{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007226556,0.001129718,0.001209338,0.01410927,0.002903257,0.007113591,0.002345446,0.002048759,0.01222938],"category_scores_gemma":[0.02735732,0.0007271369,0.001781682,0.0107309,0.003630518,0.00785522,0.003618976,0.003749698,0.004329045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001903925,"about_ca_system_score_gemma":0.002437739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003264914,"about_ca_topic_score_gemma":0.00385684,"domain_scores_codex":[0.9878954,0.007689397,0.0009185111,0.001550787,0.001613017,0.0003329247],"domain_scores_gemma":[0.9613931,0.02893557,0.00127746,0.003239039,0.004769684,0.0003852382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000251472,0.0001707042,0.001504477,0.001304377,0.000118172,0.0002214719,0.01607263,0.001662854,0.01216898,0.08546381,0.01205399,0.8690071],"study_design_scores_gemma":[0.0001757506,0.0003828859,0.01266422,0.001843567,0.0003977816,0.001919,0.02887434,0.09293558,0.0579101,0.471309,0.3311895,0.0003984309],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01698106,0.002678397,0.9627343,0.001071675,0.0003657677,0.0008209973,0.000814171,0.004492004,0.01004173],"genre_scores_gemma":[0.09037993,0.001235339,0.8979108,0.0002268994,0.0001687762,0.0008595361,0.001383632,0.001095724,0.006739473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01410927,"threshold_uncertainty_score":0.04091138,"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."}}