{"id":"W2081301917","doi":"10.2501/s1470785309201314","title":"How far can you rely on a concept test: the generalizability of testing over occasions","year":2011,"lang":"en","type":"article","venue":"International Journal of Market Research","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalizability theory; Test (biology); Business; Marketing; Computer science; Psychology","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01500837,0.0001139012,0.0002657061,0.0006019664,0.0001588305,0.00038651,0.002719983,0.00007552936,0.001134695],"category_scores_gemma":[0.05037899,0.00006387057,0.0002193832,0.0005380381,0.0004567417,0.0002451717,0.0003994959,0.0006527717,0.00001541842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001843073,"about_ca_system_score_gemma":0.0004000783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000230975,"about_ca_topic_score_gemma":0.00005891182,"domain_scores_codex":[0.9943852,0.0007762732,0.0009417428,0.000277375,0.003364023,0.0002554253],"domain_scores_gemma":[0.9816861,0.01180188,0.000749776,0.0005477527,0.005057895,0.0001566611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008151036,0.0007806218,0.2288564,0.000002154633,0.00008372004,0.0002404578,0.001910601,0.00008939919,0.002230249,0.001073054,0.05487855,0.7090397],"study_design_scores_gemma":[0.002007872,0.002611427,0.7023372,0.0003478221,0.00003267442,0.0006268969,0.006929062,0.003359734,0.004735124,0.2040039,0.07262498,0.0003833248],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834252,0.00005904812,0.0001213898,0.004452618,0.000754819,0.0001085206,0.00007145559,0.000004038364,0.0110029],"genre_scores_gemma":[0.9961579,0.0000243534,0.001422661,0.0001307103,0.0002383243,0.000002534045,5.168442e-7,0.000009907524,0.002013096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7086564,"threshold_uncertainty_score":0.9997784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.559281526593081,"score_gpt":0.5036483420894333,"score_spread":0.05563318450364763,"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."}}