{"id":"W1998420836","doi":"10.1145/979743.979751","title":"Report on the First International Workshop on Comparative Evaluation in Requirements Engineering","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Requirements engineering; Computer science; Engineering management; Engineering; Management science; Engineering ethics; Systems engineering; Software","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001064713,0.0003338426,0.0002335292,0.0003398782,0.00009461659,0.0001612693,0.001502924,0.0001190078,0.00002007352],"category_scores_gemma":[0.07062853,0.0002875784,0.00008648184,0.0006270192,0.00001544987,0.0006008312,0.000301955,0.0005238433,0.00003709534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004374984,"about_ca_system_score_gemma":0.0000601176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003218483,"about_ca_topic_score_gemma":0.000006964315,"domain_scores_codex":[0.9978566,0.00002448693,0.0004168499,0.0005423306,0.0007893444,0.0003704289],"domain_scores_gemma":[0.9768477,0.02155399,0.0001531395,0.001249054,0.0001188898,0.00007723195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00002129026,0.0001673824,0.01545783,0.00002961298,0.00008058722,0.0001604813,0.00090466,0.9687424,0.0001535048,0.01010123,0.0005274987,0.003653495],"study_design_scores_gemma":[0.004504634,0.0009124689,0.6737506,0.006077528,0.0001018431,0.0004349701,0.00007149002,0.1953073,0.04020016,0.003126495,0.07127351,0.004239005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2428546,0.0003017538,0.7420623,0.008025168,0.002948476,0.001064581,0.000007581805,0.002677198,0.00005837076],"genre_scores_gemma":[0.9198624,0.00002149919,0.07943784,0.0002625908,0.0001428056,0.0002167119,0.00001651921,0.00003229379,0.000007342282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7734351,"threshold_uncertainty_score":0.9999576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07222270662731178,"score_gpt":0.3246901087089216,"score_spread":0.2524674020816098,"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."}}