SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.09330 · 2024

BARO: Robust Root Cause Analysis for Microservices via Multivariate Bayesian Online Change Point Detection

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 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/2405.09330.json · badge: /api/ran/2405.09330.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
phamquiluan/baro canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_mem_mb Ran
ran; our contract draft was wrong, not the code
phamquiluan/baro/baro/root_cause_analysis.py
code served (permissive licence) · get_code("d3c7ae0ea1bc5e8b")
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 memory columns and non-memory columns
data = {
    'cpu_mem': [1000000.0, 2000000.0, 3000000.0],
    'gpu_mem': [500000.0, 1500000.0, 2500000.0],
    'name': ['task1', 'task2', 'task3'],
    'duration_mem': [100000.0, 200000.0, 300000.0],
    'other_value': [10, 20, 30]
}

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
drop_extra Ran
ran; our contract draft was wrong, not the code
phamquiluan/baro/baro/root_cause_analysis.py
code served (permissive licence) · get_code("3fd4531b6cc521f0")
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 various columns that should be dropped
# and some that should be kept
df = pd.DataFrame({
    'time': [1, 2],
    'time.1': [3, 4],
    'value': [5, 6],
    'metric': [7, 8],
    'frontend-external-calls': [9, 10],
    'main_cpu': [11, 12],
    'main_memory': [13, 14],
    'PassthroughCluster_latency': [15, 16],
    'redis_connections': [17, 18],
    'rabbitmq_queue_depth': [19, 20],
    'queue_size': [21, 22],
    'session_id': [23, 24],
    'istio-proxy-latency': [25, 26],
    'keep_this': [27, 28],
    'another_keep': [29, 30]
})

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 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
nsigma Ran
ran; our contract draft was wrong, not the code
phamquiluan/baro/baro/anomaly_detection.py
code served (permissive licence) · get_code("0176111946c71b54")
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 list, 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 pandas as pd
import numpy as np

# Create a small time series dataset with a 'time' column and data columns
np.random.seed(0)

# Generate synthetic time series data
n_rows = 150
time_values = pd.date_range(start='2024-01-01', periods=n_rows, freq='D')
data_col1 = np.random.normal(loc=100, scale=10, size=n_rows)
data_col2 = np.random.normal(loc=50, scale=5, size=n_rows)

# Inject an anomaly
data_col1[120] = 200  # Anomaly in col1
data_col2[130] = 150  # Anomaly in col2

df = pd.DataFrame({
    'time': time_values,
    'metric1': data_col1,
    'metric2': data_col2
})

ARGS = {
    'data': df,
    'k': 3,
    'startsfrom': 100
}
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 list, ndim 1, dtype family float — a list 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
select_useful_cols Ran
ran; our contract draft was wrong, not the code
phamquiluan/baro/baro/root_cause_analysis.py
code served (permissive licence) · get_code("1071c24f3a786747")
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 list, 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 pandas as pd
import numpy as np

# Create a small pandas DataFrame with relevant columns for testing
np.random.seed(0)

data = pd.DataFrame({
    'timestamp': np.arange(10),
    'time_ms': np.arange(10),
    'cpu_usage_cpu': np.random.normal(50, 2, 10),  # std > 1
    'memory_cpu': np.random.normal(60, 0.5, 10),  # std < 1, should not be selected
    'gpu_mem': np.random.normal(30, 2, 10),  # std > 1
    'latency_lat50': np.random.normal(0.05, 0.015, 10),  # (std*1000) > 10
    'other_metric': np.random.normal(100, 0.1, 10),  # std < 1, no matching criteria
})

ARGS = {
    'data': data
}
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 list, ndim 1, dtype family float — a list 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
find_anomalies Not yet run
unverified (harvested, no recorded run)
phamquiluan/baro/baro/anomaly_detection.py
code served (permissive licence) · get_code("7466bdfc71a04d00")
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, 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 5 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

Detecting failures and identifying their root causes promptly and accurately is crucial for ensuring the availability of microservice systems. A typical failure troubleshooting pipeline for microservices consists of two phases: anomaly detection and root cause analysis. While various existing works on root cause analysis require accurate anomaly detection, there is no guarantee of accurate estimation with anomaly detection techniques. Inaccurate anomaly detection results can significantly affect the root cause localization results. To address this challenge, we propose BARO, an end-to-end approach that integrates anomaly detection and root cause analysis for effectively troubleshooting failures in microservice systems. BARO leverages the Multivariate Bayesian Online Change Point Detection technique to model the dependency within multivariate time-series metrics data, enabling it to detect anomalies more accurately. BARO also incorporates a novel nonparametric statistical hypothesis testing technique for robustly identifying root causes, which is less sensitive to the accuracy of anomaly detection compared to existing works. Our comprehensive experiments conducted on three popular benchmark microservice systems demonstrate that BARO consistently outperforms state-of-the-art approaches in both anomaly detection and root cause analysis.

For agents

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

get_harvested_code_for_paper("2405.09330")
get_code_for_paper("2405.09330")
have("2405.09330")

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

curl https://syntology.ai/api/ran/2405.09330.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.09330.svg)](https://syntology.ai/paper/2405.09330)

Connect an agent — have() is free.