{"id":"W1982086232","doi":"10.5539/ass.v11n5p193","title":"Validity of Teacher-Made Assessment: A Table of Specification Approach","year":2015,"lang":"en","type":"article","venue":"Asian Social Science","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Table (database); Mathematics education; Content validity; Test (biology); Process (computing); Table of contents; Computer science; Psychology; Psychometrics; Programming language; Database; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1683748,0.0009037912,0.001912066,0.008114302,0.002782835,0.005664333,0.003272356,0.001010671,0.002059008],"category_scores_gemma":[0.3728194,0.000875391,0.002851923,0.007210362,0.006280655,0.006586339,0.005114457,0.002125242,0.000449097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008120906,"about_ca_system_score_gemma":0.009910394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01108936,"about_ca_topic_score_gemma":0.01288252,"domain_scores_codex":[0.6987628,0.1913858,0.0314418,0.01215641,0.06356814,0.00268506],"domain_scores_gemma":[0.4384334,0.363034,0.04947596,0.06086822,0.08581488,0.002373645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009135737,0.0005991954,0.5362588,0.002163447,0.000886816,0.0002443766,0.05156701,0.005010929,0.003428236,0.03882328,0.003155248,0.356949],"study_design_scores_gemma":[0.0005395476,0.003214759,0.6271228,0.004898478,0.0008403148,0.00113148,0.06521939,0.129087,0.01444127,0.1009174,0.05167526,0.000912321],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.484937,0.001017208,0.4696104,0.0018742,0.0004184502,0.005710416,0.001090942,0.0006307552,0.03471075],"genre_scores_gemma":[0.8858366,0.0002457878,0.1089034,0.0001836608,0.0000454552,0.003125482,0.0005381644,0.000108164,0.00101329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1683748,"threshold_uncertainty_score":0.8904617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1325012978466284,"score_gpt":0.3295369606647536,"score_spread":0.1970356628181252,"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."}}