{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003371502,0.0002237968,0.0004446039,0.0001316588,0.0000521246,0.00003467305,0.007035461,0.0001682921,0.000001062917],"category_scores_gemma":[0.00002450908,0.0002135263,0.00008483318,0.00005336948,0.000233828,0.0002912249,0.005149703,0.0004555733,0.000001839293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001483023,"about_ca_system_score_gemma":0.0009729915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006621446,"about_ca_topic_score_gemma":0.00002604881,"domain_scores_codex":[0.9980978,0.0001570066,0.0003196035,0.0006932724,0.0005064598,0.0002258741],"domain_scores_gemma":[0.9971835,0.0002873875,0.0003828944,0.00194951,0.0001108847,0.00008580066],"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":[0.0001019052,0.00005220201,0.00003519497,0.001248114,0.0002122856,0.0003325459,0.003639552,0.0002302664,0.0003362994,0.8240557,0.1519442,0.01781175],"study_design_scores_gemma":[0.001038975,0.0002047964,0.00004846008,0.003598163,0.0002457978,0.0000232612,0.0001778595,0.1011418,0.0007437391,0.0001142471,0.8917957,0.0008672276],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002806843,0.0007888766,0.04410475,0.001684134,0.00009586748,0.00153292,0.0008689999,0.000143048,0.9505007],"genre_scores_gemma":[0.00278808,0.0001116468,0.007075745,0.00011825,0.00006650007,9.475056e-7,0.00003670375,0.00001991812,0.9897822],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8239415,"threshold_uncertainty_score":0.998337,"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."}}