{"id":"W2217736073","doi":"","title":"A specialized parallel corpus of english and spanish free trade agreements for the study of specialized collocations","year":2011,"lang":"en","type":"article","venue":"Journal of Professional Communication","topic":"linguistics and terminology studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005258377,0.00007805366,0.0002714842,0.00006890129,0.0004004402,0.00001327023,0.0004537037,0.00002988304,0.00007541812],"category_scores_gemma":[0.0006127953,0.00004933263,0.0000683607,0.00002794278,0.0003100621,0.00007184588,0.0001522453,0.0001409569,1.324939e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001309722,"about_ca_system_score_gemma":0.00005932685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001132357,"about_ca_topic_score_gemma":0.001097494,"domain_scores_codex":[0.9989074,0.0001578122,0.0006166922,0.00005548151,0.0001890655,0.00007347226],"domain_scores_gemma":[0.997209,0.0005396371,0.000956716,0.000308979,0.000964764,0.00002088404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00146891,0.003971674,0.01131119,0.00008794391,0.001119479,0.000001327521,0.5689951,0.000001541441,0.00007909002,0.3970015,0.0137742,0.002188133],"study_design_scores_gemma":[0.01976597,0.003507215,0.2961534,0.0005928127,0.001597272,0.000005595709,0.3349878,0.00008753237,0.0002926115,0.119627,0.2229934,0.0003894171],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737201,0.00353262,0.00008142014,0.00111664,0.004047786,0.001774286,0.0001118188,0.00001097015,0.01560431],"genre_scores_gemma":[0.9976854,0.0004092663,0.000982869,0.00003530014,0.000497992,0.0000265687,0.000003532424,0.000006923175,0.0003521424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2848423,"threshold_uncertainty_score":0.3079903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1479343314015869,"score_gpt":0.3212929148086007,"score_spread":0.1733585834070138,"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."}}