{"id":"W2589239371","doi":"10.71781/10596","title":"Software stability assessment using multiple prediction models","year":2003,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Stability (learning theory); Computer science; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003014177,0.0005470586,0.0008340518,0.0002330606,0.0009123144,0.002235753,0.00235166,0.0006237901,0.002990468],"category_scores_gemma":[0.0009132619,0.0005789681,0.0003845588,0.001230032,0.0001764286,0.002832792,0.0007092116,0.000983969,0.0001978694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001029089,"about_ca_system_score_gemma":0.003140618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002595585,"about_ca_topic_score_gemma":0.001414471,"domain_scores_codex":[0.9935942,0.001130746,0.001089004,0.001970561,0.001402085,0.0008134167],"domain_scores_gemma":[0.9955358,0.000765276,0.000459787,0.001622813,0.001230231,0.0003861294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001440654,0.002774764,0.07959821,0.0006156053,0.000614586,0.0000587474,0.01078287,0.1215126,0.002475665,0.0004075229,0.0001303742,0.7808849],"study_design_scores_gemma":[0.0006444777,0.0001443868,0.003160229,0.0003627909,0.0001718783,0.00001007093,0.001518169,0.9867554,0.002599856,0.00137462,0.002698975,0.0005591574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4022652,0.000347732,0.5924784,0.00008095454,0.0009325755,0.001386177,0.0002202635,0.00000994008,0.002278705],"genre_scores_gemma":[0.4186397,0.0001356822,0.572466,0.00002835519,0.000120437,0.0001303537,0.001114281,0.00005778602,0.00730742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8652427,"threshold_uncertainty_score":0.9996662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1653782328543069,"score_gpt":0.3908664435388779,"score_spread":0.2254882106845709,"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."}}