{"id":"W2058821124","doi":"10.3758/brm.40.2.428","title":"Comparing online and lab methods in a problem-solving experiment","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":216,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Psychology; Mathematics education","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":[],"consensus_categories":[],"category_scores_codex":[0.01938509,0.0001389739,0.0003410794,0.0004576694,0.0009581465,0.00009627462,0.0003498807,0.0001410852,0.0001603713],"category_scores_gemma":[0.0015332,0.0001333617,0.00005564353,0.001042793,0.0006367282,0.0002575383,0.0003488853,0.001033688,0.000005261613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002341441,"about_ca_system_score_gemma":0.0005587364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005012541,"about_ca_topic_score_gemma":0.001482034,"domain_scores_codex":[0.9876562,0.009925307,0.0003656284,0.0004568877,0.0007230553,0.0008729575],"domain_scores_gemma":[0.9978076,0.001414259,0.00006170811,0.0002452013,0.0001979978,0.0002732745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003189087,0.0006802698,0.1455212,0.00002672267,0.00001008942,0.0001433061,0.03344533,0.000009838343,0.05152101,0.001734267,0.0001378747,0.7667382],"study_design_scores_gemma":[0.002755153,0.0006125722,0.3357007,0.0003921344,0.00004264766,0.00007443967,0.1422314,0.001888453,0.02632296,0.002081225,0.486652,0.001246289],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9835528,0.001754782,0.005228939,0.0007579337,0.00009796155,0.0007521693,0.000001637165,0.00009346843,0.00776027],"genre_scores_gemma":[0.1122124,0.0005771697,0.885247,0.00001309145,0.0001563042,0.0001276404,0.000003664533,0.00002284534,0.001639929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8800181,"threshold_uncertainty_score":0.7577496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4997630286426059,"score_gpt":0.6502886072233989,"score_spread":0.150525578580793,"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."}}