SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.11570 · 2026

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering

Liang Zhao, Xiangyu Zhang, Xiangfeng Wang, Qi Han, Chun Yuan, Daxin Jiang, Zheng Ge, Tong Xu, Yinmin Zhang, Hangyu Guo, Chengyuan Yao, Yanlin Lai, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.11570.json · badge: /api/ran/2602.11570.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
wonderful9462/PRIME canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_scores Ran
ran; our contract draft was wrong, not the code
wonderful9462/PRIME/evaluation/calculate_accuracy.py
pointer only (licence: NONE) · get_code("32f5344f9c7eac24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wonderful9462/PRIME when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_token_number Ran
ran, honoured the contract we drafted
wonderful9462/PRIME/evaluation/calculate_accuracy.py
pointer only (licence: NONE) · get_code("e46a2c41657f58df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wonderful9462/PRIME when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_jsonl_file Ran
ran; our contract draft was wrong, not the code
wonderful9462/PRIME/evaluation/calculate_accuracy.py
pointer only (licence: NONE) · get_code("59a153f4788626a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wonderful9462/PRIME when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_judgment Ran
ran; our contract draft was wrong, not the code
wonderful9462/PRIME/evaluation/evaluate_compassverifier.py
pointer only (licence: NONE) · get_code("e1ae9a61eea7cd2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wonderful9462/PRIME when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth, often neglecting potential errors in the derivation process. This leads to assigning positive rewards to correct answers produced from incorrect derivations. To bridge this gap, we introduce P R I M E, a benchmark for evaluating verifiers on PRocess-outcome alignment verification In Mathematics and Engineering. Curated from a comprehensive collection of college-level STEM problems, P R I M E comprises 2,530 high-difficulty samples through a consistency-based filtering pipeline. Through extensive evaluation, we find that current verifiers frequently fail to detect derivation flaws. Furthermore, we propose a process-aware RLVR training paradigm utilizing verifiers selected via P R I M E. This approach substantially outperforms the outcome-only verification baseline, achieving absolute performance gains of 8.29%, 9.12%, and 7.31% on AIME24, AIME25, and Beyond-AIME, respectively, for the Qwen3-14B-Base model. Finally, we demonstrate a strong linear correlation (𝑅 2 > 0.92) between verifier accuracy on P R I M E and RLVR training effectiveness, validating P R I M E as a reliable predictor for verifier selection. We release the benchmark and code at https://github.com/wonderful9462/PRIME.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.11570")
get_code_for_paper("2602.11570")
have("2602.11570")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.11570.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.11570.svg)](https://syntology.ai/paper/2602.11570)

Connect an agent — have() is free.