Files
Open_Ultra_SAST/src/openultrasast/learn/compile.toml
T

45 lines
1.9 KiB
TOML
Raw Normal View History

# The pre-registered compile specification of the decision engine's program (learned-decision-engine design 4.3).
# Committed before any compile runs: the metric, the seeds, the search space and the budget are fixed here, and the
# compiled artifact records this file's sha256. Changing anything below after looking at a result is a new spec.
version = 1
seed = 0
[metric]
name = "balanced_brier_v1" # Brier score of the raw score s on C_val, each (family, label) cell weighted equally
repository_cap = 5 # each repository counts at most 5 effective rows per cell
unsure_score = 0.5 # unsure and parse_failed answers score as s = 0.5
tie_tolerance = 0.005 # within this, fewer prompt tokens wins, then the earlier configuration
secondary = ["recall_at_precision_0.90", "unsure_share"] # reported, never optimised
[split]
compile_fraction = 0.25 # of the repository groups, per primary family; never an evaluation fold
boot_fraction = 0.6 # C_boot (demonstrations) vs C_val (scoring)
retrieval = "compile_only" # during the compile, memory is the compile split only: no evaluated group shapes it
[bootstrap]
max_candidates = 150
min_confidence = 0.7
demo_sets = 4
demos_per_set = 3 # one positive, one negative, one of either; families mixed
[search]
proposals = 6 # instructions proposed in one call, scored with the hand-written baseline (7)
errors_shown = 20 # summarised bootstrap errors in the proposal prompt (signals and verdicts, no code)
val_candidates = 60
[classify]
model = "deepseek-flash"
k = 1 # k and lam are A/B variants (design section 6), not searched here
max_output_tokens = 300
[retrieval]
n1 = 40
k = 6
lam = 0.5
near_duplicate_cos = 0.98
priors = "off"
[budget]
usd = 3.0 # a compile that reaches it is `unfinished` and writes no artifact
calls = 1200