A representation property is identifiable from the induced predictor iff it is constant on the fibers of the map from admissible (representation, head) pairs to the composite predictor.
B \" u hlmann, P
9 Pith papers cite this work, alongside 64 external citations. Polarity classification is still indexing.
9
Pith papers citing it
64
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Indirect elicitation via triplet comparisons recovers meaningful association structures from LLMs and supports conservative causal candidate links across prompted subpopulations.
A 1825 storm created a new sea connection in Denmark, producing a 27 percent population increase (elasticity 1.6 to market access) driven by fertility and occupational change toward fishing and manufacturing, with symmetric medieval declines after waterway closure.
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
ECR-Net is a framework that discovers and adapts causal structures in non-stationary data by evolving gene-regulatory-network-like graphs via fitness-optimized search.
CauSim turns scarce causal reasoning labels into scalable supervised data by having LLMs incrementally construct complex executable structural causal models.
POSCMs extend SCMs to settings where the causal graph itself is generated by latent context and can be intervened on, with conditional kernel-identifiability theorems and illustrative retina simulations.
Proposes framing auditing of deployed AI systems as continuous statistical monitoring of risk-controlled constraints like fairness and safety under uncertainty.
LLMs support decision prediction and rationale generation but lack evidence for genuine decision explanation, requiring stricter standards to avoid over-crediting.
citing papers explorer
-
A Fiber Criterion for Representation Identifiability in Supervised Learning
A representation property is identifiable from the induced predictor iff it is constant on the fibers of the map from admissible (representation, head) pairs to the composite predictor.
-
Eliciting associations between clinical variables from LLMs via comparison questions across populations
Indirect elicitation via triplet comparisons recovers meaningful association structures from LLMs and supports conservative causal candidate links across prompted subpopulations.
-
A Perfect Storm: First-Nature Geography and Economic Development
A 1825 storm created a new sea connection in Denmark, producing a 27 percent population increase (elasticity 1.6 to market access) driven by fertility and occupational change toward fishing and manufacturing, with symmetric medieval declines after waterway closure.
-
Anchor PCA
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
-
Evolving Causal Regulatory Networks (ECR-Net)
ECR-Net is a framework that discovers and adapts causal structures in non-stationary data by evolving gene-regulatory-network-like graphs via fitness-optimized search.
-
CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
CauSim turns scarce causal reasoning labels into scalable supervised data by having LLMs incrementally construct complex executable structural causal models.
-
Partially Observed Structural Causal Models
POSCMs extend SCMs to settings where the causal graph itself is generated by latent context and can be intervened on, with conditional kernel-identifiability theorems and illustrative retina simulations.
-
Towards Auditing AI Systems in the Wild
Proposes framing auditing of deployed AI systems as continuous statistical monitoring of risk-controlled constraints like fairness and safety under uncertainty.
-
LLMs Should Not Yet Be Credited with Decision Explanation
LLMs support decision prediction and rationale generation but lack evidence for genuine decision explanation, requiring stricter standards to avoid over-crediting.