SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.10866 · EMNLP · 2022

CodeRetriever: Large-scale Contrastive Pre-training for Code Search

Weizhu Chen, Weizhen Qi, Yeyun Gong, Nan Duan, Yelong Shen, Hang Zhang, Xipeng Qiu, Daxin Jiang, Xiaonan Li, Bolun Yao

arXiv · PDF · Open in the Atlas

Code that ran

None of the 2 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (2 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/2201.10866.json · badge: /api/ran/2201.10866.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
microsoft/ar2 marked official in Papers with Code
Papers with Code archive
0 ran · 2 no recorded run
FunctionStatusWhere it lives
BiBertEncoder Not yet run
unverified (harvested, no recorded run)
microsoft/ar2/AR2/model/models.py
code served (permissive licence) · get_code("04b4fbd2f94fbd79")
How it ran

no invocation recorded.

HFBertEncoder Not yet run
unverified (harvested, no recorded run)
microsoft/ar2/AR2/model/models.py
code served (permissive licence) · get_code("4398cd906200a582")
How it ran

no invocation 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, 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 2 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 paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt two contrastive learning schemes in CodeRetriever: unimodal contrastive learning and bimodal contrastive learning. For unimodal contrastive learning, we design an unsupervised learning approach to build semanticrelated code pairs based on the documentation and function name. For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build code-text pairs. Both contrastive objectives can fully leverage large-scale code corpus for pre-training. Extensive experimental results show that CodeRetriever achieves new stateof-the-art with significant improvement over existing code pre-trained models, on eleven domain/language-specific code search tasks with six programming languages in different code granularity (function-level, snippet-level and statement-level). These results demonstrate the effectiveness and robustness of CodeRetriever. The codes and resources are available at https://github.com/microsoft/ AR2/tree/main/CodeRetriever.

For agents

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

get_harvested_code_for_paper("2201.10866")
get_code_for_paper("2201.10866")
have("2201.10866")

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

curl https://syntology.ai/api/ran/2201.10866.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.10866.svg)](https://syntology.ai/paper/2201.10866)

Connect an agent — have() is free.