{"id":"W4390477219","doi":"10.33137/js.v5i.42259","title":"Corpus Linguistics Strategies for Identifying Accepted Theories in Early Modern England","year":2023,"lang":"en","type":"article","venue":"Scientonomy Journal for the Science of Science","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Corpus linguistics; Adjective; Context (archaeology); Set (abstract data type); Linguistics; Text corpus; Computational linguistics; Computer science; Natural language processing; Artificial intelligence; Noun phrase; Noun; History; Philosophy; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.02371121,0.0001119866,0.0001811772,0.0009852616,0.005647064,0.001386214,0.002531689,0.00004663713,0.00001951174],"category_scores_gemma":[0.01862315,0.00008131481,0.00008811886,0.004869814,0.01154596,0.0008743669,0.0001832331,0.0001645315,0.000005005737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002213794,"about_ca_system_score_gemma":0.005092924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002531813,"about_ca_topic_score_gemma":0.0002106529,"domain_scores_codex":[0.9968535,0.00005910116,0.0004593519,0.0004092699,0.001255118,0.0009636781],"domain_scores_gemma":[0.9958324,0.0009891707,0.0003715897,0.0002505314,0.002319253,0.000237094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003719804,0.00002682663,0.000993437,0.00001005718,0.000004458578,0.000002036349,0.05474049,0.002145291,0.00849313,0.9286671,0.00009390982,0.00478602],"study_design_scores_gemma":[0.001072877,0.0001651837,0.007080221,0.00005908754,0.00002358501,0.000007623762,0.04180728,0.02187083,0.003146692,0.9117682,0.01273463,0.0002637891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8762152,0.0001609423,0.07402628,0.002516428,0.02623564,0.001768025,0.0000478011,0.0001098731,0.01891987],"genre_scores_gemma":[0.9962386,0.00004289446,0.00271141,0.00004931773,0.000465902,0.00002826186,5.45725e-7,0.000006157567,0.0004569034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1200235,"threshold_uncertainty_score":0.9996504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07801143135558652,"score_gpt":0.3940014506527059,"score_spread":0.3159900192971194,"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."}}