# Wide Learning: Learning to Reach Evidence

arXiv: https://arxiv.org/abs/2608.29608 · HTML: https://mlsanity.com/paper/2608.29608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence](https://mlsanity.com/paper/2601.03220/) (2026)
- [Adaptive Camera Sensor for Vision Models](https://mlsanity.com/paper/2503.02170/) (2025)
- [Meta-active Learning in Probabilistically-Safe Optimization](https://mlsanity.com/paper/2007.03742/) (2020)
- [In-Context Learning for Pure Exploration](https://mlsanity.com/paper/2506.01876/) (2025)
- [The Curious Language Model: Strategic Test-Time Information Acquisition](https://mlsanity.com/paper/2506.09173/) (2025)
- [Learning-To-Measure: In-Context Active Feature Acquisition](https://mlsanity.com/paper/2510.12624/) (2025)
- [To go deep or wide in learning?](https://mlsanity.com/paper/1402.5634/) (2014)
- [Learning to Acquire Information](https://mlsanity.com/paper/1704.06131/) (2017)
- [Designing Optimal Behavioral Experiments Using Machine Learning](https://mlsanity.com/paper/2305.07721/) (2023)
- [AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift](https://mlsanity.com/paper/2507.07820/) (2025)
- [Towards Wide Learning: Experiments in Healthcare](https://mlsanity.com/paper/1612.05730/) (2016)

## Abstract (arXiv)

Machine learning is usually evaluated after an evidence interface has been fixed. A dataset, sensor suite, query language, action set, or experimental protocol determines which observations can be obtained, and learning is judged by what it extracts from them. We study a complementary capability. A learner's state can determine which evidence-generating experiments it can reliably realise under bounded resources, even when primitive affordances remain fixed. We call this learner-relative experiment family its effective epistemic reach, and use Wide Learning for task-relevant learning-induced changes in that family.We formalise effective reach relative to learner state, deployment budget, reliability threshold, and evaluation distribution. In a controlled construction, two hidden worlds have exactly the same public observation law. An informative diagnostic exists in a fixed five-primitive substrate. Before calibration, one address attempt realises it with probability at most 2-10 = 1/1024, below a pre-specified 0.95 threshold; after calibration, held-out realisation is 1. Public-channel total variation is 0, whereas the realised diagnostic has total variation 1, and sealed binary risk moves from approximately 1/2 to 0. The construction establishes that learning can change effective epistemic reach even when primitive affordances and deployment resources are held fixed. It opens a complementary evaluation question for learning systems: not only what they infer from available evidence, but what informative evidence experience teaches them to bring within reach.