{"id":"W6891749672","doi":"10.48448/cy45-tk72","title":"BLP-2023 Task 2: Sentiment Analysis","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Sentiment analysis; Matching (statistics); Feature (linguistics); Focus (optics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002957494,0.007180678,0.002151586,0.002999603,0.002258285,0.003064259,0.002701175,0.005661074,0.06949686],"category_scores_gemma":[0.009610773,0.0009172069,0.00326107,0.002623735,0.0006551382,0.003248646,0.005263001,0.003973732,0.1040731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00156538,"about_ca_system_score_gemma":0.002858406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01795326,"about_ca_topic_score_gemma":0.0333193,"domain_scores_codex":[0.996595,0.0009733077,0.0002608561,0.0007581762,0.0009248751,0.0004877399],"domain_scores_gemma":[0.9959565,0.00132242,0.0002423071,0.0007474147,0.001136383,0.000594954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003803516,0.0001989365,0.0006712427,0.0005712142,0.0000680856,0.000131582,0.00006304099,0.0005586579,0.002899797,0.0006329377,0.9622236,0.03160039],"study_design_scores_gemma":[0.001456713,0.00054205,0.01495878,0.0004151415,0.0002952614,0.0008704574,0.0006188334,0.04561246,0.02071686,0.01020254,0.9040297,0.000281325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0227758,0.001853395,0.02410848,0.002660811,0.0034638,0.001840339,0.8427136,0.05672735,0.04385639],"genre_scores_gemma":[0.01863048,0.0002238562,0.02586756,0.0007653212,0.000365064,0.001334084,0.925258,0.002543564,0.02501206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06949686,"threshold_uncertainty_score":0.2324902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03800800714268091,"score_gpt":0.340366844813951,"score_spread":0.3023588376712701,"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."}}