{"id":"W4386195873","doi":"10.1038/s41597-023-02464-w","title":"Digitization of the Australian Parliamentary Debates, 1998–2022","year":2023,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Parliament; Digitization; Democracy; Politics; Resource (disambiguation); Metadata; Public administration; Political science; Library science; Data science; Sociology; Computer science; World Wide Web; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388746,0.00004001475,0.00006696925,0.00008702769,0.0006485545,0.0001693393,0.001111581,0.00001899168,0.0002568204],"category_scores_gemma":[0.000318496,0.00002942094,0.00003921601,0.002271165,0.0004142191,0.0002771103,0.0004464118,0.00004048905,0.0001132402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002048496,"about_ca_system_score_gemma":0.0001481713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001162656,"about_ca_topic_score_gemma":0.003101329,"domain_scores_codex":[0.9986581,0.0001939466,0.0001511343,0.0002698883,0.0005746857,0.0001522302],"domain_scores_gemma":[0.999097,0.0001314794,0.00007734422,0.0006032853,0.00004855926,0.00004231635],"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":[0.000003287956,0.00006938203,0.01764892,0.00001638147,0.00004983856,0.00000194013,0.004267078,0.0005725826,0.0008582532,0.009724496,0.8402878,0.1265],"study_design_scores_gemma":[0.00006114523,0.000002551475,0.02103295,0.00001490801,0.00002846165,1.50146e-7,0.002669055,0.003471258,0.0002728305,0.0169553,0.9554183,0.00007302235],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9001688,0.0002801362,0.004541974,0.0408754,0.01896161,0.00131442,0.009591341,0.0006024262,0.02366385],"genre_scores_gemma":[0.9436088,0.00001919486,0.000835467,0.00007648394,0.0001598047,0.000004064449,0.004276157,0.000006145891,0.05101386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.126427,"threshold_uncertainty_score":0.4988223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1295125417729573,"score_gpt":0.39690934396953,"score_spread":0.2673968021965727,"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."}}