Skip to main content

Module scorer

Module scorer 

Source
Expand description

The shared option-scorer: ONE linear projection over anchor-token hidden states, with per-primitive readouts. This is the generalist head (P1.1) — no per-question parameters, no cross-question conditioning: each question is scored exclusively from its own anchor positions, so runtime-declared questions work zero-shot and the 255-option cardinality ceiling costs nothing in parameters.

Structs§

QuestionScore
The scored output for one question: the raw per-anchor logits plus the primitive’s distribution readout, derived on demand.
SharedScorer
One shared linear scorer over anchor-token hidden states: a single d_model → 1 projection applied to every anchor position, of every option, of every question. Trained weights live in a [nn::VarStore] so checkpoints attach to the converted backbone in P1.2 without a format boundary.

Functions§

soft_target_kl
KL divergence KL(target ‖ p) between a target distribution (the corrected teacher-average histogram in P1.4 distillation) and the scorer’s readout for one question. Distribution targets are the native input of the binned-softmax parameterization (S6b2); the target must be non-negative and sum to 1 over the question’s label arity (2 for noul: [P(false), P(true)]).