{"id":"W2140223269","doi":"10.1109/tsmcb.2009.2036443","title":"A Gradient-Descent-Based Approach for Transparent Linguistic Interface Generation in Fuzzy Models","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Interface (matter); Computer science; Fuzzy logic; Artificial intelligence; Gradient descent; Decision tree; Fuzzy set; Natural language processing; Machine learning; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004917143,0.0004811764,0.0006158114,0.0003009985,0.0002146426,0.0003937776,0.0005758117,0.0002472601,0.000001428523],"category_scores_gemma":[0.000006973741,0.0004645912,0.000192669,0.0003355949,0.00007888525,0.0001674348,0.000003367937,0.0003112693,0.000009616463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001664626,"about_ca_system_score_gemma":0.0000774764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001617957,"about_ca_topic_score_gemma":0.0001136448,"domain_scores_codex":[0.9967384,0.0002294534,0.0009079434,0.0009742664,0.0004833305,0.0006665857],"domain_scores_gemma":[0.9985287,0.0001093934,0.0002009756,0.0007137186,0.0001618721,0.0002853463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001152867,0.0009693005,0.00001452856,0.000182955,0.00006069252,0.00001055549,0.001949153,0.9429473,0.000950806,0.04091095,0.0003851011,0.01150339],"study_design_scores_gemma":[0.002368607,0.0008115769,0.00004167698,0.0001662342,0.00006283612,0.00002156614,0.0001088507,0.9919592,0.001025385,0.00191174,0.0009724902,0.0005498194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006421292,0.001130275,0.9853671,0.0002351484,0.001154333,0.001651914,0.00003963942,0.0001721968,0.003828099],"genre_scores_gemma":[0.9939353,0.000113692,0.004387742,0.000209356,0.00021442,0.0003613491,0.00001605149,0.00003415803,0.0007279581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.987514,"threshold_uncertainty_score":0.9997806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05159735027703299,"score_gpt":0.2537770197502269,"score_spread":0.2021796694731939,"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."}}