generation_settings.toml

[rng]
seed = 0xbafaad6f89daafa

[publication_date]
min = "2020-01-01T01:01:01Z"
max = "2023-01-01T01:01:01Z"
sample_distribution = { type="uniform" }

[publication_date.filters]
has_upper_bound = 0.4
has_lower_bound = 0.8
# Note: the implementation isn't not exactly normal distributed, but close enough to it
upper_bound_sample_distribution = { type="normal", mean="37.5%", std="12.5%" }
lower_bound_sample_distribution = { type="normal", mean="62.5%", std="12.5%" }
# min range of possible valid values in seconds, this applies to `both`
# as much as it does apply to min..upper_bound and lower_bound..max
min_range_len = 86400

[tags]
population = 1000
zipfs_law_pmf = { s= 1 }
property_count_distribution = [0.1, 0.3, 0.25, 0.15, 0.1, 0.05, 0.05]

[tags.filters]
include_count_distribution = [0.3, 0.35, 0.25, 0.1]
exclude_count_distribution = [0.55, 0.275, 0.175]

[authors]
population = 20
zipfs_law_pmf = { s= 1.25 }
property_count_distribution = [0, 0.6, 0.3, 0.1]

[authors.filters]
include_count_distribution = [0.5, 0.26, 0.14]
exclude_count_distribution = [0.60, 0.40]