{"id":"W2949134526","doi":"10.1016/j.coldregions.2019.102812","title":"Field measurements of suspended frazil ice. Part I: A support vector machine learning algorithm to identify frazil ice particles","year":2019,"lang":"en","type":"article","venue":"Cold Regions Science and Technology","topic":"Landslides and related hazards","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sediment; Geology; Offshore geotechnical engineering; Geomorphology; Particle size; Algorithm; Particle-size distribution; Particle (ecology); Oceanography; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006528826,0.0001329992,0.0002101455,0.0002061186,0.0003150579,0.00003891634,0.0005239563,0.0001708423,0.0007888051],"category_scores_gemma":[0.0002154461,0.0001049237,0.0000342678,0.001555445,0.0006924282,0.0002197469,0.0004960844,0.0002657013,0.0002968722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007331288,"about_ca_system_score_gemma":0.00006340418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001504828,"about_ca_topic_score_gemma":0.0001118126,"domain_scores_codex":[0.9982573,0.00002360534,0.0002402132,0.0004872433,0.0005408477,0.0004507719],"domain_scores_gemma":[0.9992527,0.00003954285,0.0001073729,0.0003875679,0.00006668334,0.0001460962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004001984,0.0002188622,0.4307964,0.00002312879,0.00004213215,0.00003279677,0.0005349042,0.0001013767,0.5058744,0.002363885,0.00603194,0.05394015],"study_design_scores_gemma":[0.002388841,0.00342036,0.03970703,0.0001874306,0.0001294938,0.0001681436,0.001429428,0.007029119,0.7029205,0.003737214,0.2377706,0.001111882],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890598,0.0001355844,0.0003942573,0.004774023,0.0003183317,0.0004546794,0.000004174149,0.0001214831,0.004737641],"genre_scores_gemma":[0.9972705,0.00006427291,0.001225388,0.0002313248,0.00001136187,0.00001992949,0.000001116922,0.000008552288,0.001167532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3910894,"threshold_uncertainty_score":0.8636862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574475329406854,"score_gpt":0.2603097356992068,"score_spread":0.2445649824051383,"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."}}