{"id":"W4414818091","doi":"10.1109/ase63991.2025.00012","title":"MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model","year":2025,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Imitation; Task (project management); Big Five personality traits; Video game; Personality; Neglect","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082399,0.00007433965,0.0001324739,0.00007228619,0.0004932046,0.00007336738,0.0001214836,0.00004504778,0.0001005781],"category_scores_gemma":[0.000805379,0.0000648324,0.0001188042,0.0003728421,0.00004945927,0.0001235419,0.00004279734,0.00007218731,0.000001550377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007299575,"about_ca_system_score_gemma":0.0001565451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002415056,"about_ca_topic_score_gemma":0.002839247,"domain_scores_codex":[0.9991491,0.0001275131,0.0001530663,0.0001867865,0.0001630828,0.0002204266],"domain_scores_gemma":[0.9990273,0.0006773254,0.00005089617,0.00004582015,0.0001576405,0.00004107406],"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":[0.00003460985,0.0003045484,0.03679023,0.000134652,0.0003082434,0.000006255923,0.118133,0.01500204,0.0160802,0.3986697,0.001744851,0.4127917],"study_design_scores_gemma":[0.0001940809,0.0000036742,0.001178402,0.00002483031,0.00005755906,1.182332e-7,0.01299661,0.9679381,0.00006747469,0.01674568,0.0006908039,0.0001026445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3969045,0.00002263809,0.5871921,0.0006242834,0.0000393586,0.00009930668,0.00001173562,0.00004715677,0.01505894],"genre_scores_gemma":[0.7150878,2.295753e-7,0.2811285,0.000840779,0.0001013756,0.000004799653,0.000004141713,0.000003197841,0.002829215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9529361,"threshold_uncertainty_score":0.3793381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1288867297546579,"score_gpt":0.4435177640939151,"score_spread":0.3146310343392572,"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."}}