SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.16490 · 2022

Coder Reviewer Reranking for Code Generation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 1 violated it and 0 have no contract verdict; 0 failures 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/2211.16490.json · badge: /api/ran/2211.16490.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
facebookresearch/coder_reviewer_reranking canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
filter_repeat Ran
ran, violated the contract we drafted
facebookresearch/coder_reviewer_reranking/sample_selectors.py
pointer only (licence: NOASSERTION) · get_code("64d47c9d4e0d0c5e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/coder_reviewer_reranking (NOASSERTION). 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.

single_exec_result_matching Ran
ran, honoured the contract we drafted
facebookresearch/coder_reviewer_reranking/sample_selectors.py
pointer only (licence: NOASSERTION) · get_code("e0d0a3c69f5ae939")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/coder_reviewer_reranking (NOASSERTION). 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
single_exec_result_matching 1 other paper
1 dated earlier
2204.11454 (2022-04)
Natural Language to Code Translation with Execution

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

Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions. Inspired by collaborative programming, we propose Coder-Reviewer reranking. We augment Coder language models from past work, which generate programs given language instructions, with Reviewer models, which evaluate the likelihood of the instruction given the generated programs. We perform an extensive study across six datasets with eight models from three model families. Experimental results show that Coder-Reviewer reranking leads to consistent and significant improvement (up to 17% absolute accuracy gain) over reranking with the Coder model only. When combined with executability filtering, Coder-Reviewer reranking can often outperform the minimum Bayes risk method. Coder-Reviewer reranking is easy to implement by prompting, can generalize to different programming languages, and works well with off-the-shelf hyperparameters.

For agents

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

get_harvested_code_for_paper("2211.16490")
get_code_for_paper("2211.16490")
have("2211.16490")

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

curl https://syntology.ai/api/ran/2211.16490.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.16490.svg)](https://syntology.ai/paper/2211.16490)

Connect an agent — have() is free.