Bibliographic record
Abstract
Rational inattention models characterize optimal decision-making in data-rich environments. In such environments, it can be costly to look carefully at all of the information. Some information is much more salient for the decision at hand and merits closer scrutiny. The inattention decision model formalizes this choice and deduces how best to navigate through the potentially vast array of data when making decisions. In the rational formulation, the decision-maker commits fully to a subjective prior distribution over the possible states of the world that could be realized. We relax this assumption and look for a robustly optimal solution to the inattention problem by allowing the decision-maker to be ambiguity averse with respect to this prior. We feature a setup that is deliberately simple by a) assuming a discrete set of choices, b) using Shannon's mutual information to quantify attention costs, and c) imposing relative entropy with respect to a baseline probability distribution to quantify prior divergence. We provide necessary and sufficient conditions for the robust solution and develop numerical methods to solve it. In comparison to the rational solution with no prior uncertainty, our decision-maker slants priors in more cautious or pessimistic directions when deducing how to allocate attention over the range of available information. This approach implements a form of robustness to prior misspecification, or equivalently, a form of ambiguity aversion. We explore some examples that show how the robust solution differs from the rational solution with a commitment to a subjective prior distribution and how it differs from imposing risk aversion.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.038 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".