{"id":"W3022019328","doi":"10.17613/0qq4-xp47","title":"A comparison of top-down and bottom-up approaches to recognizing component assemblies in image mining electronic circuits","year":2020,"lang":"en","type":"article","venue":"Humanities Commons CORE (Modern Language Association / Columbia University)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Top-down and bottom-up design; Component (thermodynamics); Computer science; Electronic circuit; Artificial intelligence; Data mining; Engineering; Electrical engineering; Physics; Software 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":[0.0002199412,0.0001430527,0.0004213749,0.0002768851,0.0001612653,0.0001289574,0.00014562,0.000150028,0.00003124919],"category_scores_gemma":[0.00009389767,0.0002227264,0.00006575036,0.0004561002,0.00002091191,0.0002335747,0.00007893857,0.0003329556,0.00000417139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005474758,"about_ca_system_score_gemma":0.00003468055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008129962,"about_ca_topic_score_gemma":0.01062254,"domain_scores_codex":[0.9988326,0.0001194022,0.0003074738,0.0002144854,0.0002265733,0.0002994922],"domain_scores_gemma":[0.9993806,0.0001950273,0.0001648791,0.0001227974,0.00006373884,0.00007291524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003157161,0.0003892814,0.3835326,0.001083202,0.0009873079,0.0001543425,0.4324797,0.00700014,0.09558848,0.003219991,0.01028106,0.06496814],"study_design_scores_gemma":[0.01285125,0.002132541,0.110137,0.001229265,0.0006329796,0.00002516236,0.5343271,0.2850921,0.01608798,0.000281011,0.03330162,0.003901936],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910648,0.0001511085,0.0014336,0.00004660636,0.0001261131,0.0003404019,0.00004107059,0.000185456,0.006610886],"genre_scores_gemma":[0.999249,0.000007173305,0.00007681042,0.00002809734,0.00006102854,0.000003705674,0.00002870769,0.00002453116,0.0005209674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.278092,"threshold_uncertainty_score":0.9082521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031613896165299,"score_gpt":0.2353524128005987,"score_spread":0.1321910231840688,"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."}}