{"id":"W4417132981","doi":"10.48550/arxiv.2510.09458","title":"SilvaScenes: Tree Segmentation and Species Classification from Under-Canopy Images in Natural Forests","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Benchmarking; Tree (set theory); Biodiversity; Vegetation (pathology); Focus (optics); Relevance (law); Decision tree","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006721244,0.003198361,0.001173023,0.003560509,0.001316187,0.002087218,0.002985043,0.002057409,0.004775934],"category_scores_gemma":[0.002121649,0.0007222748,0.001829307,0.003326626,0.0008001339,0.001469198,0.001891191,0.001633384,0.005879761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002696385,"about_ca_system_score_gemma":0.002863503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2596149,"about_ca_topic_score_gemma":0.5497083,"domain_scores_codex":[0.9989166,0.00006800017,0.00005000137,0.0004733423,0.0002828999,0.0002091558],"domain_scores_gemma":[0.9992318,0.0001225617,0.00005502857,0.0002424654,0.0002365085,0.0001115616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001235225,0.0008251773,0.03276058,0.003132767,0.0008085663,0.0009428724,0.0008632297,0.02769119,0.03114493,0.002215055,0.6590744,0.239306],"study_design_scores_gemma":[0.0005717495,0.0004204722,0.1701824,0.00115463,0.0004490988,0.002465067,0.002075723,0.2492059,0.04748106,0.009114773,0.5164743,0.0004047195],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2055563,0.005957261,0.02938189,0.0008623409,0.0006590622,0.0007331743,0.6654948,0.07412557,0.0172296],"genre_scores_gemma":[0.07748862,0.0006663987,0.0376405,0.0002406717,0.00005141063,0.0001641113,0.8790012,0.00123053,0.003516646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2596149,"threshold_uncertainty_score":0.5162076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03342704383512894,"score_gpt":0.2729821566714035,"score_spread":0.2395551128362745,"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."}}