{"id":"W4403441540","doi":"10.1016/j.mfglet.2024.09.160","title":"Hierarchical robot learning method for industrial fluorescent penetrant inspection","year":2024,"lang":"en","type":"article","venue":"Manufacturing Letters","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"ING Robotic Aviation","funders":"Office of the Secretary of Defense; Arm","keywords":"Penetrant (biochemical); Artificial intelligence; Robot; Computer science; Fluorescence; Computer vision; Engineering; Biology; Biotechnology; Physics; Optics","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":[0.000266331,0.0001826024,0.0001564034,0.0002330322,0.000153002,0.0001991829,0.00009269817,0.0001041608,0.00006915317],"category_scores_gemma":[0.00002624353,0.0001833569,0.0001237993,0.00008975496,0.00001568618,0.000133632,0.00001898014,0.0007398755,0.00004891969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001450998,"about_ca_system_score_gemma":0.000006877748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002218208,"about_ca_topic_score_gemma":0.000003344688,"domain_scores_codex":[0.9989793,0.00005058996,0.0002236333,0.0002666799,0.0001628421,0.0003169468],"domain_scores_gemma":[0.9996367,0.0001647522,0.00001680284,0.0001034587,0.000005285692,0.0000730676],"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":[0.0000137101,0.000003393255,0.00005797894,0.0000978597,0.00005131359,0.00001192761,0.000314664,0.9298141,0.02646981,0.00008092527,0.0024138,0.04067054],"study_design_scores_gemma":[0.0004254517,0.00003411482,0.002666168,0.0001022508,0.00003384606,0.00001823188,0.00003560009,0.8720509,0.05358765,0.00003928368,0.07068923,0.0003172584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1310515,0.00008636329,0.863224,0.001447505,0.001830571,0.0002578467,6.837614e-7,0.001853436,0.0002480227],"genre_scores_gemma":[0.9905837,0.000007998248,0.00797698,0.0001698883,0.001016498,0.00003387321,0.00003313461,0.00007498357,0.0001029369],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8595322,"threshold_uncertainty_score":0.7477078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02703823608565987,"score_gpt":0.2573461736067439,"score_spread":0.2303079375210841,"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."}}