{"id":"W4410536892","doi":"10.1109/icst62969.2025.10988995","title":"An Analysis of LLM Fine-Tuning and Few-Shot Learning for Flaky Test Detection and Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Metallurgy and Material Forming","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Shot (pellet); Computer science; Test (biology); One shot; Artificial intelligence; Machine learning; Materials science; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004180828,0.001497911,0.001226459,0.00147198,0.0007401321,0.001248103,0.00293828,0.001983291,0.001743744],"category_scores_gemma":[0.02127254,0.0005373368,0.0006986387,0.0008184758,0.0009777476,0.002482784,0.001637873,0.002141651,0.0006927823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002094331,"about_ca_system_score_gemma":0.002155262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01538155,"about_ca_topic_score_gemma":0.01819115,"domain_scores_codex":[0.9977801,0.0005513389,0.0001586111,0.0006617581,0.0005290835,0.0003191562],"domain_scores_gemma":[0.9911362,0.005680702,0.0004886158,0.001136019,0.001176092,0.0003824238],"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":[0.000518195,0.0006059648,0.01813094,0.0003739357,0.0001645591,0.000217908,0.00018656,0.5551745,0.008839817,0.003270996,0.009233777,0.4032829],"study_design_scores_gemma":[0.00001370614,0.00007680961,0.001200426,0.00001466586,0.00001224787,0.0000336503,0.0000295148,0.9949009,0.00173688,0.00142188,0.0005497545,0.000009564687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3613414,0.00637415,0.6037464,0.00244481,0.0003896397,0.0005073904,0.0009558927,0.0164919,0.007748604],"genre_scores_gemma":[0.86255,0.00034753,0.1305224,0.0008778706,0.00008870238,0.0002550674,0.002087771,0.0004283321,0.002842337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01538155,"threshold_uncertainty_score":0.03058404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01702181613840942,"score_gpt":0.2534774304121387,"score_spread":0.2364556142737293,"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."}}