{"id":"W3111856980","doi":"10.5121/ijsea.2020.11603","title":"A Data Extraction Algorithm from Open Source Software Project Repositories for Building Duration Estimation Models: Case Study of Github","year":2020,"lang":"en","type":"article","venue":"International Journal of Software Engineering & Applications","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Duration (music); Schedule; Computer science; Estimation; Software; Data extraction; Variable (mathematics); Work (physics); Data mining; Data science; Engineering; Systems engineering; Mathematics","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":[0.003468516,0.0008427078,0.0006072738,0.003761966,0.0007159075,0.001373474,0.00105925,0.0008902237,0.0008178237],"category_scores_gemma":[0.01612689,0.0004176483,0.0009832499,0.00457328,0.0003292855,0.002168519,0.001352038,0.001049172,0.0008074901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007928506,"about_ca_system_score_gemma":0.002400435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009077639,"about_ca_topic_score_gemma":0.01325875,"domain_scores_codex":[0.9981062,0.0005717226,0.000317737,0.0004488512,0.0004554122,0.00009999591],"domain_scores_gemma":[0.9896081,0.005989944,0.00107482,0.001155863,0.001952053,0.0002192394],"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":[0.0002513696,0.0006998143,0.08352529,0.000692581,0.00015848,0.0006767029,0.001464458,0.07403966,0.008369513,0.006706387,0.008771734,0.814644],"study_design_scores_gemma":[0.00006222801,0.0002906942,0.03527278,0.000220388,0.0001259285,0.0006933623,0.001301996,0.9149073,0.0151093,0.008508408,0.02340135,0.0001062239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1635965,0.0005056139,0.8248202,0.0006501936,0.00005540131,0.0006265491,0.004464392,0.003358915,0.001922306],"genre_scores_gemma":[0.2356749,0.0003793517,0.7533501,0.00005509114,0.00002749983,0.0007199503,0.008424677,0.0001438833,0.001224602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009077639,"threshold_uncertainty_score":0.01834345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0748553564177604,"score_gpt":0.3637761955950537,"score_spread":0.2889208391772933,"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."}}