{"total":30,"items":[{"citing_arxiv_id":"2605.20681","ref_index":278,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis","primary_cat":"stat.ME","submitted_at":"2026-05-20T03:48:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17763","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Comparing Two Categorical Gini Correlations with Applications to Classification Problems","primary_cat":"stat.ME","submitted_at":"2026-05-18T02:29:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes an inferential framework to test differences in categorical Gini correlations for predictor importance in classification, establishing asymptotic normality and consistency while accommodating unequal dimensions and dependence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17186","ref_index":111,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Solving linear-rate ODE hierarchies (like master equations) using closures and operator splitting","primary_cat":"math.NA","submitted_at":"2026-05-16T22:46:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"For linear-rate master equations the generating function admits an exact composition-multiplier representation whose Taylor coefficients on any finite window are obtained from a closed lower-triangular ODE of size 2(N+1), independent of the truncation cap N; the same closure is combined with Strang–","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14318","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Semantic segmentation decomposes monitoring features into canonical and residual components that concentrate fault-predictive information while preserving operational meaning in predictive maintenance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13710","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Pattern-based tests for two-dimensional copulas","primary_cat":"math.ST","submitted_at":"2026-05-13T15:57:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A functional central limit theorem for pattern frequencies in 2D samples enables nonparametric goodness-of-fit, two-sample, and symmetry tests for copulas, with bootstrap critical values and parametric examples.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"As there are only two patterns of this length its test statistic𝜏can be written as a function of the number of concordant pairs, where an increase in the𝑥-values corresponds to an increase in the𝑦- values. This is the number of 12-patterns in the permutation, with 12 short for the identity permutation of size two. Longer patterns were already considered by Hoeffding [28] who showed that there is a linear pattern statistic of degree five which leads to a test that detects dependence asymptotically whenever the underlying distribution has continuous joint and marginal densities. Yanagimoto [51] proved that this consistency can already be obtained with a linear pattern statistic of degree four, and under the weaker condition that𝜇has a continuous distribution function."},{"citing_arxiv_id":"2605.10234","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Social Policy of Large Language Models: How GPT, Claude, DeepSeek and Grok Allocate Social Budgets in Spain and Germany","primary_cat":"cs.CY","submitted_at":"2026-05-11T09:10:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Four LLMs exhibit a shared implicit social policy that under-allocates pensions by a factor of three and over-allocates housing by four compared to OECD budgets, with only Claude showing meaningful response to national context.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08380","ref_index":10,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook","primary_cat":"cs.SE","submitted_at":"2026-05-08T18:38:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Empirical analysis of 4707 MoltBook posts shows AI-only technical discourse focuses on security, trust, and abstract topics while lacking concrete runtime and project details found in human GitHub discussions.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP). doi:10. 18653/v1/2024.emnlp-main.1079 [28] Henry B. Mann and Donald R. Whitney. 1947. On a Test of Whether One of Two Random Variables is Stochastically Larger than the Other.The Annals of Mathematical Statistics18 (1947). doi:10.1214/aoms/1177730491 [29] Leland McInnes, John Healy, and Steve Astels. 2017. hdbscan: Hierarchical Density Based Clustering.The Journal of Open Source Software2 (2017). doi:10. 21105/joss.00205 [30] Nuthan Munaiah, Steven Kroh, Craig Cabrey, and Meiyappan Nagappan. 2017. Curating GitHub for Engineered Software Projects.Empirical Software Engineer- ing22 (2017). doi:10.1007/s10664-017-9512-6"},{"citing_arxiv_id":"2605.08001","ref_index":258,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scale selection for geometric medians on product manifolds","primary_cat":"math.ST","submitted_at":"2026-05-08T16:57:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Joint location-scale minimization for geometric medians on product manifolds degenerates to marginal medians, and three new scale-selection methods restore identifiability with asymptotic guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06880","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Zombies in Alternate Realities: The Afterlife of Domain Names in DNS Integrations","primary_cat":"cs.CR","submitted_at":"2026-05-07T19:30:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Zombie domain linkages persist after ownership changes in DNS integrations at rates of 3% in Web PKI, 24% in ENS, and 15% in Maven Central, with validate-once designs accumulating long-term risks while per-use validation prevents them.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Our goal is to understand how linkages created in non-DNS ecosys- tems on the basis of DNS ownership can outlive that ownership, and how that can lead to abuse. 3.1 How Ecosystems Integrate DNS We useecosystemto refer to any non-DNS system that maintains its own namespace. Table 1 shows the three ecosystems we study: Web PKI [7], ENS (Ethereum Name Service) [33], and Maven Central [31]. ADNS integrationis a mechanism by which an ecosystem uses a DNS name as an identifier within its own namespace [45]. DNS names are attractive for this purpose because they are human- friendly, unlike native identifiers in some ecosystems, and because they ground new namespaces in the most widely deployed names- pace on the Internet. Each integration binds aDNS nameto an identifier in the ecosys-"},{"citing_arxiv_id":"2605.00479","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Reduced-Precision Stochastic Simulation for Mathematical Biology","primary_cat":"q-bio.QM","submitted_at":"2026-05-01T07:39:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Mixed-precision SSA with stochastic rounding preserves ensemble statistics across five biological models while cutting memory use by 2-4x and delivering up to 1.5x CPU speedup.