{"id":"W4393520745","doi":"10.5281/zenodo.8200678","title":"OpenAlex Author Name Disambiguation V3 Data - Disambiguation Model","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"OpenAlex","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.01275534,0.000398017,0.000502179,0.0009634974,0.003015762,0.006330061,0.01234599,0.0002548854,0.009475511],"category_scores_gemma":[0.01873715,0.000377501,0.0001164144,0.00190382,0.0003001968,0.001848524,0.01757186,0.000672679,0.2168645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002607848,"about_ca_system_score_gemma":0.00002475904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002941412,"about_ca_topic_score_gemma":0.00003037807,"domain_scores_codex":[0.9910929,0.00154502,0.001250993,0.001963944,0.003506051,0.0006410451],"domain_scores_gemma":[0.9921137,0.0002933149,0.0007453348,0.005480812,0.001038053,0.0003287761],"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":[0.00004734028,0.0001652099,6.57782e-8,0.00007767517,0.0000609928,0.00001319879,0.000177099,0.0007329917,0.00001115151,0.001098673,0.920554,0.07706162],"study_design_scores_gemma":[0.0003631945,0.00009696136,0.00005832705,0.00006346629,0.00007802695,0.00001123763,0.0004137556,0.02674541,0.000002411536,0.003454411,0.9682992,0.0004135899],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002394333,0.00003826809,0.02561487,0.003006418,0.0005483415,0.0009727594,0.9650159,0.000954895,0.00382463],"genre_scores_gemma":[0.000192097,0.0002539574,0.0003070444,0.0003555971,0.0003213033,2.561356e-7,0.9898431,0.001282184,0.007444424],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.207389,"threshold_uncertainty_score":0.9998677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4820321125774946,"score_gpt":0.4447693692728105,"score_spread":0.03726274330468415,"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."}}