Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
2
2
enable_thinking
bool
1 class
id
stringlengths
16
16
source
stringclasses
2 values
sample_index
int64
0
7
step_idx
int64
2
169
num_steps
int64
1
168
label
stringclasses
1 value
correct
bool
2 classes
loss_weight
float64
1
1
reward
float64
0
1
[ { "role": "user", "content": "# Role\nYou are forecasting the rubric value of a response trajectory for an olympiad\nmathematics proof. The problem and response prefix below are fixed. The prefix may\nbe incomplete, or it may already contain the complete response including its final\nanswer.\n\nIf the prefi...
false
d3b87a033b6e837b
fineproofs
5
4
14
yes
false
1
0.433036
[ { "role": "user", "content": "# Role\nYou are forecasting the rubric value of a response trajectory for an olympiad\nmathematics proof. The problem and response prefix below are fixed. The prefix may\nbe incomplete, or it may already contain the complete response including its final\nanswer.\n\nIf the prefi...
false
d3b87a033b6e837b
fineproofs
5
8
14
yes
false
1
0.09375
[ { "role": "user", "content": "# Role\nYou are forecasting the rubric value of a response trajectory for an olympiad\nmathematics proof. The problem and response prefix below are fixed. The prefix may\nbe incomplete, or it may already contain the complete response including its final\nanswer.\n\nIf the prefi...
false
d3b87a033b6e837b
fineproofs
5
12
14
yes
false
1
0.03125
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
5
14
14
yes
false
1
0
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
4
33
yes
false
1
0.1875
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
8
33
yes
false
1
0
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
12
33
yes
false
1
0
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
16
33
yes
false
1
0
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
20
33
yes
false
1
0.03125
[{"role":"user","content":"# Role\nYou are forecasting the rubric value of a response trajectory for(...TRUNCATED)
false
d3b87a033b6e837b
fineproofs
6
24
33
yes
false
1
0
End of preview. Expand in Data Studio

FineProofs PRM Context v2: Solution Label Xprob

This arm uses solution_label context from cross_problem rollouts with packing policy whole_solutions_no_truncation.

This is one of nine row-matched context variants built from the verified FineProofs rollout collection. Partial-prefix and complete-response targets both use canonical normalized rubric credit derived from clamped points divided by max points. The correct column is only a legacy boolean projection at reward >= 0.5; training uses the dense reward target.

Contract

  • Run ID: fineproofs_all_qwen35_9b_direct2phase_m32_20260730
  • Collection model: Qwen/Qwen3.5-9B
  • Collection model revision: c202236235762e1c871ad0ccb60c8ee5ba337b9a
  • Context arm: solution_label_xprob
  • Context mode: solution_label
  • Context scope: cross_problem
  • Correctness labels in context: yes
  • Verification SHA-256: c5a3b92bd6196d4a33cded2c1a01870d1963d323351d573b369b7f97f3b7f648

The nine arms have identical row keys, labels, rewards, train/validation problem split, and hard endpoint coverage. Held-out problems are removed before splitting and context selection.

Splits

Split Rows Problems
train 53,457 2,542
validation 2,602 128

The local val.parquet is published as validation.parquet. dataset_provenance.json, verification.json, and _SUCCESS.json contain the live-input provenance, cross-arm checks, and exact published file fingerprints.

Downloads last month
61