{"id":"W4417098842","doi":"10.48550/arxiv.2508.01430","title":"From Technical Excellence to Practical Adoption: Lessons Learned Building an ML-Enhanced Trace Analysis Tool","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Excellence; TRACE (psycholinguistics); Quality (philosophy); Automation; Eclipse; Tracing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08540995,0.0009581294,0.0005999846,0.002622057,0.002801766,0.01343145,0.004205162,0.003615604,0.0026353],"category_scores_gemma":[0.1513188,0.0008280149,0.0006893171,0.001578008,0.01094636,0.02606321,0.0101709,0.00674321,0.001031185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006730703,"about_ca_system_score_gemma":0.01263216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003648598,"about_ca_topic_score_gemma":0.004538846,"domain_scores_codex":[0.9426925,0.03991912,0.002590962,0.002707808,0.009235132,0.002854439],"domain_scores_gemma":[0.7875506,0.1591355,0.004347031,0.01799116,0.0244594,0.006516346],"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":[0.0001988808,0.001187269,0.03874629,0.002021654,0.0001052232,0.00188145,0.1457908,0.005773214,0.007439711,0.1874032,0.01167695,0.5977754],"study_design_scores_gemma":[0.0002130312,0.002197031,0.02121147,0.006560262,0.000287959,0.002865122,0.1589149,0.05064525,0.02751514,0.3772189,0.351921,0.0004498003],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3629098,0.003454381,0.4563551,0.1255834,0.0004793228,0.0006165218,0.00009792383,0.001983606,0.04851999],"genre_scores_gemma":[0.7611489,0.002322396,0.2281768,0.003049042,0.0001443366,0.0002823427,0.0001295176,0.0006510553,0.004095613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08540995,"threshold_uncertainty_score":0.4516964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2115964489550482,"score_gpt":0.4956994976843678,"score_spread":0.2841030487293196,"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."}}