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"two-sample Kolmogorov-Smirnov (KS) test [33, 34] assesses whether two samples are drawn from the same distribution. Here, each sample is the ensemble of per-trajectory state values at the simulation end time, and we compare the FP64 ensemble against each reduced-precision ensemble: a p-value near 1 indicates no detectable difference, while p <0.05 rejects the null hypothesis of distributional equivalence. The Wasserstein-1 distance (earth mover's distance) [35, 36] quantifies the average absolute displacement needed to transform one distribution into the other; it inherits the units of the distributions being compared (here, molecules) and is zero if and only if the distributions are identical. We additionally report sample means and variances of the steady-state distributions. 4.1 Birth-Death Process The birth-death process [1] is a minimal linear kinetics model with reactions"},{"citing_arxiv_id":"2605.00363","ref_index":213,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space","primary_cat":"math.ST","submitted_at":"2026-05-01T02:54:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23240","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"sumoITScontrol: Traffic Controller Collection for SUMO Traffic Simulations","primary_cat":"eess.SY","submitted_at":"2026-04-25T10:31:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"sumoITScontrol provides a collection of traffic controllers for SUMO simulations and stresses the importance of variance-aware evaluation methods for reproducible research.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21991","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-Task Optimization over Networks of Tasks","primary_cat":"cs.LG","submitted_at":"2026-04-23T18:18:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MONET represents tasks as graph nodes and uses neighbor-based crossover plus per-task mutation to transfer knowledge, matching or exceeding MAP-Elites performance on four large-scale simulation domains.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"and horizontal windW∈[−10,10] m/s 2; solutions (2D) are yaw and pitch in [−π/12, π/12]at fixed launch speedv 0 = 70 m/s. Arm.A planar 10-degree-of-freedom (10-DoF) arm places its end-effector at a fixed target (Figure 3b) [4,39]. Tasks (2D) vary the link lengthLand maximum joint angleα max, both in[0,1]; solutions (10D) are the 10 joint angles. Cartpole.Cart-pole balancing under varying physical parameters (Figure 3c) [8, 36].Tasks(2D)varypolemassm p ∈[0.05,0.5]kgandpolelengthL∈[0.3,1.2]m; solutions (16D) are a direct encoding of the weights of a small multi-layer per- ceptron controller (4 inputs, 2 hidden tanh units, 2 output logits, with bias units on the input and hidden layers). Hexapod.A simulated hexapod walks forward across 2000 random morphologies (Figure 3d) [14,39], simulated in PyBullet [13]."},{"citing_arxiv_id":"2604.20285","ref_index":236,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Time-dependent structural equation modeling of fans' football fever using activity tracking data during the 2025 DFB Cup final","primary_cat":"stat.AP","submitted_at":"2026-04-22T07:31:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Football fever in spectators follows a V-shaped time course captured as a latent process from heart rate and stress data via time-dependent structural equation modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17926","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Information on hidden birth events restores identifiability in phylodynamic inference","primary_cat":"q-bio.PE","submitted_at":"2026-04-20T08:06:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Hidden birth event information restores identifiability to time-dependent birth-death phylodynamic models; mutation-at-birth models make sequences sufficient to recover it.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"model is also identifiable from the joint distributionP(X, Y|θ) =P(Y|X, θ)P(X|θ). Proof.We assume two sets of parametersθandθ ′ that yield the same joint distribution ofXand Y, i.e. P(Y|X, θ)P(X|θ) =P(Y|X, θ ′)P(X|θ ′) 2 for allXandY. Integrating both sides overY, we get that P(X|θ) =P(X|θ ′) (2) for allXand thusP(Y|X, θ)P(X|θ) =P(Y|X, θ ′)P(X|θ). From this, we deduce that P(Y|X, θ) =P(Y|X, θ ′) (3) for allXandY. If the parameters are identifiable from (P(X|θ), P(Y|X, θ)), results (2)- (3) imply thatθ=θ ′. Thus, the parameters are also identifiable from the joint distribution P(X, Y|θ). 2.1 Identifiability from trees with extant sampling and hidden birth events Time-dependent birth-death models with extant sampling are defined by their birth and death"},{"citing_arxiv_id":"2604.16197","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:07:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence analysis on LLMs up to 32B parameters.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Mathematical Statistics, 18(3):309-348, 09 1947. ISSN 0003-4851. doi: 10.1214/aoms/1177730385. URLhttps://cir.nii.ac.jp/crid/1363670318640582912. 18 [50] Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533, 2022. [51] Kilian Weinberger, Anirban Dasgupta, Josh Attenberg, John Langford, and Alex Smola. Feature hashing for large scale multitask learning, 2010. URLhttps://arxiv.org/abs/0902.2206. [52] Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, and Zhangyang Wang. Llms can get \"brain rot\"!, 2025. URL https: //arxiv.org/abs/2510."