{"id":"W3031481612","doi":"10.1017/ehs.2020.30","title":"Coding culture: challenges and recommendations for comparative cultural databases","year":2020,"lang":"en","type":"article","venue":"Evolutionary Human Sciences","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Max-Planck-Institut für Menschheitsgeschichte; Templeton Religion Trust","keywords":"Interoperability; Data science; Coding (social sciences); Cultural diversity; Data collection; Computer science; Population; Sociology; Social science; World Wide Web","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003183023,0.00009745515,0.0001271328,0.00002780509,0.002907674,0.00007985552,0.0002103645,0.00003383373,0.0001406302],"category_scores_gemma":[0.0001747101,0.0000743943,0.0000433636,0.0002074579,0.0008665256,0.001158929,0.0000557724,0.00007001546,0.00001505915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691622,"about_ca_system_score_gemma":0.0000638504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000195895,"about_ca_topic_score_gemma":0.0006845126,"domain_scores_codex":[0.9988918,0.0001274017,0.0001480001,0.0003284575,0.0002609716,0.0002433912],"domain_scores_gemma":[0.9995093,0.0001014859,0.00008025739,0.00004917807,0.0001248539,0.000134916],"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":[0.000008966128,0.00003125841,0.0002398152,0.0000169575,0.00001404278,6.123265e-7,0.1423284,0.000006808502,0.0009914025,0.7343695,0.120601,0.0013912],"study_design_scores_gemma":[0.0003886505,0.0002693417,0.004905702,0.00005297587,0.00002837204,0.000003536383,0.3252234,0.0005545503,0.00009371557,0.007256057,0.6608747,0.0003490045],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2500992,0.1175397,0.002389686,0.3378097,0.001587027,0.003829372,0.0006248482,0.001281369,0.284839],"genre_scores_gemma":[0.9920681,0.001808523,0.004218402,0.0005242084,0.0006067214,0.00003974005,0.00008036188,0.000002798835,0.0006511363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7419689,"threshold_uncertainty_score":0.9983904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3564723923206251,"score_gpt":0.4464849792672556,"score_spread":0.0900125869466305,"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."}}