{"id":"W6947057813","doi":"10.3886/e117435","title":"Name2Vec: Personal Names Embeddings","year":2020,"lang":"en","type":"dataset","venue":"ICPSR Data Holdings","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Similarity (geometry); Feature (linguistics); Sequence (biology); Table (database); Measure (data warehouse)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","insufficient_payload"],"category_scores_codex":[0.001240571,0.001710013,0.001764874,0.0006756741,0.000435297,0.001183782,0.01051824,0.001087958,0.005488573],"category_scores_gemma":[0.002980767,0.001811486,0.0003627111,0.001352792,0.0006960513,0.002081746,0.008310958,0.002956686,0.1253051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004496144,"about_ca_system_score_gemma":0.0005962729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00122938,"about_ca_topic_score_gemma":0.0001571598,"domain_scores_codex":[0.9906007,0.0002013109,0.001149547,0.003938448,0.002468609,0.001641386],"domain_scores_gemma":[0.9906273,0.0003417207,0.001250557,0.006628475,0.0002162,0.0009357648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001364536,0.0001509953,0.00002060174,0.0004683129,0.0004563107,0.0005812093,0.0002223379,4.821455e-7,0.0002952528,0.00002038493,0.9972146,0.0004330465],"study_design_scores_gemma":[0.0008781566,0.0001223149,0.00003050704,0.0004588269,0.0008007951,0.0002274871,0.0001957564,0.0003849561,0.00004748304,0.00004044819,0.9948944,0.001918909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000158516,0.001102944,0.000005463257,0.0007107835,0.00134297,0.0007371629,0.9949679,0.0008296826,0.000144605],"genre_scores_gemma":[0.00007652288,0.0006292984,0.0008107987,0.002468531,0.002708264,0.00007143096,0.992402,0.000519741,0.0003134495],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1198166,"threshold_uncertainty_score":0.9998531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07990810867150173,"score_gpt":0.328509639310023,"score_spread":0.2486015306385213,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}