{"id":"W4407293112","doi":"10.3897/rio.10.e134825","title":"Using Image-based AI for insect monitoring and conservation - InsectAI COST Action","year":2025,"lang":"en","type":"article","venue":"Research Ideas and Outcomes","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Fundação para a Ciência e a Tecnologia; Centro de Estudos Ambientais e Marinhos, Universidade de Aveiro; European Cooperation in Science and Technology","keywords":"Action (physics); Computer science; Image (mathematics); Computer vision; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.000473665,0.00006687231,0.00009218564,0.00007069205,0.0003852372,0.0001329829,0.00005200526,0.00004394878,0.0004323578],"category_scores_gemma":[0.000266385,0.00005870171,0.00002396232,0.0002167345,0.0001778309,0.0001756889,0.00008526611,0.0001013123,0.000009092565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003424129,"about_ca_system_score_gemma":0.00002469395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001277059,"about_ca_topic_score_gemma":0.0002360597,"domain_scores_codex":[0.9992515,0.00005403526,0.00009895202,0.0001755833,0.000193848,0.0002260112],"domain_scores_gemma":[0.9995588,0.0002287584,0.00001973485,0.00008641322,0.00004016187,0.00006611951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005289568,0.00002629281,0.9680876,0.00006152823,0.000007604493,9.748168e-7,0.00003169849,0.00000497709,0.02473807,0.001127382,0.001886403,0.003974612],"study_design_scores_gemma":[0.0007046408,0.00002829956,0.9768218,0.00002377748,0.000006805673,7.110101e-7,0.0005406811,0.002233945,0.00765542,0.0007990479,0.01111102,0.00007387995],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940187,0.0000779873,0.0008983015,0.003693551,0.00008264748,0.00036517,0.00002213379,0.00001911236,0.0008223601],"genre_scores_gemma":[0.9990423,0.00008926752,0.0002275388,0.0002762759,0.00001496358,0.00004756514,0.00001116661,0.000004954958,0.0002860108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01708265,"threshold_uncertainty_score":0.4734014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2498895979123728,"score_gpt":0.4600312179767744,"score_spread":0.2101416200644017,"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."}}