{"id":"W1521350685","doi":"10.16995/dscn.169","title":"Validating choices: Texts in the <i>Trésor de la Langue Française</i>","year":2003,"lang":"fr","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mahalanobis distance; Rank (graph theory); Encyclopedia; Outlier; Field (mathematics); Inclusion (mineral); Humanities; Linguistics; Computer science; History; Library science; Art; Sociology; Artificial intelligence; Mathematics; Philosophy; Social science; Combinatorics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001160137,0.0004883481,0.0006336809,0.0001406798,0.0009501907,0.001105228,0.000404104,0.0001752926,0.0003349919],"category_scores_gemma":[0.001633045,0.0003762083,0.0003559005,0.0002117597,0.0009681371,0.0003640821,0.0001381497,0.0003876904,0.0001218828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256848,"about_ca_system_score_gemma":0.0001533838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009914341,"about_ca_topic_score_gemma":0.009323293,"domain_scores_codex":[0.9973032,0.0004067435,0.0006221671,0.0004950483,0.0003928879,0.0007799076],"domain_scores_gemma":[0.9976658,0.001273319,0.0002415154,0.0004340046,0.0002655273,0.0001198852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001236979,0.0007411043,0.001410328,0.000254143,0.0006194803,0.0002595343,0.4801648,0.000197278,0.00003476948,0.5017372,0.01314294,0.001426081],"study_design_scores_gemma":[0.0004470925,0.0000572647,0.0001142745,0.0002220086,0.000006210182,0.00001432709,0.2495037,0.00006761149,0.0000444704,0.01712853,0.7320054,0.0003890678],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2052593,0.0626146,0.00008428947,0.001705572,0.0005964726,0.0002870495,0.0002743904,0.00005263446,0.7291257],"genre_scores_gemma":[0.9691072,0.003081859,0.00001448641,0.0005254317,0.002081903,0.00009757644,0.00005511693,0.0000607844,0.02497562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7638479,"threshold_uncertainty_score":0.9999317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02636547700497528,"score_gpt":0.275700480275437,"score_spread":0.2493350032704617,"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."}}