{"id":"W4416063095","doi":"10.48550/arxiv.2507.06806","title":"GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Hyperspectral imaging; Trait; Leverage (statistics); Regression; Predictive modelling; Pairwise comparison; Sampling (signal processing); Feature learning; Representation (politics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0007845725,0.002063128,0.0005358541,0.001485292,0.0005716496,0.0008269362,0.001789065,0.001606171,0.00484609],"category_scores_gemma":[0.001917906,0.0003758133,0.001072246,0.001737434,0.0005532913,0.001217176,0.001293367,0.001680803,0.005622923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006655133,"about_ca_system_score_gemma":0.0007973895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01686339,"about_ca_topic_score_gemma":0.03107531,"domain_scores_codex":[0.9995116,0.0000742492,0.00002517169,0.0001811422,0.0001438111,0.00006408004],"domain_scores_gemma":[0.9993681,0.0001557372,0.00005049344,0.0002281426,0.0001416853,0.0000557963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007500714,0.0009739986,0.02271135,0.001051145,0.0004848176,0.0004924517,0.0002944438,0.05577674,0.02916644,0.003097498,0.718032,0.167169],"study_design_scores_gemma":[0.0007915766,0.0004193716,0.1163999,0.0002963157,0.0001842762,0.0008490631,0.0005716861,0.409654,0.04112306,0.02128191,0.4079719,0.0004570941],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1227921,0.001540339,0.04657131,0.001322237,0.00051706,0.0003647096,0.7695292,0.04657303,0.01078999],"genre_scores_gemma":[0.09289613,0.0002867428,0.04275553,0.0003489099,0.00006512563,0.0002767503,0.8592095,0.001419616,0.002741701],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01686339,"threshold_uncertainty_score":0.03353041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03092626688485142,"score_gpt":0.2730402119572701,"score_spread":0.2421139450724187,"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."}}