A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status. Leaderboards publish the model and the score, so capability and leakage stay observationally equivalent. Existing taxonomies classify contamination for automated detection, not the question a reporter faces at publication: given the mitigations already applied, which validity threats remain open? We introduce a taxonomy organized by the mitigation each type defeats -- direct, derivative, temporal, distributional, and acquired -- spanning training-time and evaluation-time leakage. Holding out a private test set closes the first alone. The fifth is acquired during the evaluation itself; because it is a property of one run, it must be recorded with the reported score rather than with the benchmark release. We operationalize it as a four-field disclosure protocol in which"unknown"is a valid entry, released under CC BY 4.0 with a JSON Schema, a validator, and worked examples. Two coders external to the design team applied a pre-registered instrument to 41 documents. Per-variable linear-weighted $\kappa$ runs from 0.00 to 0.35 (median 0.21) over 29 main-pass documents against a single-coder test-retest ceiling of 0.84, collapsing under the class skew the registration anticipated; pooling raises it to 0.46 through chance correction rather than better agreement. Two variables fall below the prevalence-robust threshold registered in advance: strata reporting and the acquired type introduced here. Disagreement concentrates on when a variable applies rather than on what a document states. Elicitation budgets are reported in 13% of documents, and no document addresses all five types. The contribution is the taxonomy, the score-side artifact that follows from it, and a pre-registered measurement of instrument reliability and current disclosure.
Johanna Angulo, Víctor Yeste, H. Espinós-Morató· 0 citations
LLMs are increasingly used as human surrogates, often on the premise that richer persona data could make them substitutes or exploratory tools for specific individuals. We test this premise across four datasets covering more than 400,000 participants and more than 6,000 survey items and experimental outcomes. LLMs perform well at the aggregate level: their average responses closely align with average human responses to the same items. But this success largely reflects predicting each item's average human response. Once each item's human mean is removed, LLM predictions explain only 3.05% of the remaining respondent-specific variation, far below the 53.6% human test-retest benchmark. Richer personas, model variants, and fine-tuning do not close this gap. In variance analyses, once item means are removed, the reliable remaining signal is person-by-item. It captures how a respondent departs from the mean on a particular item and is about 8.9x larger than the stable person effect. Persona data encode the respondent, but not this item-specific deviation. LLM responses also compress human response distributions, using less spread, fewer response categories, and distorted distributional shapes. We call this pattern item-mean surrogacy. Current LLM surrogates can approximate item averages, but not the distributions or respondent-specific deviations needed to replace individual humans. We propose four empirical tests for LLM-based human-surrogate claims.
This work analyzes four experiments on a major short-video platform, establishing a positive creator response, measuring the gross corpus flow visible within three weeks, and showing the design and duration needed to identify total value.
Yuanyuan Shen, Yiren Yan, Wenjie Li et al.· 0 citations
The results show that distributionally-regularized joint embedding architectures can be successful on challenging city-scale 3D scenes, and that transfer improves when self-supervision is designed for the capture geometry and spatial context of this domain while also revealing the limits of this specialization.
A. Rusnak, S. Kovalenko, Jingru Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
An AI-based approach called ChatNDE Figure to Caption is introduced, which aims to automate the interpretation of NDE images using deep learning and natural language processing (NLP). A Vision-and-Language Pretraining (VLP) strategy is developed to help the model learn how to connect visual features with meaningful language. Basically, we built a large NDE image dataset, trained the model using annotated examples, and then evaluated how well it performed using BLEU scores to compare its output to expert written descriptions. So, the system combines a ResNet50 model to extract important features from the images and a GPT2 language model to turn those features into natural sounding text. Even though the accuracy of the model has been low the generated caption results have been solid so far, the captions were shorter but mentioned some important features of images what human experts would say, which shows the model is learning to pick up on key details. Also, a Visual Question Answering (VQA) model is used as part of the system. VQA models are designed to take an image and a question about that image (like Is there a crack? or Where is the defect located?) and generate a useful answer. By adding this layer, the platform will not just describe what it sees, it can also respond to specific questions, making it even more interactive and helpful for inspectors in the field. This whole approach is a big step toward speeding up NDE workflows, reducing human error, and making the technology more accessible.
As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.
FiLM-GPNet is proposed, a geometry-conditioned network for wrapped-phase restoration that explicitly adapts to acquisition differences using Feature-wise Linear Modulation (FiLM) and a 7D per-pair geometry descriptor, supporting geometry-conditioned restoration as an effective alternative to fixed classical filtering across heterogeneous stacks.
Getnet Demil, Muhammad Farhan Humayun, Tomi Westerlund et al.· 0 citations
This work compares a ~28M-parameter autoregressive Tiny Recursive Model (TRM-AR) on natural-language-to-Python code generation against parameter-matched and depth-matched controls, tracking fit and generation across 40 epochs and three seeds.
This work gives the first known exploration of the connections between sparse matrix computation and spectral analysis by treating sparse matrices as two-dimensional signals and analyzing their frequency-domain representations through Fast Fourier Transform.
APPSolver is introduced, a point-wise flow-prediction framework built around Adaptive Patch Partitioning (APP), a deterministic quadtree representation for fixed two-dimensional horizontal slices extracted from ship CFD simulations, characterized as a compact spatial representation with an explicit accuracy--efficiency trade-off.
Wen-Hua Huo, Fenglei Han, Wangyuan Zhao et al.· 0 citations
This work proposes that LLM web agents can learn simple environment observations at test time, and introduces trial steps for agents to decompose a complex environment observation into sub-modules, and implements a label-free learning method, Test-Time Environment Decomposition (TTED), to adapt agent behaviors with experience during inference.
Jun-Xuan Li, Zijun Liu, Zi-Yi Huang et al.· 0 citations
The signed random Fourier features (SRFF) technique is introduced, a generalization of RFF compatible with indefinite kernels whose inverse Fourier transform is absolutely integrable and speed up KDE in the case of multivariate compact kernels, which are generally not positive definite.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
