{"id":"W6947691836","doi":"10.48448/9t3f-dd09","title":"Assessment of Massively Multilingual Sentiment Classifiers","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Fern and Epiphyte Biology","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University; Brandon Regional Health Authority","funders":"","keywords":"Language model; Raw data; Production model; Sentiment analysis; Production (economics); Data collection","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":[],"category_scores_codex":[0.0004908628,0.0002178752,0.0003251443,0.00009312327,0.0002199546,0.00003184665,0.0008229578,0.0001492997,0.01453337],"category_scores_gemma":[0.00004200198,0.00008797006,0.00009714481,0.0006036282,0.00074829,0.00004034204,0.0004034054,0.000246207,0.00003656435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001466614,"about_ca_system_score_gemma":0.0001584155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005103384,"about_ca_topic_score_gemma":0.0006537148,"domain_scores_codex":[0.9979936,0.00007392476,0.0002853965,0.0005972158,0.000629848,0.0004199833],"domain_scores_gemma":[0.9992683,0.00007607338,0.0003328687,0.0001320302,0.00005914773,0.0001315571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002923957,0.001128236,0.02594619,0.00008072504,0.0001596017,0.00004777914,0.0001243877,0.00004893186,0.4817789,0.006876528,0.2276963,0.2560832],"study_design_scores_gemma":[0.0002182718,0.0005109024,0.02955817,0.00003250685,0.00002646779,0.000006316882,0.0008289799,0.001476828,0.0006049815,0.0001144607,0.9662008,0.0004212991],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07820161,0.0004447731,0.00003018542,0.00119982,0.002629396,0.0008820724,0.0007045546,0.0003340224,0.9155736],"genre_scores_gemma":[0.7129317,0.0002146427,0.004038898,0.0006354337,0.0008684354,0.00004543548,0.0007466681,0.00002314936,0.2804957],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7385045,"threshold_uncertainty_score":0.9863675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02596315241912045,"score_gpt":0.2937368588214435,"score_spread":0.2677737064023231,"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."}}