{"id":"W2771158352","doi":"10.1002/smr.1925","title":"Evaluating Pred(<i>p</i>) and standardized accuracy criteria in software development effort estimation","year":2017,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Measure (data warehouse); Consistency (knowledge bases); Software; Computer science; Estimation; Statistics; Data mining; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001991824,0.000152763,0.0002708271,0.0002671102,0.0004003722,0.0005426845,0.000576806,0.00008178617,0.000005793619],"category_scores_gemma":[0.01010893,0.0001371484,0.00003010194,0.0001487269,0.00006816226,0.002006199,0.0002356785,0.0002862456,0.000001351279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001714126,"about_ca_system_score_gemma":0.0005552112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007513862,"about_ca_topic_score_gemma":0.000004554631,"domain_scores_codex":[0.9982844,0.00004754287,0.0005008011,0.000244003,0.000663011,0.0002602699],"domain_scores_gemma":[0.9980813,0.0004848857,0.0004556417,0.0002708227,0.0005524046,0.0001550039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000197006,0.00009086449,0.4555809,0.0008124809,0.00005451465,0.00005977325,0.004241484,0.002835023,0.0001804862,0.0001368467,0.0002069737,0.5356037],"study_design_scores_gemma":[0.002253738,0.0002343856,0.95543,0.0008674515,0.0000124354,0.0002741451,0.00004706817,0.03609874,0.0006620685,0.003620813,0.0002119404,0.0002871703],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4493586,0.0006522081,0.5494996,0.0001189934,0.000208328,0.0001141309,0.000001259762,0.00004424734,0.000002634682],"genre_scores_gemma":[0.7228336,0.00003325956,0.2770375,0.00001472797,0.00004856951,0.000009515163,7.374443e-7,0.00000909226,0.00001297926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5353165,"threshold_uncertainty_score":0.9982293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03990346991028516,"score_gpt":0.3796051154684074,"score_spread":0.3397016455581222,"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."}}