Skip to the content.
DOI Hugging Face Streamlit tests Data: ODbL Code: MIT

GBFS guarantees that bike-sharing feeds are syntactically consistent — not that they are semantically comparable. This project audits 1,509 feeds across 48 countries, distils a unified taxonomy of seven data-quality classes, and releases a certified, anomaly-flagged reference dataset of 46,307 French stations so downstream consumers can filter without re-running the pipeline.

Explore the dashboard Source & pipeline Download the dataset Zenodo DOI
46,307certified stations
123French operators
1,509systems audited
48countries
7anomaly classes
30.9%stations removed
Visual abstract: from raw GBFS feeds to a certified, anomaly-flagged catalogue
From raw GBFS feeds to a certified, anomaly-flagged catalogue: a nine-step idempotent purging protocol screens every feed against seven data-quality classes.

The seven data-quality classes

Five structural errors (A1–A5) that violate the implicit semantic contract of the GBFS field they populate, plus two semantic warnings (A6–A7) for spec-compliant publication patterns whose downstream interpretation is nevertheless ambiguous.

structural
A1Out-of-domain inclusion
Car-sharing advertised as a bike-sharing system.
structural
A2Placeholder capacity
Constant non-zero capacity across every station of a system.
structural
A3Structural over-capacity
Conditional averaging on free-floating fleet anchors.
structural
A4Geospatial outlier
Transposed coordinates or stations far from the network (topology-aware).
structural
A5Out-of-perimeter
System bounding box > 50,000 km² or out-of-jurisdiction stations.
warning
A6Zero-capacity dock
At least 1 % of stations declare capacity = 0.
warning
A7Null capacity field
At least 50 % of stations declare capacity = NaN.

Why it matters: the Bordeaux case

The most extreme case in the French corpus is Pony Bordeaux: 2,996 entries each declaring 12 docks (a nominal 35,952 docks), while the actual mean capacity per entry is 0.03 bike/entry. After A3 reclassification, Bordeaux’s dock-based count collapses from 9,921 raw entries to 225 certified stations — a 98 % collapse, equivalent to a ×52 over-count on any supply-side metric built on the unaudited feed.

Bordeaux dock-based stations before and after the audit
Bordeaux before / after the audit: free-floating anchors published as docks are reclassified, removing a ×52 supply-side over-count.

Quick start

from datasets import load_dataset
gs = load_dataset("rohanfosse/gbfs-audit-catalogue", split="train").to_pandas()

# High-confidence dock-based stations
clean = gs[(gs.station_type == "docked_bike") & (gs.audit_confidence == "high")]
print(len(clean))  # 4,721

# Operator-driven flag hotspots
gs.groupby("operator_name").agg(
    n=("uid", "size"),
    A3_rate=("flag_A3", "mean"),
    A7_rate=("flag_A7", "mean"),
).sort_values("n", ascending=False).head(10)

No-auth alternative, straight from Zenodo:

import pandas as pd
gs = pd.read_parquet(
    "https://zenodo.org/records/20125460/files/stations_gold_standard_final.parquet"
)
Audit status breakdown across the French corpus
Audit verdict across the French corpus: 30.9 % of raw stations removed and a further 61 % relabelled.

Resources

Resource Where
Interactive dashboard gbfs-audit.streamlit.app
Dataset (Hugging Face) rohanfosse/gbfs-audit-catalogue
Zenodo deposit (DOI) 10.5281/zenodo.20125460
Source & audit pipeline github.com/cycling-data-lab/gbfs-audit-catalogue
Reproducible recipes notebooks/catalogue_recipes.ipynb
Human-validation protocol experiments/annotation/PROTOCOL.md
Paper (CSI 2026) Manuscript in preparation; preprint forthcoming

Schema — 46 columns at a glance

FAIR by design. The catalogue ships with machine-readable descriptors — a JSON Schema, a Frictionless Data Package, a DCAT-AP record and a Croissant manifest — plus a Docker image and a 36-test CI suite for byte-level reproducibility.

Citation

@article{Fosse2026gbfs,
  author  = {Foss\'e, Rohan and Pallares, Ga\"el},
  title   = {Auditing GBFS bike-sharing feeds at country and global scale:
             A reproducible anomaly taxonomy for open mobility data},
  journal = {Computer Standards \& Interfaces},
  year    = {2026},
  note    = {Manuscript in preparation; preprint forthcoming}
}

@dataset{Fosse2026gbfsdata,
  author    = {Foss\'e, Rohan and Pallares, Ga\"el},
  title     = {{GBFS Audit Catalogue} v1.0},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.20125460}
}

Licence & contact

Data under ODbL v1.0 · Code under MIT.

Rohan Fossé (lead contact) · rfosse@cesi.fr · CESI École d’Ingénieurs, Montpellier, France. Gaël Pallares · CESI LINEACT (EA 7527), Montpellier, France.

Issues and contributions on GitHub.