{"id":"W4321787049","doi":"10.1007/s10664-022-10272-w","title":"Semantically-enhanced topic recommendation systems for software projects","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Metadata; Recommender system; Software; Information retrieval; World Wide Web; Software engineering; Data science; Programming language","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006755839,0.0003126631,0.0003586822,0.0004339781,0.0002026387,0.000403869,0.0008503777,0.0001921901,0.00001190428],"category_scores_gemma":[0.008461006,0.0003160505,0.0001438064,0.001708315,0.00002261323,0.0004720687,0.0003786173,0.0003476564,0.0001887864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002193734,"about_ca_system_score_gemma":0.0001282431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009882524,"about_ca_topic_score_gemma":6.682448e-7,"domain_scores_codex":[0.9973806,0.00004154663,0.0004256079,0.0007293376,0.0004704323,0.0009525007],"domain_scores_gemma":[0.9952188,0.003640199,0.00005601467,0.0006197763,0.0002049122,0.000260255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008777827,0.0005038369,0.1883273,0.006749321,0.0006954838,0.0002494555,0.005941414,0.5227684,0.003547462,0.004452484,0.1414987,0.1251783],"study_design_scores_gemma":[0.001870905,0.0005124439,0.1146839,0.0004733395,0.00002979203,0.00005044511,0.00005195553,0.7572559,0.00363045,0.0004656432,0.1190472,0.00192802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05514125,0.00009515486,0.9356018,0.0005768944,0.001733508,0.0007684829,0.00001207366,0.006062954,0.000007913521],"genre_scores_gemma":[0.7620701,0.00004961091,0.2336604,0.0002046573,0.0009495391,0.001611043,0.0001671987,0.0001994828,0.001088065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7069288,"threshold_uncertainty_score":0.9999291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05002282827660898,"score_gpt":0.3143586557869092,"score_spread":0.2643358275103002,"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."}}