SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.12474 · NeurIPS · 2023

CSMED: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews

T Wien, Matthias Samwald, Wojciech Kusa, Oscar Mendoza, Petr Knoth, Allan Hanbury

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 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/2311.12474.json · badge: /api/ran/2311.12474.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
wojciechkusa/systematic-review-datasets canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
WojciechKusa/systematic-review-datasets canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
norm Ran
ran, honoured the contract we drafted
WojciechKusa/systematic-review-datasets/visualisation/create_data_card.py
code served (permissive licence) · get_code("16f4805997ad3694")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

lengths = np.array([10.5, 12.3, 9.8, 11.2, 10.1, 13.5])

ARGS = {
    "lengths": lengths
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
prepare_clinical_dataset Ran
ran; our contract draft was wrong, not the code
wojciechkusa/systematic-review-datasets/csmed/datasets/sas2010/sas2010.py
code served (permissive licence) · get_code("180bf75315cfc44d")
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 DataFrame. 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 os
import tempfile
import pandas as pd

# Create a temporary directory structure that mimics the repository layout
temp_dir = tempfile.mkdtemp()
repo_path = temp_dir

dataset_name = "test_dataset"
labels_filename = "labels.txt"

# Create the necessary directory structure
dataset_dir = f"{repo_path}/modeling/curious_snake/data/{dataset_name}"
os.makedirs(f"{dataset_dir}/Abstracts", exist_ok=True)
os.makedirs(f"{dataset_dir}/Titles", exist_ok=True)

# Create labels file
labels_file_path = f"{dataset_dir}/{labels_filename}"
with open(labels_file_path, 'w', encoding='utf-8') as f:
    f.write("doc1 1\n")
    f.write("doc2 -1\n")
    f.write("doc3 0\n")

# Create abstract files
with open(f"{dataset_dir}/Abstracts/doc1", 'w', encoding='utf-8') as f:
    f.write("This is an abstract for document 1.\n")

with open(f"{dataset_dir}/Abstracts/doc2", 'w', encoding='utf-8') as f:
    f.write("This is an abstract for document 2.\n")

with open(f"{dataset_dir}/Abstracts/doc3", 'w', encoding='utf-8') as f:
    f.write("This is an abstract for document 3.\n")

# Create title files
with open(f"{dataset_dir}/Titles/doc1", 'w', encoding='utf-8') as f:
    f.write("Title for document 1\n")

with open(f"{dataset_dir}/Titles/doc2", 'w', encoding='utf-8') as f:
    f.write("Title for document 2\n")

with open(f"{dataset_dir}/Titles/doc3", 'w', encoding='utf-8') as f:
    f.write("Title for document 3\n")

ARGS = {
    "dataset_name": dataset_name,
    "labels_filename": labels_filename,
    "repository_path": repo_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
prepare_fluoride_dataset Ran
ran; our contract draft was wrong, not the code
wojciechkusa/systematic-review-datasets/csmed/datasets/swift/swift.py
code served (permissive licence) · get_code("acf190a888a7bc41")
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 DataFrame. 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 pandas as pd

# Create a minimal DataFrame that matches what prepare_fluoride_dataset expects
df = pd.DataFrame({
    'Title': ['Title 1', None, 'Title 3'],
    'Abstract': ['Abstract 1', 'Abstract 2', None],
    'Included': ['INCLUDED', 'EXCLUDED', 'INCLUDED']
})

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
prepare_neuropathic_pain_dataset Ran
ran; our contract draft was wrong, not the code
wojciechkusa/systematic-review-datasets/csmed/datasets/swift/swift.py
code served (permissive licence) · get_code("c6aa3bdeca6296c4")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create a sample dataframe with the required columns
data = {
    'Title': ['Neuropathic Pain Study 1', 'Neuropathic Pain Study 2', None, 'Study 4'],
    'Abstract': ['This is an abstract about neuropathic pain', None, 'Another abstract', 'Final abstract'],
    'Label': ['Included', 'Excluded', 'Included', 'Excluded']
}

df = pd.DataFrame(data)

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
tokenizer Ran
ran; our contract draft was wrong, not the code
WojciechKusa/systematic-review-datasets/visualisation/create_data_card.py
code served (permissive licence) · get_code("5a0867ac775628bb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple. 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
from collections import Counter

torch.manual_seed(0)

text = "This is a sample text for tokenization"
counter = Counter()

ARGS = {
    "text": text,
    "counter": counter
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
prepare_fluoride_dataset 1 other paper
1 dated earlier
2201.07534 (2022-01)
Automation of Citation Screening for Systematic Literature Reviews using Neural Networks: A Replicability Study
prepare_neuropathic_pain_dataset 1 other paper
1 dated earlier
2201.07534 (2022-01)
Automation of Citation Screening for Systematic Literature Reviews using Neural Networks: A Replicability Study

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

Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the identification of relevant studies for SLRs. However, the lack of standardised evaluation datasets makes comparing the performance of such automated literature screening systems difficult. In this paper, we analyse the citation screening evaluation datasets, revealing that many of the available datasets are either too small, suffer from data leakage or have limited applicability to systems treating automated literature screening as a classification task, as opposed to, for example, a retrieval or question-answering task. To address these challenges, we introduce CSMED, a meta-dataset consolidating nine publicly released collections, providing unified access to 325 SLRs from the fields of medicine and computer science. CSMED serves as a comprehensive resource for training and evaluating the performance of automated citation screening models. Additionally, we introduce CSMED-FT, a new dataset designed explicitly for evaluating the full text publication screening task. To demonstrate the utility of CSMED, we conduct experiments and establish baselines on new datasets.

For agents

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

get_harvested_code_for_paper("2311.12474")
get_code_for_paper("2311.12474")
have("2311.12474")

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

curl https://syntology.ai/api/ran/2311.12474.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.12474.svg)](https://syntology.ai/paper/2311.12474)

Connect an agent — have() is free.