Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper introduces PaMIR, a novel benchmark comprising 19 public credit-default datasets totaling 1.24 million instances across nine countries, designed to address the scarcity and late arrival of labels in risk prediction. Models are evaluated under a repeated i.i.d. split and a label-delayed stream, reporting AUC by label budget to simulate real-world deployment scenarios. A synthetic data harness further assesses model robustness by testing generated training rows without access to held-out data.
A single, leakage-audited recipe reconstructs 19 public credit-default datasets, offering the first comprehensive benchmark for risk prediction with scarce, late-arriving labels.
We release PaMIR (Public Arrival-ordered Measurement for Inference in Risk), an open benchmark for credit-default prediction when labels are scarce and arrive late. The field's reference benchmark studies use eight datasets each, only two or four of them public. PaMIR brings together 19 public datasets with binary default labels -- 1.24M loans, firms and card accounts from nine countries -- rebuilt from pinned source snapshots by one leakage-audited recipe and never redistributed; to our knowledge it is the one of its kind as of today. Every model is a single function, scored under a repeated i.i.d. split and a label-delayed stream in which each application is scored on arrival, with AUC reported by label budget; fleet means are withheld unless every dataset is scored. A synthetic-data harness tests generated training rows without letting a generator see held-out rows. This report describes release 0.4.0 of this living benchmark.