},{"citing_arxiv_id":"2604.03810","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A test for normality based on self-similarity","primary_cat":"stat.ME","submitted_at":"2026-04-04T17:30:44+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The SSTN detects non-normality by tracking how the standardized empirical characteristic function changes under repeated self-similarity transformations, with the null distribution calibrated by Monte Carlo simulation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.27130","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories","primary_cat":"cs.SE","submitted_at":"2026-03-28T04:40:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.22823","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Empirical Comparison of Agent Communication Protocols for Task Orchestration","primary_cat":"cs.AI","submitted_at":"2026-03-24T05:50:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"This work provides an empirical comparison of tool integration, multi-agent delegation, and hybrid architectures for LLM task orchestration, measuring response time, context consumption, cost, error recovery, and implementation complexity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.23142","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Do Good, Stay Longer? Temporal Patterns and Predictors of Newcomer-to-Core Transitions in Conventional OSS and OSS4SG","primary_cat":"cs.SE","submitted_at":"2026-01-30T16:30:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OSS4SG projects retain contributors at 2.2X higher rates with 19.6% higher core status probability than conventional OSS, and a late-spike temporal pattern enables faster core achievement (21 weeks) than early intensive contributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.11299","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Automation and Reuse Practices in GitHub Actions Workflows: A Practitioner's Perspective","primary_cat":"cs.SE","submitted_at":"2026-01-16T13:54:54+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A survey of 419 practitioners shows strong reliance on reusable GitHub Actions for core CI/CD tasks but limited adoption of reusable workflows, with copy-pasting remaining common due to versioning and trust issues.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.01119","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Community-Based Early-Stage Chronic Kidney Disease Screening using Explainable Machine Learning for Low-Resource Settings","primary_cat":"cs.LG","submitted_at":"2026-01-03T08:43:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Machine learning models trained on Bangladeshi community data achieve 89-90% balanced accuracy for early CKD detection using few accessible features, outperforming traditional screening tools and generalizing across external datasets from India, UAE, and Bangladesh.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.23476","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sensitivity Analysis on the Sphere and a Spherical ANOVA Decomposition","primary_cat":"math.NA","submitted_at":"2025-12-29T13:59:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A parity-augmented ANOVA decomposition is established for functions on the sphere using orthogonal bases to capture geometry-induced variable dependencies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.09916","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Buoyancy-dependent induced flow by vertically migrating swimmers","primary_cat":"physics.flu-dyn","submitted_at":"2025-12-10T18:52:47+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Induced flow velocity from vertically migrating Artemia salina swarms scales with the product of swimmer number and buoyancy-driven density difference.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.08787","ref_index":52,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Exploring the Grassroots Understanding and Practices of Collective Memory Co-Contribution in a University Community","primary_cat":"cs.HC","submitted_at":"2025-12-09T16:39:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"University community members split between reflecting on past events or recording today's experiences as future history when contributing to collective memory, yielding design considerations for community platforms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.08717","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimal control of the future via prospective learning with control","primary_cat":"stat.ML","submitted_at":"2025-11-11T19:27:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Prospective Learning with Control proves ERM asymptotically achieves the Bayes optimal policy in non-stationary reset-free settings and outperforms time-aware RL on a 1D foraging benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.23205","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Network Inequality through Preferential Attachment, Triadic Closure, and Homophily","primary_cat":"physics.soc-ph","submitted_at":"2025-09-27T09:30:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PATCH model simulations show preferential attachment and homophily increase segregation and degree inequality while triadic closure reduces segregation but amplifies overall inequality, and the model accounts for observed gender disparities in 50 years of physics and CS collaboration networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.16478","ref_index":96,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Constrained Co-evolutionary Metamorphic Differential Testing for Autonomous Systems with an Interpretability Approach","primary_cat":"cs.SE","submitted_at":"2025-09-20T00:27:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CoCoMagic applies constrained cooperative co-evolution to metamorphic and differential testing to find up to 287% more distinct behavioral divergences in an end-to-end ADS than baseline search methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.16453","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Understanding the Challenges and Opportunities of Generative AI Apps: An Empirical Study","primary_cat":"cs.SE","submitted_at":"2025-06-19T16:39:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Large-scale review mining of 1M+ comments from 171 Gen-AI apps using an LLM framework reveals top topics plus three opportunities and three challenges for developers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2006.00714","ref_index":151,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bayesian inference for compact binary coalescences with BILBY: Validation and application to the first LIGO--Virgo gravitational-wave transient catalogue","primary_cat":"astro-ph.IM","submitted_at":"2020-06-01T04:46:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"BILBY is validated on simulated compact binary signals and reproduces the eleven GWTC-1 results with configuration and output files provided for reproduction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}