SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.09626 · 2022

BARS: Towards Open Benchmarking for Recommender Systems

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 3 have no contract verdict; 2 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/2205.09626.json · badge: /api/ran/2205.09626.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
openbenchmark/BARS canonical (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
FunctionStatusWhere it lives
dataset_to_uimatrix Ran
ran on a synthesized input
openbenchmark/BARS/matching/libs/CollMetric/CML_utils.py
code served (permissive licence) · get_code("95666fe6e1adbac8")
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 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 tempfile
import os

# Create temporary files with the expected format
temp_dir = tempfile.mkdtemp()
train_file_path = os.path.join(temp_dir, "train.txt")
test_file_path = os.path.join(temp_dir, "test.txt")

# Write train data: format is "user_id item1 item2 item3..."
with open(train_file_path, 'w') as f:
    f.write("0 1 3 5\n")
    f.write("1 2 4\n")
    f.write("2 1 2 3\n")

# Write test data: format is "user_id item1 item2 item3..."
with open(test_file_path, 'w') as f:
    f.write("0 2 6\n")
    f.write("1 1 5\n")
    f.write("2 4\n")

ARGS = {
    "train_data": train_file_path,
    "test_data": test_file_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
doublewrap Ran
ran; our contract draft was wrong, not the code
openbenchmark/BARS/matching/libs/CollMetric/CML.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liufancs/dmrl, is pointer only (licence: NONE) · get_code("da008ff4ea5d7cd5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liufancs/dmrl, and GitHub detected no licence in that repository when it was checked. 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.

get_count Ran
ran; our contract draft was wrong, not the code
openbenchmark/BARS/matching/cf/ENMF/src/ENMF.py
code served (permissive licence) · get_code("39a54c6a662a97bd")
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) 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 small DataFrame with an id column and some data
data = {
    'id': [1, 1, 2, 2, 3],
    'playcount': [10, 20, 30, 40, 50]
}
tp = pd.DataFrame(data)

# The function takes tp (a DataFrame) and id (a column name string)
ARGS = {
    'tp': tp,
    'id': 'id'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int 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
load_data Ran
ran on a synthesized input
openbenchmark/BARS/matching/cf/ENMF/src/ENMF.py
code served (permissive licence) · get_code("914d11222fcb12b0")
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 io

# Create a small TSV string in memory
tsv_data = "col1\tcol2\tcol3\n1\t2\t3\n4\t5\t6\n7\t8\t9\n"

# Create a temporary file-like object
csv_file = io.StringIO(tsv_data)

ARGS = {
    "csv_file": csv_file
}
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 int 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
train_step1 Ran
ran on a synthesized input
openbenchmark/BARS/matching/cf/ENMF/src/ENMF.py
code served (permissive licence) · get_code("1826d5c1a5e0e4e9")
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 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 torch
import torch.nn as nn
import numpy as np

# Create a minimal deep learning model that satisfies the function's usage
class DeepModel(nn.Module):
    def __init__(self):
        super(DeepModel, self).__init__()
        self.fc = nn.Linear(4, 2)
        
        # Create the input placeholders as attributes (mimicking TensorFlow style)
        self.input_u = "input_u_placeholder"
        self.input_ur = "input_ur_placeholder"
        self.dropout_keep_prob = "dropout_keep_prob_placeholder"
        
        # Loss attributes
        self.loss = None
        self.loss1 = None
        self.reg_loss = None
    
    def forward(self, x):
        return self.fc(x)

# Create a minimal session mock for TensorFlow-style usage
class MockSession:
    def __init__(self, deep_model):
        self.deep_model = deep_model
    
    def run(self, fetches, feed_dict):
        # Simulate running the model and computing losses
        # Return dummy values for train_op, loss, loss1, reg_loss
        dummy_loss = 0.5
        dummy_loss1 = 0.3
        dummy_reg_loss = 0.2
        return (None, dummy_loss, dummy_loss1, dummy_reg_loss)

# Create a minimal args class
class Args:
    def __init__(self):
        self.dropout = 0.5

# Setup
torch.manual_seed(0)

# Create model and session
deep = DeepModel()
sess = MockSession(deep)

# Create batch data (batch_size=2, feature_dim=4)
u_batch = np.random.randn(2, 4).astype(np.float32)
y_batch = np.random.randn(2, 4).astype(np.float32)

# Create args
args = Args()

# Create a dummy train_op (in TensorFlow context, this would be an operation)
train_op1 = None

# Define ARGS dictionary
ARGS = {
    "u_batch": u_batch,
    "y_batch": y_batch,
    "deep": deep,
    "sess": sess,
    "train_op1": train_op1,
    "args": args
}
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 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
define_scope Not yet run
unverified (harvested, no recorded run)
openbenchmark/BARS/matching/libs/CollMetric/CML.py
code served (permissive licence) · get_code("a3743ac2a99e4ab6")
How it ran

no invocation recorded.

evaluate_metrics Not yet run
unverified (harvested, no recorded run)
openbenchmark/BARS/matching/cf/EASE_R/src/utils.py
code served (permissive licence) · get_code("d1bf42856841eb19")
How it ran

no invocation recorded.

evaluate_metrics Not yet run
unverified (harvested, no recorded run)
openbenchmark/BARS/matching/item2item/ItemCF/ItemKNN_utils.py
code served (permissive licence) · get_code("e752f6a871ca1c99")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 6 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
doublewrap 2 other papers
2 dated earlier
1805.08402 (2018-05)
Adapted Deep Embeddings: A Synthesis of Methods for $k$-Shot Inductive Transfer Learning
2203.05406 (2022-03)
Disentangled Multimodal Representation Learning for Recommendation
get_count 2 other papers
2 dated earlier
1802.05814 (2018-02)
Variational Autoencoders for Collaborative Filtering
1912.11160 (2019-12)
RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback

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

The past two decades have witnessed the rapid development of personalized recommendation techniques. Despite significant progress made in both research and practice of recommender systems, to date, there is a lack of a widely-recognized benchmarking standard in this field. Many existing studies perform model evaluations and comparisons in an ad-hoc manner, for example, by employing their own private data splits or using different experimental settings. Such conventions not only increase the difficulty in reproducing existing studies, but also lead to inconsistent experimental results among them. This largely limits the credibility and practical value of research results in this field. To tackle these issues, we present an initiative project (namely BARS) aiming for open benchmarking for recommender systems. In comparison to some earlier attempts towards this goal, we take a further step by setting up a standardized benchmarking pipeline for reproducible research, which integrates all the details about datasets, source code, hyper-parameter settings, running logs, and evaluation results. The benchmark is designed with comprehensiveness and sustainability in mind. It covers both matching and ranking tasks, and also enables researchers to easily follow and contribute to the research in this field. This project will not only reduce the redundant efforts of researchers to re-implement or re-run existing baselines, but also drive more solid and reproducible research on recommender systems. We would like to call upon everyone to use the BARS benchmark for future evaluation, and contribute to the project through the portal at: https://openbenchmark.github.io/BARS.

For agents

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

get_harvested_code_for_paper("2205.09626")
get_code_for_paper("2205.09626")
have("2205.09626")

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

curl https://syntology.ai/api/ran/2205.09626.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.09626.svg)](https://syntology.ai/paper/2205.09626)

Connect an agent — have() is free.