{"id":"W2092746927","doi":"10.1080/13645579.2011.638221","title":"Exploring the validity of electronic newspaper databases","year":2011,"lang":"en","type":"article","venue":"International Journal of Social Research Methodology","topic":"Media Studies and Communication","field":"Social Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Newspaper; Lexis; Content analysis; Database; Advertising; Political science; Computer science; Sociology; Business; Social science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02098528,0.00004385896,0.0001631255,0.0001539799,0.0004083111,0.00001415877,0.001229361,0.00003046813,0.0003194616],"category_scores_gemma":[0.01110949,0.00003136953,0.000108036,0.0002158216,0.0008269697,0.0002586556,0.0002434278,0.0005407029,0.000005075315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001608761,"about_ca_system_score_gemma":0.0005010399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002918524,"about_ca_topic_score_gemma":0.001850289,"domain_scores_codex":[0.9919283,0.006327974,0.0003291113,0.00006930911,0.001070482,0.0002748067],"domain_scores_gemma":[0.9925063,0.005345675,0.0002672459,0.0001100573,0.001723325,0.00004735115],"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":[0.0002659461,0.000118487,0.003096872,0.00000360144,0.000250277,0.000007718629,0.09780763,7.091784e-7,0.001074215,0.8305742,0.00160119,0.06519913],"study_design_scores_gemma":[0.0006635478,0.000415346,0.08295842,0.00004647713,0.0000498056,0.00001620113,0.1571331,0.000005173149,0.003879264,0.1181239,0.6365674,0.0001412853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9328426,0.0005428987,0.003756681,0.02597739,0.002157339,0.0001797577,0.000006989291,0.000008651679,0.03452768],"genre_scores_gemma":[0.9891653,0.005710736,0.003837981,0.00007173921,0.001049563,0.00001155448,8.411936e-7,0.000004893134,0.0001473954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7124503,"threshold_uncertainty_score":0.9972203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9349094824766678,"score_gpt":0.6276944662901474,"score_spread":0.3072150161865205,"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."}}