{"id":"W2905726793","doi":"10.22148/16.030","title":"Critical Search: A Procedure for Guided Reading in Large-Scale Textual Corpora","year":2018,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reading (process); Computer science; Scale (ratio); Information retrieval; Natural language processing; Artificial intelligence; Linguistics; Geography; Philosophy; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.000888284,0.0001369568,0.0002929616,0.0002043003,0.0001176599,0.0002616434,0.0008480266,0.0001045515,0.000008436657],"category_scores_gemma":[0.001126747,0.00009049823,0.0001328266,0.0005755649,0.0001190826,0.001048678,0.0001452344,0.0003534863,0.000003779547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001152254,"about_ca_system_score_gemma":0.0001554835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004273967,"about_ca_topic_score_gemma":0.00002108777,"domain_scores_codex":[0.9984361,0.00004422658,0.0005446535,0.000192178,0.0004179241,0.0003649354],"domain_scores_gemma":[0.9977239,0.0001252469,0.0002279249,0.0001698928,0.001615203,0.0001377816],"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":[0.000729073,0.001637615,0.01141245,0.001235065,0.000326229,0.001183778,0.04378487,0.0002104859,0.09104089,0.5926408,0.2174502,0.03834849],"study_design_scores_gemma":[0.004123124,0.004033871,0.001876979,0.002367647,0.0002079781,0.004589188,0.005893474,0.5813993,0.1489238,0.2330705,0.01186681,0.001647348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06720544,0.0008205953,0.921524,0.009285451,0.0003207801,0.0002523368,0.000009424491,0.0001255306,0.000456418],"genre_scores_gemma":[0.5978286,0.000008924825,0.4012893,0.0003540416,0.0003461732,0.000001292194,8.90703e-7,0.000006049298,0.0001647375],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5811888,"threshold_uncertainty_score":0.3690411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0522741677462495,"score_gpt":0.3675912135698836,"score_spread":0.3153170458236341,"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."}}