{"id":"W1511980079","doi":"10.1023/a:1021855607270","title":"Categorisation Techniques in Computer-Assisted Reading and Analysis of Texts (CARAT) in the Humanities","year":2003,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Computational linguistics; Set (abstract data type); Process (computing); Reading (process); Natural language processing; Linguistics; Artificial intelligence; Programming language; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.001032652,0.0001849651,0.0004686904,0.0008025924,0.0002939784,0.0004800591,0.0005541028,0.00004982841,0.000001129417],"category_scores_gemma":[0.00001853167,0.0001216295,0.00009146371,0.0008463205,0.0006496895,0.0004101965,0.0001713422,0.0001681917,1.610371e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004154248,"about_ca_system_score_gemma":0.00002043265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003873609,"about_ca_topic_score_gemma":0.0007966632,"domain_scores_codex":[0.9984226,0.0004440607,0.0004349511,0.0002997653,0.0002039484,0.0001946539],"domain_scores_gemma":[0.9986882,0.0005810377,0.0002071128,0.0004466796,0.00006671535,0.00001029583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007973164,0.00005181447,0.002556195,0.0000248277,0.0001284309,0.000008596936,0.02260356,0.0001352445,0.00002823,0.9476224,0.00004300149,0.02678978],"study_design_scores_gemma":[0.003062339,0.0006224035,0.1298544,0.0004622247,0.0008958615,0.000106725,0.007635079,0.4362062,0.003322305,0.4090483,0.007208551,0.001575597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599532,0.001513445,0.8345889,0.000201756,0.00007665539,0.0005270656,0.000002554917,0.0001715656,0.002964827],"genre_scores_gemma":[0.9793939,0.000161316,0.01989945,0.0004437746,0.00001966425,0.00003616911,0.000004987995,0.000006898339,0.00003386685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8194407,"threshold_uncertainty_score":0.4959907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02689138140384781,"score_gpt":0.2562144994664453,"score_spread":0.2293231180625974,"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."}}