{"id":"W4285385081","doi":"10.5753/bresci.2022.222815","title":"Towards an Open Science-Based Framework for Software Engineering Controlled (Quasi-)Experiments","year":2022,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Metadata; Computer science; Scripting language; Software engineering; Software; Data science; Open science; Software evolution; Software development; Social software engineering; Work (physics); World Wide Web; Software construction; Engineering","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","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01738804,0.000160747,0.0003803745,0.0006043033,0.001504792,0.003125906,0.007971449,0.00002360875,0.002636219],"category_scores_gemma":[0.01220008,0.0001226209,0.0001094168,0.002104188,0.0001052899,0.0006696247,0.003935712,0.0001298558,0.00004295058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001629093,"about_ca_system_score_gemma":0.0004330984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007430949,"about_ca_topic_score_gemma":0.000003871554,"domain_scores_codex":[0.994775,0.0001206887,0.0006013212,0.001315075,0.002687677,0.0005002433],"domain_scores_gemma":[0.9958735,0.001468783,0.0001927426,0.001928795,0.0002945948,0.0002415473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001831175,0.0028544,0.002453607,0.00001788564,0.00009949889,0.00002251095,0.002290424,0.1841546,0.001359282,0.4067156,0.09553095,0.3026701],"study_design_scores_gemma":[0.005428534,0.0009041604,0.001102787,0.00001318629,0.00001639209,0.000001849496,0.002872764,0.8268231,0.001245091,0.03352044,0.1275892,0.0004825324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03735057,0.0000236175,0.9551824,0.0007273019,0.00311472,0.001495336,0.00006826554,0.0001863746,0.001851394],"genre_scores_gemma":[0.6841893,8.000873e-8,0.3123652,0.001041777,0.00006156709,0.0004068983,0.00002006759,0.00001343939,0.001901651],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6468387,"threshold_uncertainty_score":0.9997951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1597315417575663,"score_gpt":0.4327761347860162,"score_spread":0.2730445930284499,"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."}}