{"id":"W4393790493","doi":"10.5281/zenodo.6459607","title":"Artifact for \"Identifying Concepts in Software Projects\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Engineering Education and Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Artifact (error); Computer science; Software; Software engineering; Artificial intelligence; Data science; Programming language","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":[0.002141025,0.002094431,0.001166505,0.004808363,0.001062473,0.002836086,0.002510995,0.002379021,0.05545346],"category_scores_gemma":[0.0118579,0.0006560983,0.001462585,0.005922105,0.0005823358,0.001405772,0.00325136,0.002105656,0.07291893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001634246,"about_ca_system_score_gemma":0.003302016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434506,"about_ca_topic_score_gemma":0.02638986,"domain_scores_codex":[0.9974517,0.0006009238,0.0003750453,0.0006219227,0.0006031774,0.0003471462],"domain_scores_gemma":[0.9932566,0.002398285,0.0006963388,0.001862202,0.001249996,0.0005365859],"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":[0.00007380029,0.00004101549,0.001085124,0.0007400335,0.00002980789,0.00002554869,0.00004055458,0.0002077628,0.0001416072,0.0006787151,0.9939852,0.002950911],"study_design_scores_gemma":[0.0003230301,0.00002615964,0.006734632,0.0003379309,0.00003591229,0.00008743102,0.0001176797,0.0005528852,0.0004240323,0.001879451,0.9894498,0.00003091567],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002259292,0.00004573644,0.0002133782,0.0000756043,0.00004518174,0.00002371764,0.9982607,0.0003961535,0.0007136468],"genre_scores_gemma":[0.0004359644,0.00002790621,0.0004675702,0.00004459272,0.000008469448,0.0001168442,0.9984025,0.00005947967,0.0004365875],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05545346,"threshold_uncertainty_score":0.1855103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07316871453233603,"score_gpt":0.3143151567044254,"score_spread":0.2411464421720894,"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."}}