{"id":"W4393657389","doi":"10.5281/zenodo.8170023","title":"OpenAlex Author Name Disambiguation V3 Initial Clusters","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"OpenAlex","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001857242,0.003640133,0.001806304,0.007164037,0.002664335,0.004455758,0.003509905,0.002666512,0.04799856],"category_scores_gemma":[0.006570139,0.00089968,0.002405641,0.007104338,0.0009174796,0.002225813,0.003758491,0.002618901,0.09963918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002312308,"about_ca_system_score_gemma":0.004397653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01506908,"about_ca_topic_score_gemma":0.0351503,"domain_scores_codex":[0.9973848,0.0003093036,0.0002661885,0.001052672,0.0005376166,0.0004492884],"domain_scores_gemma":[0.9973409,0.0005803564,0.0001722235,0.0008248708,0.0008122645,0.0002693899],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001759253,0.00005992012,0.001295723,0.0005675721,0.00003882631,0.00007352728,0.00008880008,0.0005129344,0.0005224952,0.001277793,0.9878292,0.007557252],"study_design_scores_gemma":[0.0002205354,0.00002646285,0.002980381,0.0002255384,0.0000533539,0.00015641,0.0002720049,0.001479119,0.002212759,0.002808776,0.9895139,0.00005075813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001812901,0.0002641094,0.001161667,0.0001601111,0.0001220653,0.0001302329,0.9869408,0.005344713,0.004063274],"genre_scores_gemma":[0.0009938566,0.00005813565,0.002697687,0.00005168325,0.00001403851,0.0001839737,0.9943075,0.0003420744,0.001351138],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9981428,"threshold_uncertainty_score":0.1605712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06265774508346136,"score_gpt":0.3217900060954892,"score_spread":0.2591322610120278,"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."}}