{"id":"W2159903682","doi":"10.1145/337180.337477","title":"An evaluation of the paired comparisons method for software sizing","year":2000,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Canada; Ericsson (Canada)","funders":"","keywords":"Sizing; Computer science; Software; Reliability engineering; Engineering; Programming language; Chemistry","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05193543,0.00134857,0.001322759,0.002823339,0.001151841,0.001686619,0.002124182,0.001259352,0.005682824],"category_scores_gemma":[0.2075298,0.0006108746,0.001277962,0.002100579,0.002155327,0.001804719,0.001665202,0.00174706,0.001233656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009306224,"about_ca_system_score_gemma":0.0008751921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007879696,"about_ca_topic_score_gemma":0.0009338484,"domain_scores_codex":[0.9132049,0.06202848,0.001886987,0.005598607,0.01669038,0.0005906451],"domain_scores_gemma":[0.6489456,0.3085393,0.005781186,0.01520595,0.02076053,0.0007674152],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0156721,0.0009331625,0.02632245,0.001246009,0.001984593,0.0004390959,0.001682809,0.05349815,0.01671514,0.02896939,0.008376217,0.8441609],"study_design_scores_gemma":[0.002137269,0.02993371,0.05408683,0.000399618,0.001392298,0.003318906,0.001404344,0.717279,0.1096175,0.05186064,0.02783668,0.0007331991],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03981729,0.0005877415,0.9513083,0.0001054963,0.0005170414,0.0005550691,0.0003353684,0.001233729,0.005539913],"genre_scores_gemma":[0.4050783,0.0002653954,0.5895556,0.000137531,0.0002298804,0.001467308,0.000510881,0.0006579693,0.002097207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9480646,"threshold_uncertainty_score":0.2746641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08624099027380454,"score_gpt":0.3793092329480441,"score_spread":0.2930682426742396,"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."}}