{"id":"W4376278917","doi":"10.21203/rs.3.rs-2899695/v1","title":"Semi and Self-supervised Learning for Multi-label Classification for an Underwater Inspection Imagery Application","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Water Systems and Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Pontifícia Universidade Católica do Rio de Janeiro","keywords":"Underwater; Computer science; Task (project management); Machine learning; Artificial intelligence; Inference; Process (computing); Data mining; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00119518,0.000207204,0.0002285377,0.0004067201,0.0003434486,0.0003097384,0.0001553439,0.0003848039,0.000001107978],"category_scores_gemma":[0.00008243856,0.0002142873,0.0000579412,0.0002038093,0.00002909496,0.0002203128,0.0001109943,0.0005021574,0.00001367905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003082796,"about_ca_system_score_gemma":0.0000479312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167888,"about_ca_topic_score_gemma":0.0002479448,"domain_scores_codex":[0.9983236,0.0001313722,0.0003211779,0.0005565236,0.0002731133,0.0003942284],"domain_scores_gemma":[0.9987999,0.0001491288,0.00005520682,0.0003499164,0.0005389935,0.0001068731],"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":[0.0002483038,0.0007052236,0.007007782,0.04117031,0.0005247249,0.000002387901,0.01141016,0.819968,0.05318008,0.001448554,0.01425011,0.05008439],"study_design_scores_gemma":[0.0006236397,0.0001090992,0.002049744,0.0001624577,0.00001677222,7.620037e-7,0.0005320737,0.9936484,0.0008919952,0.0003542583,0.001384649,0.0002261973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02831101,0.0001792173,0.965125,0.0001232743,0.0002901,0.004248873,0.00007721407,0.001561612,0.00008373901],"genre_scores_gemma":[0.9455144,0.0005544051,0.04237042,0.000003356942,0.0006205974,0.006839002,0.003083674,0.0002284171,0.0007856991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9227545,"threshold_uncertainty_score":0.8738384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1668923449570311,"score_gpt":0.382446967727246,"score_spread":0.2155546227702149,"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."}}