{"id":"W2165960383","doi":"10.1177/2158244014564359","title":"Pair Tests in a High School Classroom","year":2014,"lang":"en","type":"article","venue":"SAGE Open","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Laziness; Psychology; Test (biology); Quarter (Canadian coin); Mathematics education; Social psychology; Outcome (game theory); Developmental psychology; Mathematics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004236316,0.0001148395,0.0002163217,0.000113568,0.00008148613,0.00007673074,0.0005184729,0.0001063859,0.003334251],"category_scores_gemma":[0.0009139481,0.0001034472,0.00002432649,0.0003231364,0.00003565978,0.0000928298,0.0001589347,0.0006348715,0.00171802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004254034,"about_ca_system_score_gemma":0.00002763915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00165714,"about_ca_topic_score_gemma":0.0001210481,"domain_scores_codex":[0.9969984,0.002101172,0.000209249,0.0003162313,0.0000859291,0.000289073],"domain_scores_gemma":[0.9990709,0.0003297609,0.00008155821,0.0004388186,0.00002351439,0.00005540123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001089526,0.0002219851,0.5632498,0.000008632406,0.00003368811,0.00003441096,0.002630098,0.00001200083,0.0009601011,0.03316592,0.02439619,0.3751783],"study_design_scores_gemma":[0.001037327,0.0001186894,0.8215489,0.00004513541,0.000003166709,0.000003959479,0.0001535633,0.00002134867,0.00003036954,0.003663369,0.1732332,0.0001409399],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6571647,0.00004162521,0.008769474,0.001254847,0.0008226785,0.0003179614,0.000001991452,0.00008769132,0.3315391],"genre_scores_gemma":[0.9336156,3.171847e-7,0.01114538,0.001278867,0.0001697918,0.00005442287,0.000006991667,0.00002538995,0.05370326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3750373,"threshold_uncertainty_score":0.9990593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04504724705469564,"score_gpt":0.3990480030120761,"score_spread":0.3540007559573805,"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."}}