{"id":"W7125651587","doi":"10.1109/cascon66301.2025.00065","title":"Design, Implementation and Evaluation of a Novel Programming Language Topic Classification Workflow","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Workflow; Natural language; Feature (linguistics); Semantics (computer science)","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":[0.009836649,0.00108847,0.001001603,0.002008824,0.001161017,0.005806324,0.004155999,0.001308355,0.007859108],"category_scores_gemma":[0.02590121,0.001285224,0.001283566,0.001468453,0.001063043,0.005351818,0.003009817,0.002655248,0.004644043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001774238,"about_ca_system_score_gemma":0.006316157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008984847,"about_ca_topic_score_gemma":0.00793487,"domain_scores_codex":[0.9946373,0.001261196,0.0007625119,0.001252764,0.001734182,0.0003519921],"domain_scores_gemma":[0.9809585,0.00868226,0.0007873717,0.003674383,0.004630998,0.001266488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003948678,0.002454316,0.01117008,0.001628087,0.0005142643,0.0004365212,0.002826788,0.01138458,0.1164665,0.0212242,0.03881135,0.7891346],"study_design_scores_gemma":[0.001865379,0.001812291,0.005922841,0.0002942853,0.0004050404,0.0004510419,0.001137484,0.5888088,0.2703708,0.01921896,0.1093833,0.0003297352],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02594831,0.0002259364,0.8631652,0.0006138855,0.0002175456,0.002149703,0.001040373,0.1047103,0.001928684],"genre_scores_gemma":[0.09780779,0.0001725129,0.8879589,0.00036789,0.00005468588,0.001016105,0.002845852,0.005838058,0.003938199],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009836649,"threshold_uncertainty_score":0.05202174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.101550596063577,"score_gpt":0.4085119845939995,"score_spread":0.3069613885304225,"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."}}