{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01023296,0.0008713976,0.0009237583,0.0007815724,0.0006767936,0.001562139,0.001475965,0.001373827,0.005161557],"category_scores_gemma":[0.04148995,0.0004595437,0.0003801351,0.0005892377,0.0006786809,0.001900766,0.001429091,0.001417594,0.0009578688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006937185,"about_ca_system_score_gemma":0.001441833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001051311,"about_ca_topic_score_gemma":0.001033291,"domain_scores_codex":[0.9923238,0.004916586,0.0005784365,0.0008984111,0.0009852457,0.0002975281],"domain_scores_gemma":[0.9275929,0.05892638,0.003091718,0.004608953,0.003223296,0.002556584],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.08310872,0.3315613,0.03326537,0.001269828,0.0005819889,0.0001280192,0.01155604,0.006656519,0.08541422,0.004448626,0.002040448,0.4399689],"study_design_scores_gemma":[0.06061847,0.4263601,0.2145348,0.0006427774,0.001972226,0.0005378131,0.008521731,0.1077566,0.1360683,0.02075161,0.02155534,0.000680124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774595,0.0001017854,0.0164277,0.0001186267,0.000107375,0.001493153,0.0001292071,0.0001645947,0.003998203],"genre_scores_gemma":[0.9160045,0.0002787626,0.06417558,0.0002875287,0.0001403586,0.009024268,0.0003253238,0.0001756388,0.009588078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.989767,"threshold_uncertainty_score":0.05411768,"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."}}