SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.06222 · 2020

An Evaluation of Change Point Detection Algorithms

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 7 failures of our instrument; 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/2003.06222.json · badge: /api/ran/2003.06222.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
alan-turing-institute/TCPD canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
alan-turing-institute/TCPDBench canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
clean_cps Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alan-turing-institute/TCPDBench/analysis/scripts/summarize.py
code served (permissive licence) · get_code("32d759dff80d8514")
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 list, ndim 1, dtype family int; 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - locations: iterable of integers that are compared with 1 and n_obs - 1
# - dataset: dict-like object with key 'n_obs' that returns an integer

locations = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
dataset = {'n_obs': 10}

ARGS = {
    'locations': locations,
    'dataset': dataset
}
Setup block drafted by
a language model, Claude Haiku 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 list, ndim 1, dtype family int — 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
frac_to_dt Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPD/utils/plot_dataset.py
code served (permissive licence) · get_code("2abd80ade287668c")
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 datetime. 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 datetime

def frac_to_dt(number):
    number = float(number)
    year = int(float(number))
    remainder = number - year
    begin = datetime.datetime(year, 1, 1)
    end = datetime.datetime(year + 1, 1, 1)
    seconds = remainder * (end - begin).total_seconds()
    return begin + datetime.timedelta(seconds=seconds)

ARGS = {
    "number": 2023.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type datetime — a datetime output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a datetime output the recorded ndim 0 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
load_annotations Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPDBench/analysis/scripts/summarize.py
code served (permissive licence) · get_code("dc1396f0c3ccf1f9")
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 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 json
import tempfile
import os

# Create a temporary JSON file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "annotations.json")

# Create sample annotation data
annotation_data = {
    "dataset1": [
        {"id": 1, "label": "cat"},
        {"id": 2, "label": "dog"}
    ],
    "dataset2": [
        {"id": 3, "label": "bird"},
        {"id": 4, "label": "fish"}
    ]
}

# Write to temporary file
with open(temp_file, 'w') as f:
    json.dump(annotation_data, f)

# Define ARGS
ARGS = {
    "filename": temp_file,
    "dataset": "dataset1"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
load_data Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPD/utils/plot_dataset.py
code served (permissive licence) · get_code("516e4b18b1e92e6b")
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 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 datetime
import json
import pandas as pd
import tempfile
import os

# Create a temporary JSON file with test data
temp_dir = tempfile.mkdtemp()
test_file = os.path.join(temp_dir, "test_data.json")

test_data = {
    "name": "Test Series",
    "time": {
        "format": "%Y-%m-%d",
        "raw": ["2020-01-01", "2020-01-02", "2020-01-03"]
    },
    "series": [
        {
            "raw": [1.0, 2.0, 3.0]
        },
        {
            "raw": [4.0, 5.0, 6.0]
        }
    ]
}

with open(test_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "filename": test_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
pandas — 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
load_dataset_script Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPD/build_tcpd.py
code served (permissive licence) · get_code("a5589988233d11df")
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 module. 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 tempfile
import os

# Create a temporary Python file to use as the dataset script
temp_dir = tempfile.mkdtemp()
script_path = os.path.join(temp_dir, "test_dataset.py")

# Write a minimal valid Python module to the temporary file
with open(script_path, 'w') as f:
    f.write("""
# Minimal dataset script
def load_data():
    return []
""")

ARGS = {
    "module_name": "test_dataset_module",
    "path": script_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
imp — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module output the recorded ndim 0 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
load_json Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPDBench/analysis/scripts/summarize.py
code served (permissive licence) · get_code("811e1abb6d8304bb")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with valid content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.json")

# Write valid JSON to the file
with open(temp_file, 'w') as f:
    json.dump({"key": "value", "number": 42}, f)

ARGS = {
    "filename": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 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
load_result Ran
ran; our contract draft was wrong, not the code
alan-turing-institute/TCPD/utils/plot_dataset.py
code served (permissive licence) · get_code("e760a298613383f4")
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 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 json
import tempfile
import os

# Create a temporary JSON file with valid data structure
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "result.json")

# Write a valid result file
result_data = {
    "status": "SUCCESS",
    "result": {
        "cplocations": [
            {"x": 10, "y": 20},
            {"x": 30, "y": 40}
        ]
    }
}

with open(temp_file, 'w') as fp:
    json.dump(result_data, fp)

ARGS = {
    "filename": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
clean_dataset Not yet run
unverified (harvested, no recorded run)
alan-turing-institute/TCPD/build_tcpd.py
code served (permissive licence) · get_code("720f4672c2ed9380")
How it ran

no invocation recorded.

collect_dataset Not yet run
unverified (harvested, no recorded run)
alan-turing-institute/TCPD/build_tcpd.py
code served (permissive licence) · get_code("674086fdf66aa215")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Change point detection is an important part of time series analysis, as the presence of a change point indicates an abrupt and significant change in the data generating process. While many algorithms for change point detection have been proposed, comparatively little attention has been paid to evaluating their performance on real-world time series. Algorithms are typically evaluated on simulated data and a small number of commonly-used series with unreliable ground truth. Clearly this does not provide sufficient insight into the comparative performance of these algorithms. Therefore, instead of developing yet another change point detection method, we consider it vastly more important to properly evaluate existing algorithms on real-world data. To achieve this, we present a data set specifically designed for the evaluation of change point detection algorithms that consists of 37 time series from various application domains. Each series was annotated by five human annotators to provide ground truth on the presence and location of change points. We analyze the consistency of the human annotators, and describe evaluation metrics that can be used to measure algorithm performance in the presence of multiple ground truth annotations. Next, we present a benchmark study where 14 algorithms are evaluated on each of the time series in the data set. Our aim is that this data set will serve as a proving ground in the development of novel change point detection algorithms.

For agents

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

get_harvested_code_for_paper("2003.06222")
get_code_for_paper("2003.06222")
have("2003.06222")

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

curl https://syntology.ai/api/ran/2003.06222.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.06222.svg)](https://syntology.ai/paper/2003.06222)

Connect an agent — have() is free.