Commit History
round-7 follow-through: disjoint_256 arm (scripts/evaluate_frozen_benchmarks.py) 8dbb6c6 verified
round-7: morgan_2048_rp parity arm (scripts/evaluate_frozen_benchmarks.py) 34f4fdb verified
review-response: upload scripts/evaluate_frozen_benchmarks.py 7ea9f42 verified
feat: evaluators support pom_alltags arm (objective_dim-aware, prospective N/A for 575-dim) 224d843
Matthew Ford commited on
feat: preregistered frozen-benchmark evaluator (substitution triplets + prospective) e6555ec
Matthew Ford commited on