{"id":"W4406242411","doi":"10.3390/jimaging11010017","title":"Supervised and Self-Supervised Learning for Assembly Line Action Recognition","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Extractor; Construct (python library); Artificial intelligence; Scalability; Semi-supervised learning; Supervised learning; Machine learning; Feature (linguistics); Action recognition; Action (physics); Line (geometry); Pattern recognition (psychology); Database; Artificial neural network; Process engineering","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":[0.00210307,0.00008194504,0.0002116569,0.0003239302,0.0007529931,0.00002021956,0.00007225138,0.00007095413,0.00005652308],"category_scores_gemma":[0.001147506,0.00007140179,0.00006659132,0.0002027948,0.00001484884,0.000347682,0.00003364239,0.0007714446,0.00001092444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000174419,"about_ca_system_score_gemma":0.0006831966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002888992,"about_ca_topic_score_gemma":0.0000106813,"domain_scores_codex":[0.9983875,0.0003685051,0.0006070499,0.0001116683,0.0002129063,0.0003123393],"domain_scores_gemma":[0.9969654,0.001591157,0.000248806,0.00006011327,0.0009996683,0.0001348472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001536133,0.0001519229,0.238365,0.002043384,0.00007130755,0.000007515559,0.001148846,0.00003132482,0.004580002,0.0001478779,0.004055248,0.7478614],"study_design_scores_gemma":[0.0196865,0.001102623,0.5473188,0.004272605,0.0002778175,0.00006802109,0.01197025,0.3127578,0.001284761,0.008778431,0.09197692,0.000505413],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9459939,0.0009096363,0.03057374,0.01692235,0.001260833,0.0009211563,0.000008151076,0.00005225002,0.003358002],"genre_scores_gemma":[0.9846322,0.0009601262,0.01165165,0.001336841,0.0007941506,0.00004475596,0.00002227188,0.0000181488,0.0005398538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.747356,"threshold_uncertainty_score":0.5791491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042314281830432,"score_gpt":0.4836934385098482,"score_spread":0.379462010326805,"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."}}