{"id":"W4384305065","doi":"10.1109/icse48619.2023.00008","title":"Artifact Evaluation","year":2023,"lang":"en","type":"article","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; University of Calgary; University of Victoria","funders":"","keywords":"Artifact (error); Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002666012,0.00141065,0.0007997783,0.004630338,0.0006200993,0.001880226,0.001098351,0.0009160631,0.02064287],"category_scores_gemma":[0.009480271,0.0001971653,0.001048685,0.001809801,0.0003264619,0.0009203483,0.001167947,0.0004170084,0.00850857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007060452,"about_ca_system_score_gemma":0.001262069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003903334,"about_ca_topic_score_gemma":0.006470168,"domain_scores_codex":[0.9956067,0.000633597,0.000358957,0.0005361005,0.002560929,0.0003038133],"domain_scores_gemma":[0.9906284,0.001052759,0.0003602279,0.001466602,0.006135961,0.0003560279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0016292,0.0008933214,0.02088447,0.0008115812,0.0002472163,0.0005209924,0.0001477541,0.006805919,0.04418997,0.00210723,0.03933994,0.8824224],"study_design_scores_gemma":[0.0005007022,0.004296075,0.1536144,0.000680394,0.001283385,0.00545464,0.0008563343,0.224565,0.3372868,0.005510504,0.2655902,0.0003616183],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.3612196,0.005528475,0.4108132,0.0007204005,0.00149358,0.005844314,0.02748439,0.02239609,0.1645],"genre_scores_gemma":[0.6726401,0.001540033,0.1782799,0.0005030899,0.000228254,0.001209085,0.04452688,0.002525285,0.09854738],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02064287,"threshold_uncertainty_score":0.06905729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05296498364968949,"score_gpt":0.2729635184845244,"score_spread":0.2199985348348349,"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."}}