{"id":"W30536900","doi":"10.1111/risa.13248","title":"Data-driven computational linguistics at FaMAF-UNC, Argentina","year":2010,"lang":"en","type":"article","venue":"North American Chapter of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computational linguistics; Computer science; Applied linguistics; Linguistics; Language technology; Language and Communication Technologies; Natural language; Natural language processing; Data science; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004383471,0.0002231975,0.0003161988,0.0001220334,0.0003907385,0.0001114894,0.002009471,0.00007511907,0.00000509904],"category_scores_gemma":[0.01003268,0.0001983161,0.000145319,0.0004250505,0.0001769308,0.00005612113,0.0009255185,0.0003424587,0.00001073799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566906,"about_ca_system_score_gemma":0.0002048426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003700474,"about_ca_topic_score_gemma":0.0001999634,"domain_scores_codex":[0.9976615,0.0000477047,0.0005895323,0.0004887671,0.0009054918,0.0003069528],"domain_scores_gemma":[0.9937282,0.001067045,0.001506686,0.0006899869,0.002911952,0.00009619926],"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":[0.00002461073,0.0001350731,0.08163271,0.00004816809,0.000150161,0.000002216735,0.0002112626,0.0289745,0.00004110626,0.8810764,0.004381099,0.003322724],"study_design_scores_gemma":[0.0005571619,0.0001106647,0.03326659,0.00002734616,0.00009995099,0.00000559204,0.000007064327,0.7153351,0.0002235975,0.1393388,0.1105015,0.0005266661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02108917,0.00009612379,0.9628587,0.001558813,0.006666676,0.00106848,0.003320744,0.0006910738,0.002650205],"genre_scores_gemma":[0.5444741,0.000001045003,0.4542126,0.0002980907,0.0004749627,0.000006448403,0.0003773663,0.00001618163,0.0001392681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7417375,"threshold_uncertainty_score":0.9983062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02033526140629643,"score_gpt":0.2892357441993217,"score_spread":0.2689004827930253,"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."}}