{"id":"W2254582040","doi":"10.1515/jhsl-2015-0002","title":"Searching for standard French: The construction and mining of the <i>Recueil historique des grammaires du français</i>","year":2015,"lang":"en","type":"article","venue":"Journal of Historical Sociolinguistics","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Ottawa","funders":"","keywords":"Linguistics; Rule-based machine translation; Grammar; Originality; Structuring; Selection (genetic algorithm); French; Humanities; Philosophy; History; Computer science; Sociology; Artificial intelligence; Political science; Anthropology; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002359697,0.00007667147,0.0002331786,0.00004163033,0.000701746,0.00002500523,0.0002358692,0.0001064444,0.000005242252],"category_scores_gemma":[0.02817789,0.0000480105,0.0001169862,0.0001103688,0.0007652756,0.00002889833,0.00003540812,0.0002413745,1.596739e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001204627,"about_ca_system_score_gemma":0.0009321437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001566886,"about_ca_topic_score_gemma":0.0002627892,"domain_scores_codex":[0.9985924,0.000294051,0.0004257202,0.0000795475,0.0004332886,0.0001749388],"domain_scores_gemma":[0.9968491,0.0009577706,0.0005320464,0.00008424219,0.001432008,0.0001448887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002714959,0.0001358842,0.06058623,0.00008166917,0.0001452704,0.00002317351,0.4806683,0.0001400204,0.0001115829,0.3655541,0.07645927,0.01582295],"study_design_scores_gemma":[0.0006043622,0.0001728635,0.0005504604,0.00002904072,0.00008867558,0.00002721735,0.004654172,0.00004462116,0.00002229266,0.05509367,0.9386344,0.00007825033],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6548923,0.01588002,0.2140058,0.02858275,0.05977921,0.001225178,0.00007406015,0.00009242314,0.02546821],"genre_scores_gemma":[0.9773755,0.0002189852,0.01893463,0.0001408383,0.003127608,0.000002204022,3.457185e-7,0.000009463723,0.0001904357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8621751,"threshold_uncertainty_score":0.9800082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04972725782999952,"score_gpt":0.3027244303230727,"score_spread":0.2529971724930732,"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."}}