{"id":"W7135874681","doi":"","title":"Can Genetic Programming improve Software Effort Estimation? A Comparative Evaluation","year":2005,"lang":"en","type":"book-chapter","venue":"Explore Bristol Research","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Software; Genetic programming; Software development; Software metric; Variety (cybernetics); Set (abstract data type); Software sizing; Software construction","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003492606,0.000611469,0.0006737729,0.00136314,0.000522661,0.0007830289,0.00267352,0.0004683757,0.0001983552],"category_scores_gemma":[0.001679907,0.0006509938,0.0002172218,0.0005543159,0.0004068283,0.0004855037,0.001264132,0.002297519,0.001026934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002143488,"about_ca_system_score_gemma":0.002149368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001146966,"about_ca_topic_score_gemma":0.00008989298,"domain_scores_codex":[0.9903138,0.0002170759,0.0007271631,0.001609061,0.005796616,0.001336289],"domain_scores_gemma":[0.9928755,0.001552867,0.0002113546,0.002114613,0.002720469,0.0005251574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002987777,0.0001036914,0.0001398159,0.0002542392,0.0001850321,0.0001673617,0.003839065,0.003587226,0.0000227428,0.008238322,0.01234262,0.97109],"study_design_scores_gemma":[0.003101226,0.00244081,0.004298623,0.002112055,0.0001477284,0.0002518406,0.0002574719,0.5577956,0.0008912528,0.06368706,0.3608735,0.004142905],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005459495,0.01743953,0.8910787,0.004018665,0.002794802,0.02424119,0.0001989036,0.004605657,0.0501631],"genre_scores_gemma":[0.1682509,0.0003307076,0.5874438,0.0000844907,0.002162962,0.005366751,0.0005670167,0.0005592813,0.2352341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9669471,"threshold_uncertainty_score":0.9997509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1558776972647941,"score_gpt":0.3972212044288398,"score_spread":0.2413435071640457,"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."}}