{"name":"A dataset of mentorship in science with semantic and demographic estimations","description":"An open dataset connecting academic mentorship relationships with researcher profiles, publication identifiers, semantic representations, and demographic estimates. It enriches Academic Family Tree records with publication information and supports research on mentorship and scientific careers, with strongest coverage and validation in neuroscience and biomedical science.","date_published":"2021-06-09","doi":"10.5281/zenodo.4917086","url":"https://zenodo.org/records/4917086","license":"https://creativecommons.org/licenses/by/4.0/","creators":["Qing Ke","Lizhen Liang","Ying Ding","Stephen V. David","Daniel E. Acuna"],"paper_key":"keacuna2022","citation":"Qing Ke, Lizhen Liang, Ying Ding, Stephen V. David, Daniel E. Acuna (2021). A dataset of mentorship in science with semantic and demographic estimations. Zenodo. https://doi.org/10.5281/zenodo.4917086","files":[{"name":"mentorship.csv.gz","bytes":9241433,"size_label":"8.8 MiB","url":"https://zenodo.org/api/records/4917086/files/mentorship.csv.gz/content","encoding_format":"application/gzip","checksum":"md5:d7705f165a3d1d12581881da7dc73f39"},{"name":"researcher.csv.gz","bytes":17197433,"size_label":"16.4 MiB","url":"https://zenodo.org/api/records/4917086/files/researcher.csv.gz/content","encoding_format":"application/gzip","checksum":"md5:768abce0e3d99af2137f84e92cf2065e"},{"name":"authorship.csv.gz","bytes":152763699,"size_label":"145.7 MiB","url":"https://zenodo.org/api/records/4917086/files/authorship.csv.gz/content","encoding_format":"application/gzip","checksum":"md5:963086e49f1a2b13af6bb4fa801bbd4a"},{"name":"paper.csv.gz","bytes":269560048,"size_label":"257.1 MiB","url":"https://zenodo.org/api/records/4917086/files/paper.csv.gz/content","encoding_format":"application/gzip","checksum":"md5:5a62108126faa60fba73b493136be22f"},{"name":"first_name_gender.csv","bytes":1349828,"size_label":"1.3 MiB","url":"https://zenodo.org/api/records/4917086/files/first_name_gender.csv/content","encoding_format":"text/csv","checksum":"md5:fbd96e1c72fd60fa3acdcd4feb17f514"},{"name":"full_name_race.csv","bytes":17014612,"size_label":"16.2 MiB","url":"https://zenodo.org/api/records/4917086/files/full_name_race.csv/content","encoding_format":"text/csv","checksum":"md5:fc188628ee3a2a615e0f1384e02057e4"},{"name":"paper_specter_0.pkl","bytes":5361370327,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_0.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:780736d954e2fd16c89880c134f7f59c"},{"name":"paper_specter_1.pkl","bytes":5355729088,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_1.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:e83bb0bf4bdcc0b3061e9fa68533f31f"},{"name":"paper_specter_2.pkl","bytes":5356320195,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_2.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:425372fb4af0d4cf394fa5d2a2c9e6a2"},{"name":"paper_specter_3.pkl","bytes":5355804952,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_3.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:ad4b3a9a781f940814b6d2dcb922258f"},{"name":"paper_specter_4.pkl","bytes":5356835438,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_4.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:5baf04c8469f8baa67498e6c35b69fbd"},{"name":"paper_specter_5.pkl","bytes":5356481406,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_5.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:99e4b147fd2c8962534e02835313993b"},{"name":"paper_specter_6.pkl","bytes":5352956891,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_6.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:3e1c9a6319a25988f30f940781b10488"},{"name":"paper_specter_7.pkl","bytes":5352978947,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_7.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:ad6e1ad80ecb3bc84f8a199161afea49"},{"name":"paper_specter_8.pkl","bytes":5355143660,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_8.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:f75a20cb8394e481968a857f83937561"},{"name":"paper_specter_9.pkl","bytes":5355125215,"size_label":"5.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_specter_9.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:73806c3f0f6413942adb269b71029b1a"},{"name":"paper_tfidf.npz","bytes":9628723417,"size_label":"9.0 GiB","url":"https://zenodo.org/api/records/4917086/files/paper_tfidf.npz/content","encoding_format":"application/octet-stream","checksum":"md5:37e8d6fedaba50e8357958498e9409e2"},{"name":"paper_tfidf_MAGPaperID.txt.gz","bytes":52536785,"size_label":"50.1 MiB","url":"https://zenodo.org/api/records/4917086/files/paper_tfidf_MAGPaperID.txt.gz/content","encoding_format":"application/gzip","checksum":"md5:7c54a5e017357d74425be40a272b9b63"},{"name":"researcher_neighbor_specter.csv.gz","bytes":41696623,"size_label":"39.8 MiB","url":"https://zenodo.org/api/records/4917086/files/researcher_neighbor_specter.csv.gz/content","encoding_format":"application/gzip","checksum":"md5:8ec1ac47b1ce5f9717ce60e5fb9b9f89"},{"name":"researcher_specter.pkl","bytes":1561077353,"size_label":"1.5 GiB","url":"https://zenodo.org/api/records/4917086/files/researcher_specter.pkl/content","encoding_format":"application/octet-stream","checksum":"md5:bbc3f5358014db0c342ccba7d981d5d4"},{"name":"researcher_tfidf.npz","bytes":5112564519,"size_label":"4.8 GiB","url":"https://zenodo.org/api/records/4917086/files/researcher_tfidf.npz/content","encoding_format":"application/octet-stream","checksum":"md5:81e7d7755c6e66fa2fa8c5d60de95356"},{"name":"researcher_tfidf_PID.txt.gz","bytes":1148561,"size_label":"1.1 MiB","url":"https://zenodo.org/api/records/4917086/files/researcher_tfidf_PID.txt.gz/content","encoding_format":"application/gzip","checksum":"md5:184f48cc30f2f6d21de92c24ee63b7ef"}],"csv_columns":{"mentorship.csv.gz":["CID","MenteeID","MentorID","MentorshipType","Institution","InstitutionMAGID","StartYear","StopYear"],"researcher.csv.gz":["PID","FirstName","MiddleName","LastName","Institution","InstitutionMAGID","ResearchArea","ORCID","MAGAuthorID"],"authorship.csv.gz":["PID","MAGPaperID"],"paper.csv.gz":["MAGPaperID","DOI","PMID"]}}
