SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.16802 · NeurIPS · 2024

AutoPSV: Automated Process-Supervised Verifier

Zhijiang Guo, Jianbo Dai, Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Yingjia Wan

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 7 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2405.16802.json · badge: /api/ran/2405.16802.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
rookie-joe/autocv canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
rookie-joe/AutoPSV canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
rookie-joe/autopsv community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
Verifier Ran
ran on a synthesized input
rookie-joe/autopsv/utils/process_verifier_models.py
pointer only (licence: NONE) · get_code("31531bb131326426")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autopsv 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.

create_train_dataloader Ran
ran; our contract draft was wrong, not the code
rookie-joe/autocv/utils/verfier_datasets.py
pointer only (licence: NONE) · get_code("49640af61a6d3492")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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.

get_dataset_examples Ran
ran; our contract draft was wrong, not the code
rookie-joe/autocv/utils/verfier_datasets.py
pointer only (licence: NONE) · get_code("69664c2b879ea002")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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_tokenizer Ran
ran; our contract draft was wrong, not the code
rookie-joe/autocv/data_annotation.py
pointer only (licence: NONE) · get_code("17243183193565ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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.

mse_loss_with_mask Ran
ran; our contract draft was wrong, not the code
rookie-joe/autopsv/utils/process_verifier_models.py
pointer only (licence: NONE) · get_code("dfef91c8dfd2a1ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autopsv 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.

read_jsonl Ran
ran; our contract draft was wrong, not the code
rookie-joe/autocv/utils/verfier_datasets.py
pointer only (licence: NONE) · get_code("c409d17fa33773fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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.

split_string_list Ran
ran; our contract draft was wrong, not the code
rookie-joe/AutoPSV/data_annotation.py
pointer only (licence: NONE) · get_code("8fd49b81e935073b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/AutoPSV 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.

split_token_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rookie-joe/AutoPSV/data_annotation.py
pointer only (licence: NONE) · get_code("3f4f58ae7ef13d89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/AutoPSV 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.

VerifierModelOutput Not yet run
unverified (harvested, no recorded run)
rookie-joe/autopsv/utils/process_verifier_models.py
pointer only (licence: NONE) · get_code("c8b43628f651b52e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autopsv 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. No invocation recorded.

build_verifier_from_osv Not yet run
unverified (harvested, no recorded run)
rookie-joe/autocv/utils/process_verifier_models.py
pointer only (licence: NONE) · get_code("100d6596edff1631")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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. No invocation recorded.

build_verifier_from_scratch Not yet run
unverified (harvested, no recorded run)
rookie-joe/autocv/utils/process_verifier_models.py
pointer only (licence: NONE) · get_code("e460ed999d4fa5b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rookie-joe/autocv 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

In this work, we propose a novel method named Automated Process-Supervised Verifier (AUTOPSV) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. AUTOPSV begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process, enabling error detection even in scenarios where ground truth answers are unavailable. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. We demonstrate that the verification model, when trained on process annotations generated by AUTOPSV, exhibits improved performance in selecting correct answers from multiple LLM-generated outputs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of AUTOPSV is available at https://github.com/rookie-joe/AutoPSV.

For agents

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

get_harvested_code_for_paper("2405.16802")
get_code_for_paper("2405.16802")
have("2405.16802")

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

curl https://syntology.ai/api/ran/2405.16802.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.16802.svg)](https://syntology.ai/paper/2405.16802)

Connect an agent — have() is free.