{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004095772,0.001392747,0.001135503,0.03197317,0.001649965,0.003374484,0.001728771,0.001854474,0.002654311],"category_scores_gemma":[0.03139678,0.0005642247,0.001324074,0.0115633,0.0007771438,0.008226857,0.004583142,0.001215735,0.002083841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001489408,"about_ca_system_score_gemma":0.00300103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003159337,"about_ca_topic_score_gemma":0.004679603,"domain_scores_codex":[0.9924078,0.001646835,0.001169828,0.001402604,0.002942038,0.0004310002],"domain_scores_gemma":[0.9766027,0.01146929,0.002479519,0.002776133,0.006188128,0.0004842684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003049237,0.0002298173,0.04011106,0.003721922,0.0002214207,0.001140243,0.007491906,0.004747843,0.05076054,0.03598463,0.02134693,0.8339387],"study_design_scores_gemma":[0.0001424075,0.0004091289,0.06142567,0.002606548,0.000419847,0.004592013,0.01469471,0.3228361,0.1065819,0.1349108,0.3509709,0.0004100663],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2261531,0.002925065,0.724333,0.0006666827,0.0003848079,0.001414602,0.01443517,0.01371581,0.01597179],"genre_scores_gemma":[0.2771993,0.001275516,0.6835091,0.0001997171,0.000108273,0.001437766,0.0308186,0.00102967,0.004422052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03197317,"threshold_uncertainty_score":0.0216608,"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."}}