{"id":"W210886163","doi":"","title":"Users' Manual and Validation of the Automated Grading System (AGS): Improving the Quality of Intelligence Summaries Using Feedback from an Unsupervised Model of Semantics","year":2012,"lang":"en","type":"article","venue":"","topic":"Education and Critical Thinking Development","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Computer science; Quality (philosophy); World Wide Web; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03688172,0.001114936,0.0009844993,0.002587678,0.0009290707,0.001985902,0.001641946,0.001253823,0.005774606],"category_scores_gemma":[0.1906239,0.0004538902,0.0004956182,0.0009653535,0.0007373962,0.001777566,0.001938534,0.001166387,0.003544413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094816,"about_ca_system_score_gemma":0.001539766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001790602,"about_ca_topic_score_gemma":0.00275353,"domain_scores_codex":[0.9737632,0.01517343,0.003794599,0.002816986,0.00404479,0.0004070034],"domain_scores_gemma":[0.7285388,0.1640123,0.007065257,0.03164075,0.06560747,0.003135396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002366685,0.002475278,0.06738037,0.001467786,0.0001419748,0.0008903288,0.02683442,0.004977572,0.07894385,0.001400118,0.04592586,0.7671958],"study_design_scores_gemma":[0.001764763,0.008265922,0.1985907,0.001136501,0.0004335647,0.002577542,0.01322142,0.3494059,0.2648339,0.004690139,0.1540287,0.001050981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8146762,0.0002113816,0.1454689,0.0009816943,0.0003463699,0.003146576,0.003194253,0.02660154,0.005373104],"genre_scores_gemma":[0.7768075,0.00009268078,0.2108159,0.0002942131,0.00009360636,0.001680624,0.003649521,0.001536245,0.005029669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03688172,"threshold_uncertainty_score":0.1950515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1075121874280076,"score_gpt":0.3840478494527516,"score_spread":0.276535662024744,"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."}}