{"id":"W4406934208","doi":"10.7717/peerj.18853","title":"Evaluating the feasibility of automating dataset retrieval for biodiversity monitoring","year":2025,"lang":"en","type":"article","venue":"PeerJ","topic":"Research Data Management Practices","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Relevance (law); Ranking (information retrieval); Information retrieval; Overfitting; Biodiversity; Database; Pace; Data mining; Data science; Machine learning; Geography; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006488908,0.00006077214,0.00009680363,0.00007247878,0.0003630521,0.0005574793,0.002130902,0.00001851908,0.000002702888],"category_scores_gemma":[0.007169458,0.00004683322,0.00003673477,0.0004580301,0.00008403841,0.004684423,0.001700878,0.0001261423,0.000004448333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005362197,"about_ca_system_score_gemma":0.00008357782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007322054,"about_ca_topic_score_gemma":0.000001965918,"domain_scores_codex":[0.9986216,0.0002416322,0.0001816191,0.0003151476,0.000451399,0.0001885361],"domain_scores_gemma":[0.9969523,0.001591212,0.0001405101,0.001137388,0.0001542942,0.00002431908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007246726,0.000759722,0.3871165,0.003018805,0.0007492008,0.00001469521,0.002547916,0.00226325,0.04803798,0.2398305,0.1125981,0.2023387],"study_design_scores_gemma":[0.00255743,0.0007489736,0.2198332,0.000221306,0.0001836267,0.000002032439,0.001356107,0.7065408,0.03850717,0.009514497,0.02006785,0.0004670037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3437186,0.0001378084,0.6447285,0.008286028,0.0006301292,0.001145046,0.0007427228,0.0001204518,0.0004907037],"genre_scores_gemma":[0.8541705,0.00003177996,0.1448378,0.000151087,0.00006836615,0.00002064847,0.0002031073,0.000003494627,0.0005131901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7042775,"threshold_uncertainty_score":0.8583029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4107494996393343,"score_gpt":0.5163996542726087,"score_spread":0.1056501546332744,"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."}}