{"id":"W7125917544","doi":"10.1109/ase63991.2025.00286","title":"From Technical Excellence to Practical Adoption: Lessons Learned Building an ML-Enhanced Trace Analysis Tool","year":2025,"lang":"","type":"article","venue":"","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Polytechnique Montréal","funders":"","keywords":"Excellence; TRACE (psycholinguistics); Quality (philosophy); Automation; Eclipse; Tracing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.08597608,0.001146633,0.000689037,0.002771332,0.002761407,0.0140218,0.004826718,0.003796203,0.002792838],"category_scores_gemma":[0.1547361,0.0009597849,0.0007872371,0.001615678,0.01003777,0.02786417,0.0105767,0.007024892,0.001128098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006326014,"about_ca_system_score_gemma":0.01283846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003908042,"about_ca_topic_score_gemma":0.005337863,"domain_scores_codex":[0.9449883,0.03640365,0.002838357,0.002930131,0.009749415,0.00309019],"domain_scores_gemma":[0.798206,0.1470885,0.004294425,0.01784334,0.0255006,0.007067155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002344233,0.001415847,0.03863223,0.002504383,0.0001159554,0.002297731,0.1576383,0.005604664,0.009053173,0.1349282,0.01232591,0.6352493],"study_design_scores_gemma":[0.0002846387,0.003285055,0.02354927,0.008736757,0.0003922567,0.004150176,0.1935061,0.05334704,0.03462088,0.2970687,0.380442,0.0006171712],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3714089,0.003539936,0.4745928,0.106138,0.0005053928,0.0007440684,0.0001115173,0.002492666,0.04046677],"genre_scores_gemma":[0.7021211,0.00242436,0.2869407,0.003011692,0.0001380575,0.0003163574,0.0001641646,0.0008063391,0.004077244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08597608,"threshold_uncertainty_score":0.4546904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1118961205184801,"score_gpt":0.4915172925986233,"score_spread":0.3796211720801432,"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."}}