{"id":"W4394866494","doi":"10.48550/arxiv.2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundação de Amparo à Pesquisa do Estado do Amazonas; Agencia Nacional de Promoción Científica y Tecnológica; International Development Research Centre; Consejo Nacional de Investigaciones Científicas y Técnicas; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Universidade Federal do Amazonas; Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; Agencia Nacional de Investigación e Innovación","keywords":"Downstream (manufacturing); Taxonomy (biology); Computer science; Software; Software engineering; Engineering; Programming language; Operations management; Biology; Ecology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.01537565,0.000972549,0.0006151124,0.002929545,0.002075793,0.007226847,0.002587627,0.002460191,0.003434696],"category_scores_gemma":[0.04731416,0.0009998007,0.001499095,0.002163581,0.01254221,0.0106195,0.006802987,0.004102124,0.001048678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00330968,"about_ca_system_score_gemma":0.004314448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00163302,"about_ca_topic_score_gemma":0.002057095,"domain_scores_codex":[0.9786089,0.01157347,0.001572206,0.002579027,0.004743744,0.0009227351],"domain_scores_gemma":[0.9637926,0.01834223,0.002333986,0.01264547,0.00238547,0.0005001897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006139763,0.00006706596,0.002628485,0.0002349956,0.00002375957,0.0002375863,0.006701265,0.008316627,0.002645469,0.8939304,0.0009784189,0.08417444],"study_design_scores_gemma":[0.00002191131,0.00007586041,0.0005908975,0.0002106711,0.00003408874,0.0004765241,0.001621836,0.04361768,0.007320277,0.9152879,0.0306944,0.00004804391],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01379377,0.0003076894,0.9777945,0.001009006,0.00003162863,0.0001107232,0.00005108022,0.001164205,0.005737302],"genre_scores_gemma":[0.3592526,0.0004434798,0.6354099,0.0004849954,0.00004148859,0.0003968175,0.0002298682,0.0006935747,0.003047339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01537565,"threshold_uncertainty_score":0.08131522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.129500478238457,"score_gpt":0.2180438260372911,"score_spread":0.08854334779883408,"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."}}