{"id":"W3151388396","doi":"10.1109/msr.2012.6224276","title":"Inferring semantically related words from software context","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; WordNet; Java; Natural language processing; Code (set theory); Program comprehension; Software; Context (archaeology); Information retrieval; Software maintenance; Artificial intelligence; Precision and recall; Programming language; Software development; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003308625,0.0001232946,0.0001383556,0.00009949888,0.00005855772,0.0001207919,0.0007463348,0.0000893626,0.0002827342],"category_scores_gemma":[0.001206319,0.0001100039,0.00004922645,0.00037615,0.00002892741,0.0007201079,0.0004777356,0.0002587384,0.001037324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005475845,"about_ca_system_score_gemma":0.00003849182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001233159,"about_ca_topic_score_gemma":0.000005490112,"domain_scores_codex":[0.9986321,0.00003636473,0.0001902664,0.0002457721,0.0003631503,0.0005323607],"domain_scores_gemma":[0.9979238,0.001128987,0.00002117744,0.0006183471,0.00005323721,0.0002544375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004841281,0.0001438761,0.788289,0.0000205067,0.0001061965,0.00003563403,0.00392916,0.0001501398,0.0009678538,0.05439879,0.002789252,0.1491648],"study_design_scores_gemma":[0.0009048386,0.00006972772,0.9564705,0.0001115368,0.00001148099,0.0000356826,0.00009416323,0.02124352,0.005625234,0.00409785,0.0105189,0.0008165321],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2588078,0.0002653146,0.7384129,0.0002479173,0.0004565783,0.00007740812,8.152879e-7,0.001108097,0.0006231596],"genre_scores_gemma":[0.9077441,0.000003356769,0.09133751,0.0001482019,0.00007467607,0.000008105508,0.000002129879,0.00001506235,0.0006669147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6489363,"threshold_uncertainty_score":0.9997405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01850973578240976,"score_gpt":0.2570664480447397,"score_spread":0.2385567122623299,"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."}}