{"id":"W4411161447","doi":"10.21203/rs.3.rs-6792823/v1","title":"AI-Powered Defect Prediction: From Code Smells to Failure Forecasting","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Code (set theory); Code smell; Computer science; Artificial intelligence; Reliability engineering; Engineering; Programming language; Software quality; Software","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001545571,0.0003966291,0.0005789438,0.0009227187,0.0003059919,0.0004331874,0.0004693797,0.001071253,0.0003079689],"category_scores_gemma":[0.0006476768,0.0004044908,0.0003592296,0.0009874235,0.00003167025,0.0001024753,0.0007548122,0.003095354,0.0003059248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007298666,"about_ca_system_score_gemma":0.0002664526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001057413,"about_ca_topic_score_gemma":0.0004851501,"domain_scores_codex":[0.9962126,0.0004263142,0.000625563,0.0007985063,0.001160424,0.0007765688],"domain_scores_gemma":[0.9974365,0.0005703107,0.00005335674,0.000994275,0.0006254936,0.0003200551],"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":[0.0005547268,0.0001104346,0.002420994,0.004568237,0.001163574,0.0001879604,0.003089046,0.343971,0.004622175,0.0001990774,0.5717707,0.067342],"study_design_scores_gemma":[0.002113023,0.0007690164,0.002217216,0.01674835,0.0001346493,0.00002027178,0.001851191,0.2025208,0.01732076,0.002990247,0.7515941,0.001720375],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6396596,0.00830887,0.1540719,0.002928297,0.03685742,0.02303437,0.02400495,0.008808834,0.1023257],"genre_scores_gemma":[0.9948905,0.00005539148,0.0004959456,0.00003088712,0.002494139,0.0005550199,0.0002908642,0.00008562473,0.001101686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3552308,"threshold_uncertainty_score":0.9998407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09121409264941353,"score_gpt":0.3609533087397981,"score_spread":0.2697392160903846,"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."}}