{"id":"W4406847525","doi":"10.1108/dta-08-2023-0461","title":"PyBibX – a Python library for bibliometric and scientometric analysis powered with artificial intelligence tools","year":2025,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Python (programming language); Computer science; Data science; Library science; Information retrieval; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.001756044,0.0001105433,0.0002256129,0.04976706,0.0004460136,0.002260415,0.002328417,0.00005940105,0.0000130077],"category_scores_gemma":[0.002186811,0.00007622463,0.00002993829,0.2691374,0.0003833373,0.0007162714,0.002923511,0.00007612854,0.000008354261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007122785,"about_ca_system_score_gemma":0.00003827901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001104709,"about_ca_topic_score_gemma":0.0000139085,"domain_scores_codex":[0.9977834,0.00001663245,0.0003957158,0.001179775,0.0004084214,0.0002160289],"domain_scores_gemma":[0.995607,0.001485944,0.000149239,0.002601413,0.0001160449,0.00004037493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008773592,0.00004081311,0.002703055,0.000006667351,0.00004814105,2.777053e-7,0.00000484348,0.00001784724,0.000006200319,0.06385104,0.01084452,0.9224678],"study_design_scores_gemma":[0.0001119075,0.00008788495,0.0185798,0.00001490672,0.0003021942,0.000002189615,0.00497536,0.05117306,0.0003181325,0.1801404,0.7440264,0.0002677554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01220815,0.001456134,0.9784138,0.00413221,0.0000524795,0.0007418699,0.001887665,0.0004673889,0.0006403676],"genre_scores_gemma":[0.9184149,0.000794221,0.07858814,0.0001252752,0.00001940097,0.0002923842,0.001017473,0.00000860683,0.00073962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9222001,"threshold_uncertainty_score":0.9987754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2671937743618359,"score_gpt":0.4353138810715237,"score_spread":0.1681201067096878,"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."}}