{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.639824,0.003872101,0.006759505,0.03357286,0.01457923,0.04234843,0.0254221,0.01394487,0.00774117],"category_scores_gemma":[0.7976837,0.003979041,0.00554732,0.04645384,0.03180879,0.06473133,0.03063958,0.02012222,0.003903999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02692937,"about_ca_system_score_gemma":0.09467968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0685593,"about_ca_topic_score_gemma":0.06023523,"domain_scores_codex":[0.3774214,0.4872717,0.08733175,0.01368554,0.02949565,0.004793893],"domain_scores_gemma":[0.1003283,0.612394,0.02529647,0.09695461,0.1538331,0.01119332],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002964399,0.0006268156,0.02727701,0.01090102,0.0004706202,0.0007854498,0.07352933,0.003942212,0.001144649,0.2932963,0.1529605,0.4347697],"study_design_scores_gemma":[0.0003170726,0.0001948998,0.009088487,0.04892832,0.0003448707,0.0006343239,0.2048098,0.01428466,0.001449324,0.4671771,0.2521299,0.000641168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.009990441,0.01702634,0.3107862,0.6282578,0.006815648,0.01088838,0.002808779,0.00135143,0.01207501],"genre_scores_gemma":[0.03797723,0.007018476,0.9109159,0.01940998,0.001384489,0.01811809,0.002914944,0.0004452243,0.001815646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.639824,"threshold_uncertainty_score":0.4441612,"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."}}