{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00191372,0.00005846074,0.00008785352,0.00003891853,0.00007983516,0.00004396877,0.0007947113,0.00003048133,0.00009096274],"category_scores_gemma":[0.0006690716,0.00004140574,0.00005271395,0.0003088676,0.00001525655,0.0001851847,0.00004920662,0.0000592923,0.000005380987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003991345,"about_ca_system_score_gemma":0.0001089358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004534288,"about_ca_topic_score_gemma":0.0000117922,"domain_scores_codex":[0.9988198,0.0001782993,0.0001291276,0.0001887014,0.0005217902,0.0001623069],"domain_scores_gemma":[0.9981651,0.000933967,0.00002354508,0.0006214935,0.0002147198,0.0000411499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005116168,0.00007569636,0.007796318,0.00001983956,0.00001872833,9.236076e-8,0.0005827696,0.0940571,0.001040838,0.001931539,0.001827999,0.892644],"study_design_scores_gemma":[0.0002419329,0.00003909552,0.04028536,0.000008870518,0.000007504389,0.000001278063,0.00001140851,0.9507204,0.006912298,0.0009298989,0.0007819522,0.0000599827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03315434,0.0000422735,0.9658412,0.0002437811,0.00008461822,0.000352007,0.000001637256,0.0001786965,0.0001014778],"genre_scores_gemma":[0.4532943,3.550029e-7,0.5465267,0.00003150408,0.00001474584,0.00003611402,7.912579e-7,0.00000475138,0.00009072531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.892584,"threshold_uncertainty_score":0.1688477,"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."}}