{"id":"W4393677065","doi":"10.5281/zenodo.7455766","title":"ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolutionary Search – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Computer science; Code (set theory); Test (biology); Similarity (geometry); Programming language; Artificial intelligence; Biology; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001545762,0.0003277939,0.0002644913,0.0006221838,0.003378026,0.001156644,0.002123653,0.000197643,0.005225187],"category_scores_gemma":[0.01009689,0.0003736372,0.00006538907,0.001194982,0.0002851889,0.0003020338,0.002999086,0.0008750189,0.000562783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004230617,"about_ca_system_score_gemma":0.00003376157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001090024,"about_ca_topic_score_gemma":0.000001238242,"domain_scores_codex":[0.9962581,0.0007127635,0.0004120024,0.001331632,0.0008336463,0.0004518818],"domain_scores_gemma":[0.9951664,0.001018784,0.0002659338,0.002634519,0.0006667916,0.0002475913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000161816,0.0004006759,0.00001290381,0.0001330225,0.000009409473,0.000295315,0.0001075376,0.0001836561,0.00001527271,0.00008259728,0.9909638,0.007779691],"study_design_scores_gemma":[0.0003244089,0.0009355234,0.0001676778,0.00007745896,0.00002171792,0.001099844,0.00001633252,0.0342077,0.00002843602,0.0002943951,0.9624466,0.0003799167],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007263965,0.00005944749,0.03452404,0.002403775,0.0001198985,0.001171907,0.9499618,0.01014657,0.001539863],"genre_scores_gemma":[0.004577559,0.000110578,0.009650894,0.0006509151,0.0001300772,9.371993e-7,0.983924,0.0007992754,0.0001558172],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03402405,"threshold_uncertainty_score":0.9998803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04402094876027669,"score_gpt":0.2760535441570954,"score_spread":0.2320325953968187,"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."}}