{"id":"W7098511277","doi":"","title":"Level and Extraneous Information in Determining Word Problem Difficulty: Steps Toward Individual Assessment","year":2016,"lang":"en","type":"article","venue":"","topic":"Marine Invertebrate Physiology and Ecology","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vocabulary; Word (group theory); Set (abstract data type); Consistency (knowledge bases); Sample (material); Task (project management); Reading (process)","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":[0.004957564,0.0007967087,0.0006179771,0.00359487,0.0007536957,0.002209025,0.001088879,0.0007549108,0.001414501],"category_scores_gemma":[0.01507668,0.0005225604,0.0003888621,0.001480519,0.0009845837,0.001127318,0.001763716,0.001071806,0.0004766129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006669292,"about_ca_system_score_gemma":0.001896676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0349905,"about_ca_topic_score_gemma":0.09241163,"domain_scores_codex":[0.9971585,0.0005620832,0.0003883424,0.0003174337,0.001300712,0.0002729785],"domain_scores_gemma":[0.9888006,0.003954619,0.001946126,0.0008184094,0.003578158,0.0009020375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001962866,0.000617868,0.9534917,0.00008515613,0.0000915963,0.00007407897,0.005329098,0.000283046,0.004048455,0.0001096715,0.0002051362,0.03546798],"study_design_scores_gemma":[0.00001839189,0.0003780608,0.9923694,0.00001962081,0.00003192298,0.00007448929,0.002703095,0.001792203,0.001772097,0.0002381808,0.0005761573,0.00002637342],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962072,0.00007596146,0.001660968,0.00003623049,0.000004148231,0.0002882632,0.000123634,0.00002682943,0.001576754],"genre_scores_gemma":[0.9902298,0.000108949,0.007946918,0.00002551204,0.00000558612,0.000231796,0.0003481635,0.0000111787,0.001092175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0349905,"threshold_uncertainty_score":0.06957364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0327489744599293,"score_gpt":0.2298553630061239,"score_spread":0.1971063885461946,"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."}}