pino-source-code / scripts /evaluate_frozen_benchmarks.py

Commit History

round-10: physics-factorial + direct-2048 chain (scripts/evaluate_frozen_benchmarks.py)
63f6c7c
verified

mattbitzesty commited on

round-7 follow-through: disjoint_256 arm (scripts/evaluate_frozen_benchmarks.py)
8dbb6c6
verified

mattbitzesty commited on

round-7: morgan_2048_rp parity arm (scripts/evaluate_frozen_benchmarks.py)
34f4fdb
verified

mattbitzesty commited on

review-response: upload scripts/evaluate_frozen_benchmarks.py
7ea9f42
verified

mattbitzesty commited on

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