{"id":"W4407179113","doi":"10.48550/arxiv.2502.01543","title":"Unsupervised anomaly detection in large-scale estuarine acoustic telemetry data","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Save Our Seas Foundation; South African Institute for Aquatic Biodiversity; Dalhousie University; National Research Foundation","keywords":"Telemetry; Scale (ratio); Anomaly detection; Estuary; Anomaly (physics); Remote sensing; Geology; Environmental science; Computer science; Oceanography; Geography; Data mining; Telecommunications; Cartography; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001089744,0.0005844663,0.00048069,0.001274221,0.0002962227,0.0005035743,0.001054084,0.0004858535,0.0002396309],"category_scores_gemma":[0.003781346,0.0002164392,0.0004544721,0.001078975,0.0003628522,0.0008114788,0.0009913666,0.0007949095,0.0002086798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004291545,"about_ca_system_score_gemma":0.0006004442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00730517,"about_ca_topic_score_gemma":0.0105285,"domain_scores_codex":[0.9992587,0.0001537383,0.00007553308,0.0002475237,0.0001728981,0.00009161634],"domain_scores_gemma":[0.9978783,0.0008180005,0.0003466126,0.0003135135,0.000567783,0.00007582528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004041897,0.0004575223,0.2347261,0.0002909892,0.0003201335,0.001164094,0.0007764068,0.2806709,0.04049699,0.001711909,0.005893054,0.4330878],"study_design_scores_gemma":[0.00001038013,0.00007551406,0.0770615,0.00002659273,0.00002458675,0.0001733546,0.0002770241,0.9109371,0.007205142,0.001973529,0.002209853,0.00002546524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.779705,0.0003682143,0.2145219,0.0002834205,0.00008924266,0.00007598728,0.0021121,0.001880274,0.0009637437],"genre_scores_gemma":[0.940496,0.0001226032,0.05409057,0.00005775199,0.00003765998,0.00007014787,0.004394072,0.00004387841,0.0006873115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00730517,"threshold_uncertainty_score":0.01452529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06172893111136151,"score_gpt":0.2949334119469225,"score_spread":0.2332044808355609,"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."}}