{"id":"W2061072593","doi":"10.1007/s10664-013-9264-x","title":"SWordNet: Inferring semantically related words from software context","year":2013,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; WordNet; Program comprehension; Information retrieval; Software; Context (archaeology); Java; Ranking (information retrieval); Natural language processing; Code (set theory); Precision and recall; Software maintenance; Artificial intelligence; Software development; Programming language; Software system","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003405247,0.0005750731,0.000616674,0.000371074,0.0001585595,0.000568375,0.001855595,0.0003756879,0.0005158201],"category_scores_gemma":[0.006343603,0.0005763877,0.0002349484,0.001374399,0.00006555812,0.001196446,0.001002056,0.001144083,0.00171623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002917064,"about_ca_system_score_gemma":0.0001196143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002936347,"about_ca_topic_score_gemma":0.000006110088,"domain_scores_codex":[0.9958898,0.00006979508,0.0007592578,0.001049811,0.0009430879,0.001288232],"domain_scores_gemma":[0.9937361,0.003930639,0.00008669266,0.001334375,0.0001891409,0.000723045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008506382,0.0002010181,0.8780437,0.0001475997,0.0003430773,0.0003128956,0.002398796,0.02836216,0.0009444081,0.0006480292,0.006907315,0.08168252],"study_design_scores_gemma":[0.001058283,0.0001441287,0.8967381,0.0003768,0.00002382016,0.00006268504,0.0000300129,0.08654048,0.001037344,0.002341302,0.01001069,0.001636404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3989303,0.0004435345,0.5955923,0.0004555904,0.0006725201,0.0003178236,0.000005164055,0.003562907,0.00001988247],"genre_scores_gemma":[0.8508537,0.00001167606,0.1480193,0.0003630594,0.0002106942,0.0001472022,0.00002020675,0.0001174693,0.0002566418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4519234,"threshold_uncertainty_score":0.9996688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01656489003974,"score_gpt":0.2521907926293967,"score_spread":0.2356259025896567,"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."}}