{"id":"W4409220222","doi":"10.4000/13pbe","title":"Collecting data on a global scale: from local to international and back again","year":2024,"lang":"en","type":"article","venue":"Statistique et société","topic":"Twentieth Century Scientific Developments","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Genetics","funders":"","keywords":"Scale (ratio); Data science; Computer science; Regional science; Geography; Cartography","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03396405,0.0006213641,0.001018363,0.009012304,0.003811505,0.01472682,0.001328972,0.001276036,0.005406995],"category_scores_gemma":[0.05818603,0.0007035006,0.0005017483,0.02258574,0.009764308,0.01573762,0.0137695,0.00390797,0.001615108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004129016,"about_ca_system_score_gemma":0.008558711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01513006,"about_ca_topic_score_gemma":0.02321183,"domain_scores_codex":[0.9714481,0.0167341,0.001989845,0.003786661,0.004773545,0.00126771],"domain_scores_gemma":[0.9215748,0.0339225,0.007136413,0.01898009,0.01481817,0.003568029],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001614432,0.0001289514,0.1722881,0.002124859,0.0005654904,0.0005415925,0.08982557,0.001523281,0.002962177,0.1140465,0.07802009,0.5378119],"study_design_scores_gemma":[0.00004877746,0.0002069419,0.1524143,0.004254203,0.000311165,0.000323993,0.1540674,0.0007184015,0.002010682,0.06643991,0.6190231,0.0001812413],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3354602,0.03201201,0.1039405,0.2101427,0.004788673,0.001435163,0.01956498,0.001651307,0.2910044],"genre_scores_gemma":[0.8669489,0.01679798,0.06803716,0.02402159,0.00166393,0.001459689,0.006911741,0.001265452,0.0128936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9852732,"threshold_uncertainty_score":0.1796212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0582892616092822,"score_gpt":0.3635547999226256,"score_spread":0.3052655383133434,"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."}}