{"id":"W4393508681","doi":"10.5281/zenodo.7570822","title":"Defectors: A Large Scale Python Dataset for Defect Prediction","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Python (programming language); Computer science; Scale (ratio); Programming language; Cartography; Geography","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":[0.001027855,0.002607749,0.0008289907,0.002899378,0.0008121182,0.0009151864,0.003655769,0.001909935,0.004807316],"category_scores_gemma":[0.003662335,0.0005781113,0.001319197,0.003381399,0.0007678461,0.001343483,0.002004963,0.002113275,0.01038004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001272712,"about_ca_system_score_gemma":0.002091918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02077182,"about_ca_topic_score_gemma":0.03625878,"domain_scores_codex":[0.9985809,0.0001407633,0.0001307677,0.000348623,0.0005949742,0.0002039513],"domain_scores_gemma":[0.9981573,0.0002553545,0.0002275723,0.0005661517,0.0005382772,0.0002552016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005380423,0.0005130732,0.01079457,0.0008487474,0.0001421177,0.0004384703,0.00009796049,0.007725004,0.003061061,0.001239668,0.9446942,0.02990693],"study_design_scores_gemma":[0.001183675,0.0007164996,0.09074788,0.0004501104,0.0002139804,0.001897727,0.0004299697,0.1059882,0.01947368,0.009599376,0.7689425,0.0003564577],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02139674,0.0003398384,0.003303738,0.0003894073,0.0001293695,0.0002136868,0.9598199,0.01169647,0.002710957],"genre_scores_gemma":[0.009157799,0.00008503093,0.003074659,0.0000806243,0.00001162639,0.0001610153,0.9863867,0.0002254735,0.0008171159],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02077182,"threshold_uncertainty_score":0.04130185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03739181245637486,"score_gpt":0.2548971986705139,"score_spread":0.2175053862141391,"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."}}