{"id":"W2086221358","doi":"10.1109/52.903173","title":"Improving subjective estimates using paired comparisons","year":2001,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Research Canada","funders":"","keywords":"Computer science; Software; Scale (ratio); Sizing; Data science; Software technical review; Software development; Software engineering; Industrial engineering; Software quality; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002643254,0.0002081848,0.0002257786,0.0002040075,0.0003813985,0.0001810353,0.000918778,0.00008915974,0.00001376358],"category_scores_gemma":[0.001141237,0.0002146945,0.00008229317,0.0007905291,0.00006031314,0.0005361947,0.0003407143,0.0002777748,0.00006417042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001962178,"about_ca_system_score_gemma":0.0001550667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003541459,"about_ca_topic_score_gemma":0.00001514284,"domain_scores_codex":[0.9982308,0.00004099231,0.0002057618,0.0004936977,0.0004177892,0.0006109253],"domain_scores_gemma":[0.99791,0.0009962625,0.00006441122,0.0006828337,0.0001699615,0.0001765511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002241068,0.0001808108,0.9072621,0.0001051047,0.00009665289,0.0004464694,0.001731195,0.03289632,0.008358406,0.0002844523,0.001715579,0.04690049],"study_design_scores_gemma":[0.0008083304,0.0001533669,0.135952,0.0001366338,0.00002156469,0.0003410121,0.00005515367,0.8472916,0.01242715,0.0007640719,0.001130454,0.0009186943],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3009442,0.0001447221,0.6971081,0.00003952158,0.000494786,0.0001303673,0.000002490441,0.00112329,0.00001252898],"genre_scores_gemma":[0.7061641,0.000002721066,0.2936154,0.00003635966,0.00009498727,0.00001468642,0.000001212435,0.00002589981,0.0000446362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8143952,"threshold_uncertainty_score":0.875499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04136745351365596,"score_gpt":0.2897496913445795,"score_spread":0.2483822378309235,"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."}}