SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.02883 · 2024

CoIR: A Comprehensive Benchmark for Code Information Retrieval Models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 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/2407.02883.json · badge: /api/ran/2407.02883.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
coir-team/coir canonical (classifier label)
classifier basis: census
2 ran · 3 no recorded run
FunctionStatusWhere it lives
cos_sim Ran
ran, honoured the contract we drafted
coir-team/coir/coir/beir/util.py
code served (permissive licence) · get_code("8ca90d5388372be5")
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 Tensor, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create two small tensors with distinct dimensions
# a: batch_size=2, embedding_dim=4
a = torch.randn(2, 4)

# b: batch_size=3, embedding_dim=4 (distinct first dim to probe shapes)
b = torch.randn(3, 4)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
dot_score Ran
ran, honoured the contract we drafted
coir-team/coir/coir/beir/util.py
code served (permissive licence) · get_code("afa18317f44e63ad")
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 Tensor, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create two small tensors for the dot_score function
# a: shape (2, 4) - 2 vectors of dimension 4
# b: shape (3, 4) - 3 vectors of dimension 4
# This will produce a (2, 3) output matrix of dot products

a = torch.randn(2, 4)
b = torch.randn(3, 4)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
download_and_unzip Not yet run
unverified (harvested, no recorded run)
coir-team/coir/coir/beir/util.py
code served (permissive licence) · get_code("5851a19162cf6895")
How it ran

no invocation recorded.

get_tasks Not yet run
unverified (harvested, no recorded run)
coir-team/coir/coir/data_loader.py
code served (permissive licence) · get_code("0adc655290cb9e75")
How it ran

no invocation recorded.

load_data_from_hf Not yet run
unverified (harvested, no recorded run)
coir-team/coir/coir/data_loader.py
code served (permissive licence) · get_code("1599b1504459ed71")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
cos_sim 7 other papers
5 dated earlier, 1 later, 1 same year, order not determinable
1907.11692 (2019-07)
RoBERTa: A Robustly Optimized BERT Pretraining Approach
2104.08663 (2021-04)
BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models
2310.20501 (2023-10)
Neural Retrievers are Biased Towards LLM-Generated Content
and 4 more not named here
dot_score 6 other papers
4 dated earlier, 1 later, 1 same year, order not determinable
1907.11692 (2019-07)
RoBERTa: A Robustly Optimized BERT Pretraining Approach
2104.08663 (2021-04)
BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models
2310.20501 (2023-10)
Neural Retrievers are Biased Towards LLM-Generated Content
and 3 more not named here
download_and_unzip 3 other papers
2 dated earlier, 1 same year, order not determinable
2310.20501 (2023-10)
Neural Retrievers are Biased Towards LLM-Generated Content
2024.findings-acl.421 (2024 (year only))
Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
2406.14277 (2024-06)
QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

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

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically important yet remains under-explored, with existing methods and benchmarks inadequately representing the diversity of code in various domains and tasks. Addressing this gap, we present COIR (Code Information Retrieval Benchmark), a robust and comprehensive benchmark specifically designed to assess code retrieval capabilities. COIR comprises ten meticulously curated code datasets, spanning eight distinctive retrieval tasks across seven diverse domains. We first discuss the construction of COIR and its diverse dataset composition. Further, we evaluate nine widely used retrieval models using COIR, uncovering significant difficulties in performing code retrieval tasks even with state-of-the-art systems. To facilitate easy adoption and integration within existing research workflows, COIR has been developed as a user-friendly Python framework, readily installable via pip. It shares same data schema as other popular benchmarks like MTEB and BEIR, enabling seamless cross-benchmark evaluations. Through COIR, we aim to invigorate research in the code retrieval domain, providing a versatile benchmarking tool that encourages further development and exploration of code retrieval systems. https://github.com/CoIR-team/coir.

For agents

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

get_harvested_code_for_paper("2407.02883")
get_code_for_paper("2407.02883")
have("2407.02883")

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

curl https://syntology.ai/api/ran/2407.02883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.02883.svg)](https://syntology.ai/paper/2407.02883)

Connect an agent — have() is free.