{"id":"W1967515268","doi":"10.1191/0142331204tm0104oa","title":"Predicting safety and quality of thermally processed canned foods using a neural network","year":2004,"lang":"en","type":"article","venue":"Transactions of the Institute of Measurement and Control","topic":"Meat and Animal Product Quality","field":"Agricultural and Biological Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Artificial neural network; Sensitivity (control systems); Thermal diffusivity; Dependency (UML); Feedforward neural network; Feed forward; Process (computing); Statistics; Approximation error; Computer science; Mean squared prediction error; Mathematics; Artificial intelligence; Engineering; Physics; Control engineering; Thermodynamics","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":[0.0008608081,0.00008640689,0.0002383883,0.000005304983,0.0001988705,0.000008494228,0.0001123886,0.00003834851,0.000005846567],"category_scores_gemma":[0.00004111224,0.00003397168,0.00007728679,0.0001300561,0.0001710433,0.0001361031,0.000006563273,0.00007101491,1.733637e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001254638,"about_ca_system_score_gemma":0.00003095094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001893852,"about_ca_topic_score_gemma":0.00294498,"domain_scores_codex":[0.9990447,0.00007847182,0.000367771,0.000124703,0.0002734011,0.0001110152],"domain_scores_gemma":[0.9995188,0.00002635146,0.0002150761,0.00005296952,0.0001537133,0.00003316636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000604447,0.0001024318,0.01004304,0.0001307751,0.00008214429,5.931354e-8,0.0001552803,0.008166139,0.9718721,0.0003331133,1.76777e-7,0.008510286],"study_design_scores_gemma":[0.004946724,0.0009111587,0.8891124,0.0006240321,0.0004548666,0.000006783411,0.0006246052,0.001942826,0.09930781,0.001540099,0.0001449938,0.0003837777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974851,0.0004316209,0.000816069,0.0008006845,0.0000887427,0.0002751489,0.00002176402,0.000008846504,0.00007204586],"genre_scores_gemma":[0.9998034,0.00002013285,0.00009216161,0.00002790774,0.00004931009,0.000002261936,5.277048e-7,5.895001e-7,0.000003699571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8790693,"threshold_uncertainty_score":0.2862951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07749762375600149,"score_gpt":0.2500560589637011,"score_spread":0.1725584352076996,"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."}}