{"id":"W4235970556","doi":"10.1007/s10664-021-10009-1","title":"Conclusion stability for natural language based mining of design discussions","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Artifact (error); Code refactoring; Computer science; Relevance (law); Task (project management); Context (archaeology); Documentation; Stability (learning theory); Software; Machine learning; Artificial intelligence; Data mining; Software engineering; Engineering; Programming language; Systems engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005039414,0.0001895501,0.0002855264,0.000116147,0.00008472801,0.00005648692,0.0005340473,0.00009398717,0.00003063654],"category_scores_gemma":[0.009141325,0.0001668552,0.0001563647,0.0007161945,0.00002600079,0.000196361,0.0003532524,0.0002307888,0.00000252922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001251807,"about_ca_system_score_gemma":0.0001973307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003138284,"about_ca_topic_score_gemma":8.812921e-7,"domain_scores_codex":[0.998331,0.00006825256,0.0003027741,0.0004469288,0.0004067869,0.0004443322],"domain_scores_gemma":[0.993813,0.005165726,0.00004272939,0.0006088945,0.0002002684,0.0001693467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001661353,0.001089949,0.1990151,0.002371127,0.0003251683,0.0005374586,0.01121836,0.5244576,0.1704056,0.0006019215,0.009910828,0.0799008],"study_design_scores_gemma":[0.001003262,0.0001804506,0.04211508,0.0001903202,0.00001519536,0.0000162398,0.00007743159,0.776938,0.1773587,0.00004016877,0.001517003,0.0005480878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1546725,0.000469575,0.8434724,0.0002871872,0.0003759097,0.0002037237,0.00001047795,0.0005065912,0.000001673626],"genre_scores_gemma":[0.5888748,5.815162e-7,0.4109587,0.00003255417,0.00004048151,0.00003288009,0.00001189351,0.00001949769,0.00002866669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4342023,"threshold_uncertainty_score":0.9992051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04044770805115119,"score_gpt":0.3104229520862787,"score_spread":0.2699752440351275,"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."}}