SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.12708 · EMNLP · 2024

AGENTREVIEW: Exploring Peer Review Dynamics with LLM Agents

Jindong Wang, Hao Chen, Yijia Xiao, Yiqiao Jin, Kaijie Zhu, Qinlin Zhao, Yiyang Wang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure of our instrument; 0 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/2406.12708.json · badge: /api/ran/2406.12708.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
ahren09/agentreview canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_text_into_dict Ran
ran; our contract draft was wrong, not the code
ahren09/agentreview/agentreview/paper_processor.py
code served (permissive licence) · get_code("d22ad1c48fa00ddc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Construct a sample PDF-extracted text with the expected structure
sample_text = """Under review at ICLR 2024

Deep Learning Architecture for Computer Vision

John Doe, Jane Smith

Abstract
This paper proposes a novel deep learning architecture for computer vision tasks.
We demonstrate state-of-the-art results on multiple benchmarks.
Our method outperforms existing approaches by significant margins.

Introduction
Computer vision has made tremendous progress in recent years.
Traditional methods have been largely replaced by deep learning approaches.
In this work, we present a new architecture that improves upon existing methods.

Related Work
Previous work in this area includes CNNs, Vision Transformers, and hybrid approaches.
Our method builds upon these foundations.

Figure 1: Sample figure showing the architecture overview.
This figure demonstrates the main components of our system.

Methodology
Our approach consists of three main components.
First, we use a feature extraction module.
Second, we apply a refinement network.
Third, we use a classification head.

Figure 2: Detailed component breakdown.
This figure shows how components interact.

Table 1: Comparison of methods.
Our method achieves better performance than baselines.

Experimental Results
We evaluate on multiple datasets.
Results show improvements across all metrics.

Table 2: Quantitative results.
Performance numbers for all tested methods.

References
[1] Smith et al. 2020
[2] Johnson et al. 2021

Appendix A: Additional Details
Here we provide additional implementation details.
Code availability and hyperparameters are discussed here.

Appendix B: Extended Experiments
Additional experiments with different configurations.
Results remain consistent across settings.
"""

ARGS = {
    "text": sample_text
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exploration and statistics of existing peer review data, which do not adequately address the multivariate nature of the process, account for the latent variables, and are further constrained by privacy concerns due to the sensitive nature of the data. We introduce AGENTREVIEW, the first large language model (LLM) based peer review simulation framework, which effectively disentangles the impacts of multiple latent factors and addresses the privacy issue. Our study reveals significant insights, including a notable 37.1% variation in paper decisions due to reviewers' biases, supported by sociological theories such as the social influence theory, altruism fatigue, and authority bias. We believe that this study could offer valuable insights to improve the design of peer review mechanisms. Our code is available at https://github.com/Ahren09/ AgentReview.

For agents

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

get_harvested_code_for_paper("2406.12708")
get_code_for_paper("2406.12708")
have("2406.12708")

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

curl https://syntology.ai/api/ran/2406.12708.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.12708.svg)](https://syntology.ai/paper/2406.12708)

Connect an agent — have() is free.