{"id":"W4387123803","doi":"10.1109/rew57809.2023.00022","title":"Automatic Domain-Specific Corpora Generation from Wikipedia - A Replication Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Baseline (sea); Crawling; Encoder; Artificial intelligence; Natural language processing; Workflow; Replication (statistics); Replicate; Domain (mathematical analysis); Realm; World Wide Web; Information retrieval; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004261003,0.00008569792,0.0001008275,0.00008752663,0.0001011812,0.0001738135,0.0004711481,0.00003244522,0.00004985289],"category_scores_gemma":[0.00001156255,0.00007865676,0.0000248347,0.0004746478,0.000007838557,0.0002993546,0.0001648462,0.00005520292,0.0005705509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003922519,"about_ca_system_score_gemma":0.00002831418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008973591,"about_ca_topic_score_gemma":0.00003385733,"domain_scores_codex":[0.9986733,0.00006742604,0.0002593834,0.0005677163,0.0002870893,0.0001451236],"domain_scores_gemma":[0.9983599,0.00005378851,0.0000760638,0.001419436,0.00004209502,0.00004871458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002674182,0.0003386907,0.01085605,0.000006543139,0.00004930394,0.00006002955,0.01282996,0.001694315,0.02245954,0.5041284,0.03726731,0.4103072],"study_design_scores_gemma":[0.0002745308,0.00003975416,0.03544362,0.00000303609,0.000002671886,0.000001302612,0.0002025532,0.9460017,0.0003047041,0.01467494,0.002921314,0.0001298593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5239675,0.00001044725,0.4741361,0.0005056834,0.0002465339,0.0002028669,4.942434e-7,0.0005902059,0.0003401938],"genre_scores_gemma":[0.8507533,0.000004862751,0.1484727,0.0001187228,0.000236848,0.00006131706,0.00001926188,0.000007296559,0.0003257434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9443074,"threshold_uncertainty_score":0.7333468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0838222573724981,"score_gpt":0.2817979867145097,"score_spread":0.1979757293420116,"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."}}