{"id":"W4398274863","doi":"10.7910/dvn/k0oyqf/hiqwhn","title":"canada200","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Word (group theory); Ideology; Linguistics; Word length; Natural language processing; Computer science; Political science; Philosophy; Politics; 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008059096,0.0001600522,0.0002842152,0.0001641464,0.0003053601,0.0001198638,0.0007196394,0.0001960616,0.1010012],"category_scores_gemma":[0.0004425209,0.0001612647,0.0001333045,0.0003049223,0.0001251423,0.0001564768,0.0001683657,0.000243583,0.1582736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001704633,"about_ca_system_score_gemma":0.0009880489,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.09514435,"about_ca_topic_score_gemma":0.08780655,"domain_scores_codex":[0.9981202,0.0003505949,0.0002050467,0.0003382018,0.0006896367,0.0002963264],"domain_scores_gemma":[0.9986914,0.0002954892,0.0001475125,0.0005947888,0.0001066523,0.0001641951],"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":[0.000003877338,0.00001797714,0.000006524013,0.00001526372,0.00005765294,0.00002323002,0.00005949082,0.00001980541,1.617129e-7,0.0004448011,0.9985247,0.0008265429],"study_design_scores_gemma":[0.00008325229,0.000005958585,0.00002688638,0.00001656221,0.0001160259,6.696395e-7,0.0001607671,0.00001719207,1.622261e-7,0.0001946594,0.9991738,0.0002040603],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000002548273,0.000001406892,0.00008941775,0.00003333945,0.001141572,0.0001405257,0.9931445,0.0000212539,0.00542551],"genre_scores_gemma":[0.0000046512,0.0002075864,0.0004995103,0.0004878061,0.0006423169,0.000005435642,0.990176,0.000007332507,0.007969365],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05727241,"threshold_uncertainty_score":0.9288386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04332124749979459,"score_gpt":0.3451813906196236,"score_spread":0.3018601431198289,"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."}}