{"id":"W2183772626","doi":"10.4242/balisagevol8.huitfeldt02","title":"The MLCD Overlap Corpus (MOC)","year":2012,"lang":"en","type":"article","venue":"Balisage series on markup technologies","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003808168,0.0003020373,0.0002245678,0.0001000427,0.001420404,0.001379768,0.0007595322,0.0001252289,0.0005780157],"category_scores_gemma":[0.0003554338,0.0001923373,0.0001366073,0.00006692422,0.001532553,0.001545984,0.0002983033,0.0003953402,0.0003518407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006483554,"about_ca_system_score_gemma":0.00001613563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003434438,"about_ca_topic_score_gemma":0.0003886726,"domain_scores_codex":[0.9983544,0.00004483909,0.000292336,0.0002280786,0.0003347916,0.0007455613],"domain_scores_gemma":[0.9987678,0.0002554292,0.0001287525,0.0007130791,0.00008308794,0.00005185695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007284719,0.00005613233,0.000506908,0.00001350265,0.0000321963,0.000006135852,0.001471877,1.716103e-7,0.0000140275,0.9319479,0.02869972,0.03717857],"study_design_scores_gemma":[0.0001187957,0.0001972876,0.0004408468,0.00002703774,0.00001267789,0.00001041753,0.04229631,6.233385e-7,0.0005729192,0.02465153,0.9313875,0.0002840925],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1513059,0.003764727,0.0000024725,0.003718596,0.002623054,0.000370923,0.0001269038,0.002492604,0.8355948],"genre_scores_gemma":[0.9182095,0.0005262588,0.00003626003,0.0003600653,0.000396118,0.00008243206,0.00001494024,0.00003844469,0.08033597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9072964,"threshold_uncertainty_score":0.9998796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03398389952082131,"score_gpt":0.2191594948432474,"score_spread":0.1851755953224261,"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."}}