What Do Learned Models Measure?

• URL: http://arxiv.org/abs/2601.18278v1
• Date: Mon, 26 Jan 2026 09:00:48 GMT
• Title: What Do Learned Models Measure?
• Authors: Indrė Žliobaitė,
• Abstract summary: In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments.<n>We show that standard evaluation criteria in machine learning, including generalization error, calibration, and robustness, do not guarantee measurement stability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the mapping from observations to quantities is determined implicitly by the training distribution and inductive biases, allowing multiple inequivalent mappings to satisfy standard predictive evaluation criteria. We formalize learned measurement functions as a distinct focus of evaluation and introduce measurement stability, a property capturing invariance of the measured quantity across admissible realizations of the learning process and across contexts. We show that standard evaluation criteria in machine learning, including generalization error, calibration, and robustness, do not guarantee measurement stability. Through a real-world case study, we show that models with comparable predictive performance can implement systematically inequivalent measurement functions, with distribution shift providing a concrete illustration of this failure. Taken together, our results highlight a limitation of existing evaluation frameworks in settings where learned model outputs are identified as measurements, motivating the need for an additional evaluative dimension.

Related papers

• Position: All Current Generative Fidelity and Diversity Metrics are Flawed [58.815519650465774]
  We show that all current generative fidelity and diversity metrics are flawed.<n>Our aim is to convince the research community to spend more effort in developing metrics, instead of models.
  arXiv  Detail & Related papers  (2025-05-28T15:10:33Z)
• A comprehensive review of classifier probability calibration metrics [0.0]
  Probabilities or confidence values produced by AI andML models often do not reflect their true accuracy.<n>Probabilities calibration metrics measure the discrepancy between confidence and accuracy.
  arXiv  Detail & Related papers  (2025-04-25T11:44:44Z)
• Developing a Dataset-Adaptive, Normalized Metric for Machine Learning Model Assessment: Integrating Size, Complexity, and Class Imbalance [0.0]
  Traditional metrics like accuracy, F1-score, and precision are frequently used to evaluate machine learning models.<n>A dataset-adaptive, normalized metric that incorporates dataset characteristics like size, feature dimensionality, class imbalance, and signal-to-noise ratio is presented.
  arXiv  Detail & Related papers  (2024-12-10T07:10:00Z)
• Robustness investigation of cross-validation based quality measures for model assessment [0.0]
  The prediction quality of a machine learning model is evaluated based on a cross-validation approach. The presented measures quantify the amount of explained variation in the model prediction.
  arXiv  Detail & Related papers  (2024-08-08T11:51:34Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)
• Rigorous Assessment of Model Inference Accuracy using Language Cardinality [5.584832154027001]
  We develop a systematic approach that minimizes bias and uncertainty in model accuracy assessment by replacing statistical estimation with deterministic accuracy measures. We experimentally demonstrate the consistency and applicability of our approach by assessing the accuracy of models inferred by state-of-the-art inference tools.
  arXiv  Detail & Related papers  (2022-11-29T21:03:26Z)
• Calibration tests beyond classification [30.616624345970973]
  Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible targets. Calibrated models guarantee that the predictions are neither over- nor under-confident.
  arXiv  Detail & Related papers  (2022-10-21T09:49:57Z)
• Post-hoc Models for Performance Estimation of Machine Learning Inference [22.977047604404884]
  Estimating how well a machine learning model performs during inference is critical in a variety of scenarios. We systematically generalize performance estimation to a diverse set of metrics and scenarios. We find that proposed post-hoc models consistently outperform the standard confidence baselines.
  arXiv  Detail & Related papers  (2021-10-06T02:20:37Z)
• How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models [95.8037674226622]
  We introduce a 3-dimensional evaluation metric that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity.
  arXiv  Detail & Related papers  (2021-02-17T18:25:30Z)
• Performance metrics for intervention-triggering prediction models do not reflect an expected reduction in outcomes from using the model [71.9860741092209]
  Clinical researchers often select among and evaluate risk prediction models. Standard metrics calculated from retrospective data are only related to model utility under certain assumptions. When predictions are delivered repeatedly throughout time, the relationship between standard metrics and utility is further complicated.
  arXiv  Detail & Related papers  (2020-06-02T16:26:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.