{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006893787,0.0002346093,0.0002141207,0.0001817211,0.001048653,0.0004422736,0.001291434,0.0004071966,0.001372124],"category_scores_gemma":[0.001879127,0.0002362113,0.00009531031,0.0002883919,0.000316669,0.000007946923,0.002014819,0.0003943184,0.01635028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006118952,"about_ca_system_score_gemma":0.0000130489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005549262,"about_ca_topic_score_gemma":0.000003720126,"domain_scores_codex":[0.9978956,0.0003699638,0.0003097515,0.0006267923,0.0003919791,0.0004059215],"domain_scores_gemma":[0.9987109,0.00002003843,0.0001622603,0.0006570636,0.0002673269,0.0001824155],"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":[0.00007607058,0.00005992702,1.066738e-7,0.00008365919,0.00007136358,0.00001782999,0.00004275102,0.000007700502,0.00054819,0.000008166114,0.9546582,0.04442602],"study_design_scores_gemma":[0.0004005542,0.0004502436,0.00005300306,0.00005297345,0.00003311898,0.00005634292,0.0001262668,0.00003297317,0.000163943,0.00002180918,0.998336,0.0002728046],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000667042,0.0001778434,0.0009859981,0.0009908095,0.0006086834,0.0004450352,0.9935439,0.000602184,0.001978535],"genre_scores_gemma":[0.0007708496,0.0002914726,0.000112462,0.0002229609,0.0006382944,1.699122e-7,0.9955772,0.001005197,0.001381381],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04415321,"threshold_uncertainty_score":0.9995407,"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."}}