Table 2. Descriptions of all the explanatory features.

Feature	Description
gender	is the gender of the author in question as predicted by Genni 2.0 [27, 34, 35]. Each author is labeled as one of the following: Female, Male, or Unknown.
age(pub count)	is the age of the author as measured by the number of papers published in the years prior to the article in question.
ethnicity	is the ethnicity of the author as predicted by Ethnea [34]. Each author can have one (or a mixture of two, equally weighted) of the following ethnicities: ARAB, CHINESE, DUTCH, ENGLISH, FRENCH, GERMAN, HISPANIC, INDIAN, ITALIAN, JAPANESE, KOREAN, NORDIC, OTHER, SLAV, and UNKNOWN.
country	is the country of affiliation of the first-listed author on the article in question, as inferred by MapAffil [41, 42]. Each article is assigned one of the following countries: Australia, Canada, China, France, Germany, India, Italy, Japan, Netherlands, Other, Spain, Sweden, UK, Unknown, or USA.
collabortion size	is the number of authors on the article in question, capped at 20.
language	is 1 if the article was written in English as tagged in MEDLINE [43], 0 otherwise.
reference count	is the total number of references listed on the article in question.
MeSH count	is the number of MeSH terms (and all their unique ancestors in the MeSH tree structure) as assigned in MEDLINE.
novelty score	is the number of prior papers for the youngest MeSH term assigned to the article in question (the so-called “volume novelty” in [44, 45]).
pub type	is the publication type(s) of the referenced article as tagged in MEDLINE [43]. Each article can have one or more of following: “journal article”, “case report”, “review article”, and “letter/editorial/comment”.
venue	is encoded by indicating whether the article and its reference were published in the same or similar journal as captured by the exact name match and the implicit journal score [46] which is similar to author odds ratio [47].
timelag	is the difference in publication years between the articles in question and its reference
ref. language	is 1 if the referenced article was written in English as tagged in MEDLINE [43], 0 otherwise.
ref. citation count	is the number of citations received by the referenced article prior to the citation in question.
ref. MeSH count	is the number of MeSH terms (and all their unique ancestors in the MeSH tree structure) assigned to the referenced article.
ref. novelty score	is the number of prior papers for the youngest MeSH term assigned to the referenced article (the so-called “volume novelty” in [44, 45]).
ref. pub type	is the publication type of the referenced article as tagged in MEDLINE [43]. Each article can have one or more of following: “journal article”, “case report”, “review article”, and “letter/editorial/comment”.