{"id":"W26774929","doi":"10.1007/978-3-642-21233-8_4","title":"Evaluation of Software Process Assessment Methods – Case Study","year":2011,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Implementation; Process (computing); Software; Set (abstract data type); Evaluation methods; Software implementation; Software engineering; Reliability engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02222862,0.001082586,0.0007370886,0.003399938,0.00142352,0.00220895,0.002436984,0.002568464,0.002178562],"category_scores_gemma":[0.04837197,0.000659186,0.0009304091,0.002639017,0.001125291,0.002217048,0.001979464,0.0009045234,0.0005739926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002536211,"about_ca_system_score_gemma":0.00146637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001308374,"about_ca_topic_score_gemma":0.001968792,"domain_scores_codex":[0.9587414,0.03006284,0.002175131,0.001232614,0.006978082,0.0008098863],"domain_scores_gemma":[0.9199814,0.05688089,0.002989192,0.004968529,0.01444739,0.0007326512],"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":[0.007351963,0.0308753,0.03498843,0.005332453,0.0005200561,0.002654122,0.02174539,0.02764379,0.04236311,0.01233944,0.003327126,0.8108588],"study_design_scores_gemma":[0.003596661,0.1049536,0.1113269,0.005731339,0.002554696,0.01018448,0.03500476,0.3021353,0.3299642,0.01928276,0.07442544,0.0008400397],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9090499,0.001783977,0.07053111,0.0002485053,0.00006182389,0.002673524,0.0001494941,0.000165806,0.01533578],"genre_scores_gemma":[0.9295102,0.0007391621,0.06618211,0.00007055159,0.00002846709,0.0008527219,0.0001467328,0.00004799103,0.002422146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02222862,"threshold_uncertainty_score":0.1175576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1674171664530736,"score_gpt":0.4624608992862835,"score_spread":0.2950437328332099,"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."}}