal Experimental Design using Reinforcement Learning","primary_cat":"stat.ML","submitted_at":"2023-06-17T21:47:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"vsOED uses a variational one-point reward and RL policy optimization to provide a lower bound on expected information gain for sequential experimental design, supporting nuisance parameters, implicit likelihoods, and multiple design goals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.07810","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Stability selection enables robust learning of partial differential equations from limited noisy data","primary_cat":"math.NA","submitted_at":"2019-07-17T23:35:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PDE-STRIDE applies stability-based model selection to sparse regression for robust, parameter-free recovery of PDEs from noisy data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.05381","ref_index":5,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adaptive Pricing in Insurance: Generalized Linear Models and Gaussian Process Regression Approaches","primary_cat":"econ.EM","submitted_at":"2019-07-02T08:18:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Adaptive GLM with MQLE and GP regression with UCB for dynamic insurance pricing, showing parameter convergence and regret analysis under delayed claims.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.09793","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Commensal discovery of four Fast Radio Bursts during Parkes Pulsar Timing Array observations","primary_cat":"astro-ph.HE","submitted_at":"2019-06-24T09:07:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Four new FRBs discovered commensally during Parkes PTA pulsar observations, including one with record S/N and unusual spectrum; all highly polarized.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1904.02180","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences","primary_cat":"astro-ph.IM","submitted_at":"2019-04-03T18:04:57+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"dynesty is an open-source Python package for dynamic nested sampling that improves efficiency in Bayesian posterior and evidence estimation compared to MCMC on certain problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}