Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This book presents a theoretical overview of recent developments at the interface between deep neural networks and causal inference (although the title mentions Artificial Intelligence, the methods discussed are exclusively neural networks). Chapters 1–4 introduce deep learning models, including variational autoencoders, generative adversarial networks and neural networks as Gaussian processes. Chapter 5 then discusses causal models, including Pearl’s do-calculus, mediation analysis, confounding, instrumental variables and how these can be integrated with neural networks. The remaining chapters discuss various topics that combine both deep neural networks and causal inference, such as reinforcement learning and counterfactual reasoning. Both deep learning and causal inference are fast-moving fields, and the author covers the latest topics and methods well. The book has a high ratio of equations to text, and even more technical material is contained in appendices at the end of each chapter. No worked examples with data are provided to illustrate how the methods should be implemented; however, at the end of each chapter links to software packages and code (primarily GitHub repositories) developed by others are provided. Although readers will gain a mathematical understanding of the latest methods, they will have to look elsewhere for examples of how to analyse and interpret the results.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it