{"id":"W4407685124","doi":"10.24124/2024/59603","title":"Machine learning based classification of early seral vegetation in cut-blocks in the interior of northern British Columbia","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Tree Root and Stability Studies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Seral community; Vegetation (pathology); Geography; Forestry; Artificial intelligence; Computer science; Machine learning; Ecology; Ecological succession; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002072808,0.0001100422,0.0002801217,0.0001157765,0.00001871874,0.00005722335,0.0001149214,0.0001242959,0.00002672231],"category_scores_gemma":[0.00004442051,0.0001316101,0.00007649318,0.0003046935,0.00001839743,0.00005233484,0.00000618993,0.0003662878,0.000001930573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006044843,"about_ca_system_score_gemma":0.00002623533,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03026941,"about_ca_topic_score_gemma":0.9864274,"domain_scores_codex":[0.9990388,0.00005294579,0.000474456,0.0001557979,0.0001692418,0.0001087459],"domain_scores_gemma":[0.999658,0.00007999397,0.00007186039,0.0001132908,0.00006757613,0.000009241064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003515474,0.00005623995,0.9582646,0.00240295,0.0000564397,0.000005817808,0.0138301,0.004115853,0.001523534,0.000007637802,0.00006572356,0.01963592],"study_design_scores_gemma":[0.000202701,0.00005024845,0.9546899,0.0005828334,0.00002458415,3.510364e-7,0.00202413,0.04213018,0.00006883215,0.00005839607,0.00005503534,0.0001127754],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961344,0.001046338,0.00004194805,0.00001626804,0.0001767313,0.0002687231,0.00001306794,0.00005063357,0.002251866],"genre_scores_gemma":[0.998859,0.00002477621,0.00002732066,0.000001611894,0.00001273674,0.00005848356,0.0002780225,0.00002612999,0.000711845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.956158,"threshold_uncertainty_score":0.9761881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009617406368931686,"score_gpt":0.2242392761253483,"score_spread":0.2146218697564166,"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."}}