{"id":"W3088218728","doi":"10.1017/9781108922036","title":"Can We Be Wrong? The Problem of Textual Evidence in a Time of Data","year":2020,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Topic Modeling","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Generalizability theory; Generalization; Element (criminal law); Computer science; Field (mathematics); Data science; Artificial intelligence; Discipline; Epistemology; Natural language processing; Psychology; Sociology; Mathematics; Social science; Political science; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03041616,0.0008705815,0.00189077,0.005184226,0.003614375,0.01559761,0.003688973,0.005537604,0.008477568],"category_scores_gemma":[0.1232861,0.001172496,0.001201532,0.005641414,0.02535573,0.04701611,0.004650903,0.01105564,0.002221866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003726602,"about_ca_system_score_gemma":0.003560194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002105704,"about_ca_topic_score_gemma":0.002630534,"domain_scores_codex":[0.9787629,0.01388771,0.000842,0.002187829,0.004030026,0.0002895474],"domain_scores_gemma":[0.829283,0.1561383,0.003313406,0.007193132,0.003362562,0.0007095599],"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":[0.00003618309,0.00001445531,0.0006198967,0.0003800392,0.00007658448,0.0001507472,0.003243818,0.001113944,0.00009875981,0.9154058,0.01985605,0.05900389],"study_design_scores_gemma":[0.000005965423,0.000009489861,0.0001701203,0.0004051781,0.00001598896,0.0001563326,0.001095176,0.002250431,0.0001281367,0.9485497,0.04719292,0.00002044911],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009372923,0.03498795,0.4885014,0.3436606,0.005230688,0.0002066262,0.001562618,0.0004668005,0.1160105],"genre_scores_gemma":[0.4389028,0.03134421,0.3749039,0.06069234,0.01626157,0.001182974,0.001652805,0.001552045,0.07350742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03041616,"threshold_uncertainty_score":0.160858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08577631419635601,"score_gpt":0.2379681552953743,"score_spread":0.1521918410990183,"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."}}