Design

This experiment tests the next falsifier from the draft empirical sketch proof:
whether the plain EGGROLL and decomposed EGGROLL LLM paths still behave
reasonably once answer-token likelihood is replaced by sampled-answer scalar
reward.

There is still no solid theory note for the project, so this should be read as
an empirical gate, not as a settled-theory test. The falsifying outcome for the
current draft claim would be a clear plain-EGGROLL win under matched reward
budget. A flat reward result would mostly say that this first exact-answer
benchmark is too sparse.

Results

20260801-113246-pretrained_llm_exact_reward_smoke_jean_zay-6224172

commit: 6224172

metricvalue
both_success_rate0.3333333333333333
decomposed_mean_accuracy_improvement0.015625
decomposed_mean_best_accuracy0.4322916666666667
decomposed_mean_final_accuracy0.4114583333333333
decomposed_mean_final_parseable_rate0.9791666666666666
decomposed_mean_finite_epoch_fraction1
decomposed_mean_parseable_rate_improvement0.0625
decomposed_mean_shaped_epoch_fraction0
decomposed_median_final_accuracy0.40625
decomposed_success_rate0.3333333333333333
decomposed_win_rate0.16666666666666666
eggroll_mean_accuracy_improvement0.010416666666666666
eggroll_mean_best_accuracy0.4479166666666667
eggroll_mean_final_accuracy0.40625
eggroll_mean_final_parseable_rate0.9791666666666666
eggroll_mean_finite_epoch_fraction1
eggroll_mean_parseable_rate_improvement0.0625
eggroll_mean_shaped_epoch_fraction0
eggroll_median_final_accuracy0.40625
eggroll_success_rate0.3333333333333333
epochs8
eval_samples32
mean_accuracy_gap_decomposed_minus_eggroll0.005208333333333333
mean_improvement_gap_decomposed_minus_eggroll0.005208333333333333
mean_parseable_gap_decomposed_minus_eggroll0
num_pairs6
num_ranks2
num_seeds3
num_target_modules7
population16
rank_1_decomposed_success_rate0.3333333333333333
rank_1_decomposed_win_rate0
rank_1_eggroll_success_rate0.3333333333333333
rank_1_mean_accuracy_gap_decomposed_minus_eggroll0
rank_2_decomposed_success_rate0.3333333333333333
rank_2_decomposed_win_rate0.3333333333333333
rank_2_eggroll_success_rate0.3333333333333333
rank_2_mean_accuracy_gap_decomposed_minus_eggroll0.010416666666666666

Interpretation

Run 20260801-113246-pretrained_llm_exact_reward_smoke_jean_zay-6224172 cleared
the basic reward-only plumbing gate. Both variants ran through sampled
generation, integer parsing, scalar correctness reward, ES update, and final
metrics without numerical failure.

The result does not give a strong decomposed win. Decomposed EGGROLL was only
slightly ahead on mean final correctness and mean improvement, while plain
EGGROLL had the better best-achieved correctness. The win pattern is weak and
rank-dependent, so the honest interpretation is parity with a small favorable
hint for decomposed EGGROLL, not evidence strong enough for a paper claim.

The boring alternative explanation is sampling noise and benchmark granularity:
the evaluation set is deliberately tiny, and correctness moves in coarse jumps.
This run does not rule that out.

The useful next step is either a larger generated-arithmetic exact-reward sweep
with the same code path, or a true GSM8K-subset smoke that streams the dataset
inside the job workdir and keeps the same sampled-answer numeric reward.