{"id":"W2803893519","doi":"10.1109/tse.2018.2836450","title":"Automatically Categorizing Software Technologies","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Categorization; Software; Taxonomy (biology); Domain (mathematical analysis); Phrase; Software engineering; Programming language; Natural language processing; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002859925,0.0003808086,0.0002980381,0.0007030903,0.0002896147,0.0002377394,0.001400032,0.000239435,0.00004032205],"category_scores_gemma":[0.0007272593,0.0003958175,0.0001456534,0.001424613,0.0001097409,0.0006317836,0.00002287717,0.0006962441,0.0004459377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002610036,"about_ca_system_score_gemma":0.0001121961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001150627,"about_ca_topic_score_gemma":0.000002756585,"domain_scores_codex":[0.997529,0.00002230172,0.0003592404,0.0006663765,0.000608845,0.0008142408],"domain_scores_gemma":[0.9973199,0.001067783,0.0000437973,0.00119599,0.000203744,0.0001688012],"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":[0.00004761825,0.0006571848,0.001839329,0.0006944053,0.0006103684,0.0003565901,0.00255778,0.2901714,0.007950512,0.005056173,0.002290491,0.6877682],"study_design_scores_gemma":[0.001890208,0.001608882,0.005512482,0.0008749799,0.0000773057,0.0004755338,0.0001175934,0.5456637,0.4284779,0.001149225,0.01050902,0.00364315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009862662,0.00007453973,0.9729411,0.0001210488,0.001656132,0.0002342959,0.00000737014,0.01508863,0.00001424097],"genre_scores_gemma":[0.593047,0.00001013541,0.4065838,0.00003270005,0.0000689871,0.00009620903,6.538187e-7,0.00005693705,0.0001035023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.684125,"threshold_uncertainty_score":0.9998494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01385843483838927,"score_gpt":0.2421132290283111,"score_spread":0.2282547941899218,"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."}}