Datasets:

asingh15
/

prm-mc-value-context-solution-label-xprob-stratified-v1

messages listlengths 2 2	enable_thinking bool 1 class	id stringlengths 16 16	source stringclasses 1 value	sample_index int64 0 7	step_idx int64 0 244	num_steps int64 1 2.26k	label stringclasses 1 value	correct bool 2 classes	loss_weight float64 1 1	reward float64 0.13 0.88
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	1	4	12	yes	true	1	0.625
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	1	8	12	yes	true	1	0.8125
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	1	12	12	yes	true	1	0.875
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	0	0	23	yes	true	1	0.8125
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	0	4	23	yes	true	1	0.6875
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	0	8	23	yes	true	1	0.6875
[ { "role": "user", "content": "# Role\nYou are an expert evaluator acting as a process reward model (PRM). You are given a\nproblem and a step-by-step solution that may be only a partial trace -- a prefix\nof a longer reasoning chain that can stop in the middle of a step. Judge whether the\nreasoning sho...	false	8754a7c9a035fd12	polaris	0	12	23	yes	true	1	0.75
[{"role":"user","content":"# Role\nYou are an expert evaluator acting as a process reward model (PRM(...TRUNCATED)	false	8754a7c9a035fd12	polaris	0	16	23	yes	true	1	0.875
[{"role":"user","content":"# Role\nYou are an expert evaluator acting as a process reward model (PRM(...TRUNCATED)	false	8754a7c9a035fd12	polaris	0	20	23	yes	true	1	0.6875
[{"role":"user","content":"# Role\nYou are an expert evaluator acting as a process reward model (PRM(...TRUNCATED)	false	8754a7c9a035fd12	polaris	0	23	23	yes	true	1	0.8125

End of preview. Expand in Data Studio

PRM MC Value Context: Solution Label Xprob (Stratified v1)

Solutions from a different problem in the same split are tagged correct or incorrect.

This repository is one arm of a five-way, row-matched process reward model ablation. The target is a Monte Carlo probability of eventual rollout success for a partial solution prefix; only the auxiliary context changes between arms.

Arm configuration

Context mode: solution_label
Cross-problem context: yes
Context correctness labels: yes
Split policy: deterministic difficulty-stratified v1
Split manifest SHA-256: c7287b917d3ee6eca482051c5256610b1b193e8f7bcd7800a28bfaed21351637

Cross-problem examples are selected within the query row's split. The held-out problems therefore do not leak into training context.

Splits

Split	Rows	Problems
train	50,447	6,879
validation	1,098	128
test	4,755	512

The local val.parquet artifact is published as validation.parquet. dataset_provenance.json, split_manifest.json, and verification.json record the build and five-arm integrity checks.

Downloads last month: 17