{"id":"W6893163416","doi":"10.5281/zenodo.13685828","title":"LTM: Scalable and Black-box Similarity-based Test Suite Minimization based on Language Models - Replication Package","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University; University of Ottawa","funders":"","keywords":"Test suite; Python (programming language); Scalability; Suite; Minification; Directory; Source code; Replication (statistics)","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":[0.00484275,0.00230452,0.001353395,0.002496853,0.0006455182,0.002135509,0.004548356,0.001449679,0.02579948],"category_scores_gemma":[0.02751211,0.001123304,0.003132258,0.001300607,0.0008742831,0.003213372,0.003655833,0.002527323,0.01437781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001352881,"about_ca_system_score_gemma":0.003806814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00335639,"about_ca_topic_score_gemma":0.003712239,"domain_scores_codex":[0.9933303,0.001781418,0.0005446456,0.0009825284,0.002904595,0.0004565442],"domain_scores_gemma":[0.9900252,0.003428801,0.0008233553,0.003238908,0.00213863,0.0003452144],"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":[0.001142306,0.0005656536,0.008047931,0.001422722,0.0004561725,0.000558676,0.0002815427,0.159676,0.02922136,0.03027186,0.2745191,0.4938367],"study_design_scores_gemma":[0.0003488903,0.0004286324,0.001784562,0.0001115162,0.0000860391,0.0004579702,0.00009132065,0.8960101,0.02542238,0.03996738,0.03519163,0.00009955451],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.006180253,0.000221545,0.7895635,0.0003684614,0.000118909,0.0007533114,0.004822723,0.1937484,0.004222842],"genre_scores_gemma":[0.1274444,0.0001774096,0.8152467,0.0005962353,0.0001156866,0.002461376,0.02538003,0.02009657,0.008481611],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.02579948,"threshold_uncertainty_score":0.08630788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03060336274726343,"score_gpt":0.2660249887945808,"score_spread":0.2354216260473174,"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."}}