The Large Space of Information Structures
Bibliographic record
Abstract
We revisit the question of modeling incomplete information among 2 Bayesian\nplayers, following an ex-ante approach based on values of zero-sum games. $K$\nbeing the finite set of possible parameters, an information structure is\ndefined as a probability distribution $u$ with finite support over $K\\times\n\\mathbb{N} \\times \\mathbb{N}$ with the interpretation that: $u$ is publicly\nknown by the players, $(k,c,d)$ is selected according to $u$, then $c$ (resp.\n$d$) is announced to player 1 (resp. player 2). Given a payoff structure $g$,\ncomposed of matrix games indexed by the state, the value of the incomplete\ninformation game defined by $u$ and $g$ is denoted $\\mathrm{val}(u,g)$. We\nevaluate the pseudo-distance $d(u,v)$ between 2 information structures $u$ and\n$v$ by the supremum of $|\\mathrm{val}(u,g)-\\mathrm{val}(v,g)|$ for all $g$ with\npayoffs in $[-1,1]$, and study the metric space $Z^*$ of equivalent information\nstructures.\n We first provide a tractable characterization of $d(u,v)$, as the minimal\ndistance between 2 polytopes, and recover the characterization of Peski (2008)\nfor $u \\succeq v$, generalizing to 2 players Blackwell's comparison of\nexperiments via garblings. We then show that $Z^*$, endowed with a weak\ndistance $d_W$, is homeomorphic to the set of consistent probabilities with\nfinite support over the universal belief space of Mertens and Zamir. Finally we\nshow the existence of a sequence of information structures, where players\nacquire more and more information, and of $\\varepsilon>0$ such that any two\nelements of the sequence have distance at least $\\varepsilon$: having more and\nmore information may lead now here. As a consequence, the completion of\n$(Z^*,d)$ is not compact, hence not homeomorphic to the set of consistent\nprobabilities over the states of the world {\\it \\`a la} Mertens and Zamir. This\nexample answers by the negative the second (and last unsolved) of the three\nproblems posed by J.F. Mertens in his paper ``Repeated Games", ICM 1986.\n
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 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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.002 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".