{"id":"W4401258033","doi":"10.1111/ecog.07294","title":"Optimising occurrence data in species distribution models: sample size, positional uncertainty, and sampling bias matter","year":2024,"lang":"en","type":"article","venue":"Ecography","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"HORIZON EUROPE Framework Programme; European Regional Development Fund; Deutsche Forschungsgemeinschaft; Agencia Estatal de Investigación; Akademie Věd České Republiky; European Commission; Fundação para a Ciência e a Tecnologia; Biodiversa+","keywords":"Species distribution; Sampling (signal processing); Sample size determination; Sampling bias; Ecology; Limiting; Sample (material); Computer science; Data quality; Econometrics; Statistics; Data mining; Environmental science; Biology; Mathematics; Habitat; Physics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002782397,0.000131225,0.0001059522,0.00005872147,0.0001204453,0.0002497032,0.000232857,0.00004923573,0.02163272],"category_scores_gemma":[0.00005814903,0.000125782,0.00004455282,0.0006100164,0.0002009417,0.0005665999,0.0003644064,0.000128898,0.000195135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001657095,"about_ca_system_score_gemma":0.00000777881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004492912,"about_ca_topic_score_gemma":0.0003837239,"domain_scores_codex":[0.9988162,0.00002818646,0.0001882285,0.0004561912,0.0002432459,0.0002679699],"domain_scores_gemma":[0.9993427,0.0002878372,0.00002837349,0.0002572003,0.000006998125,0.00007683723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008621554,0.0003826191,0.8032559,0.0002113481,0.00007753049,0.00004076137,0.001098121,0.006465168,0.001533899,0.01397164,0.1624508,0.01042601],"study_design_scores_gemma":[0.0003335903,0.00003517061,0.8891487,0.000151274,0.00003125172,0.00002768863,0.001069611,0.03378509,0.00005332882,0.01182319,0.06300242,0.0005387125],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9598356,0.0007589485,0.01025521,0.001800693,0.0003287554,0.0002196883,0.01851447,0.0001189977,0.008167568],"genre_scores_gemma":[0.9946482,0.0003089627,0.0007965899,0.0002161823,0.00003224557,0.00001065203,0.003957015,0.000006971396,0.00002319305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09944841,"threshold_uncertainty_score":0.9792616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135833419121204,"score_gpt":0.2958887181732883,"score_spread":0.1823053762611679,"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."}}