{"id":"W3037176076","doi":"10.1002/essoar.10503379.1","title":"Machine Learning for Outlier Detection in Algal and Cyanobacterial Fluorescence Signals","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; World Wide Web; Information retrieval; Anomaly detection; Outlier; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003522327,0.001323391,0.001511748,0.002009318,0.0006472934,0.00100812,0.001114259,0.001023071,0.000466271],"category_scores_gemma":[0.008619923,0.0002989056,0.001110843,0.001645989,0.0005286529,0.0009338792,0.0008528311,0.001611169,0.0002791196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008859214,"about_ca_system_score_gemma":0.001231425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005780528,"about_ca_topic_score_gemma":0.003173687,"domain_scores_codex":[0.9980064,0.0005516775,0.0002369054,0.000448396,0.0005235366,0.00023305],"domain_scores_gemma":[0.9952497,0.002828889,0.0005892215,0.000222322,0.0009895143,0.0001203637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004298062,0.0004704377,0.02842815,0.0002370271,0.0002820927,0.0002754933,0.0001761371,0.5289221,0.005859876,0.001778952,0.002633957,0.4305059],"study_design_scores_gemma":[0.000005537238,0.00003524031,0.001573977,0.000006122365,0.000007315075,0.00002570821,0.00002083861,0.9963986,0.001031708,0.0007108555,0.0001783695,0.000005722683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2221404,0.001607063,0.7691437,0.0006497133,0.0001817469,0.0001607482,0.0005030828,0.004456893,0.001156609],"genre_scores_gemma":[0.8644374,0.0002794278,0.1332722,0.0001011565,0.00007812578,0.0001244564,0.001096455,0.00006761726,0.0005431884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005780528,"threshold_uncertainty_score":0.01862806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01783601677787732,"score_gpt":0.2106759974302488,"score_spread":0.1928399806523715,"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."}}