JoaquinVanschoren commited on
Commit
e76200d
·
1 Parent(s): b5d447a

license clarification

Browse files
Files changed (1) hide show
  1. validation.py +6 -6
validation.py CHANGED
@@ -60,12 +60,12 @@ def validate_croissant(json_data):
60
  missing = [f for f in REQUIRED_SCHEMA_FIELDS if not json_data.get(f)]
61
  if missing:
62
  return True, (
63
- "The dataset passes Croissant schema validation, but the `license` field is missing. "
64
- "Please add a `license` field to your Croissant file. "
65
- "Croissant recommends using the URL of a known license, e.g. one of the licenses listed at "
66
- "<a href='https://spdx.org/licenses/' target='_blank'>https://spdx.org/licenses/</a>. "
67
- "Note that if your paper is accepted at NeurIPS, a permissive license will be required."
68
- ), "warning"
69
  return True, "The dataset passes Croissant validation.", "pass"
70
  except mlc.ValidationError as e:
71
  error_details = traceback.format_exc()
 
60
  missing = [f for f in REQUIRED_SCHEMA_FIELDS if not json_data.get(f)]
61
  if missing:
62
  return True, (
63
+ "The `license` field is missing. This is required for NeurIPS dataset submissions. "
64
+ "Please add a `license` field to your Croissant file with the name or URL of the licence governing your dataset. "
65
+ "Where possible, use <a href='https://www.kaggle.com/discussions/getting-started/116476' target='_blank'>open licenses</a> that "
66
+ "allow reuse and reproducibility. However, when the dataset contains sensitive data or stricter licensing is unavoidable, "
67
+ "please select an appropriate license that is as open as possible given the constraints."
68
+ ), "error"
69
  return True, "The dataset passes Croissant validation.", "pass"
70
  except mlc.ValidationError as e:
71
  error_details = traceback.format_exc()