{"id":"W2610765827","doi":"10.1515/phras-2013-0003","title":"In support of multiword unit classifications: Corpus and human rating data validate phraseological classifications of three different multiword unit types","year":2013,"lang":"en","type":"article","venue":"Yearbook of Phraseology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Natural language processing; Linguistics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0003541503,0.0001743922,0.0004298602,0.0002963324,0.00005481088,0.00001991386,0.001436678,0.0001741158,0.0001252262],"category_scores_gemma":[0.0002989626,0.000146512,0.00003435236,0.0003304363,0.0006061214,0.0003938388,0.0008335796,0.0002641047,0.000007911931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001514015,"about_ca_system_score_gemma":0.00007488408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005497838,"about_ca_topic_score_gemma":0.0003792571,"domain_scores_codex":[0.9982531,0.0001753454,0.0006876666,0.0004572172,0.0001895185,0.0002371557],"domain_scores_gemma":[0.9976514,0.0003963503,0.0005213391,0.001153936,0.0002133955,0.00006356055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000031425,0.0008030216,0.1600857,0.0002557902,0.00008321515,0.00001601534,0.0008207846,0.00000990937,0.5613127,0.2578139,0.0009975499,0.01777],"study_design_scores_gemma":[0.003415213,0.001192916,0.3892127,0.0004241844,0.0001635216,0.00006669718,0.0003058586,0.05583028,0.3586789,0.1878851,0.001578317,0.001246315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9242422,0.0008684937,0.07149257,0.001720492,0.0001066768,0.0008028269,0.00007082003,0.0001700444,0.0005258651],"genre_scores_gemma":[0.8928921,0.00002868659,0.1067552,0.00007642867,0.00001752871,0.00003656518,0.00006729953,0.00001027335,0.0001159802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2291269,"threshold_uncertainty_score":0.5974587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1005506097616091,"score_gpt":0.3419018279530505,"score_spread":0.2413512181914414,"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."}}