SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.19767 · 2026

skchange: Fast and Flexible Algorithms for Changepoint Detection

Martin Tveten, Johannes Kolstø, Per August, Jarval Moen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 18 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
NorskRegnesentral/skchange canonical 4 of 15
NorskRegnesentral/change-point-benchmark canonical 3 of 3
FunctionStatusWhere it lives
check_random_generator Ran NorskRegnesentral/skchange/skchange/datasets/_utils.py
code served (permissive licence) · get_code("65e9cdd140ddcdbb")
check_segment_lengths Ran NorskRegnesentral/skchange/skchange/datasets/_utils.py
code served (permissive licence) · get_code("cc8b62725c8d5d9c")
find_repo_root Ran NorskRegnesentral/change-point-benchmark/src/change_bench/paths.py
pointer only (licence: NONE) · get_code("7627c883ecac4153")
get_n_variables Ran NorskRegnesentral/skchange/skchange/datasets/_generate_normal.py
code served (permissive licence) · get_code("31eae627be50ede8")
latest_result_path Ran NorskRegnesentral/change-point-benchmark/src/change_bench/paths.py
pointer only (licence: NONE) · get_code("6c0b0d3cff4aa450")
recycle_list Ran NorskRegnesentral/skchange/skchange/datasets/_utils.py
code served (permissive licence) · get_code("4b3cd97c7142e071")
result_date Ran NorskRegnesentral/change-point-benchmark/src/change_bench/paths.py
pointer only (licence: NONE) · get_code("f909cad74c5045d6")
generate_continuous_piecewise_linear_data Not yet run NorskRegnesentral/skchange/skchange/datasets/_generate_linear_trend.py
code served (permissive licence) · get_code("202b5f03a1470cae")
generate_piecewise_data Not yet run NorskRegnesentral/skchange/skchange/datasets/_generate.py
code served (permissive licence) · get_code("d3a86d27b9b6e57a")
generate_piecewise_normal_data Not yet run NorskRegnesentral/skchange/skchange/datasets/_generate_normal.py
code served (permissive licence) · get_code("18dae5d0f3fd3ff2")
generate_piecewise_regression_data Not yet run NorskRegnesentral/skchange/skchange/datasets/_generate_regression.py
code served (permissive licence) · get_code("abb6641005dfa0ac")
is_change_detector Not yet run NorskRegnesentral/skchange/skchange/detectors/_base.py
code served (permissive licence) · get_code("24b6e4192929c392")
is_change_score Not yet run NorskRegnesentral/skchange/skchange/interval_scorers/_base.py
code served (permissive licence) · get_code("3f9ed6c28db376f0")
is_cost Not yet run NorskRegnesentral/skchange/skchange/interval_scorers/_base.py
code served (permissive licence) · get_code("2558b0d16025cb4d")
is_saving Not yet run NorskRegnesentral/skchange/skchange/interval_scorers/_base.py
code served (permissive licence) · get_code("ff284f19db5493f6")
load_hvac_system_data Not yet run NorskRegnesentral/skchange/skchange/datasets/_data_loaders.py
code served (permissive licence) · get_code("1dfb050bb0457458")
resolve_sampler Not yet run NorskRegnesentral/skchange/skchange/tuning/_null_models.py
code served (permissive licence) · get_code("fe8663e999e3240f")
sampler_requires_data Not yet run NorskRegnesentral/skchange/skchange/tuning/_null_models.py
code served (permissive licence) · get_code("0beffbfc2c7f1556")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Skchange is an open-source Python library for detecting structural changes in time series. It implements modern change detection algorithms within a unified and extensible framework. The algorithms are modular and composable, and they include changepoint search methods based on both cost minimisation and statistical tests. Key features include the detection of anomalous segments in addition to changepoints; theoretically well-founded fast and approximate search methods; theoretically well-founded algorithms for high-dimensional data, covering settings where either few or many features change simultaneously; utilities for automatic and data-driven penalty calibration, which balances false alarms against missed detections; and a large collection of built-in costs and statistical tests. The design follows established scikit-learn conventions to streamline both user and contributor experience, and Numba is used extensively to achieve high computational performance. Source code and documentation are available at https://github.com/NorskRegnesentral/skchange.

For agents

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

get_harvested_code_for_paper("2608.19767")
get_code_for_paper("2608.19767")
have("2608.19767")

Connect an agent — have() is free.