{"id":"W7116744000","doi":"10.1109/mitp.2025.3633473","title":"Large Language Models in Human Subject Research, and the Presence of Idiosyncratic Human Behaviors","year":2025,"lang":"en","type":"article","venue":"IT Professional","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Subject (documents); Human language; Language model; Language understanding; On Language; Information technology; Human studies","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":[],"consensus_categories":[],"category_scores_codex":[0.002182255,0.00005121671,0.000111341,0.00007311416,0.0007989747,0.00002324697,0.0002307618,0.00007842548,0.0001267434],"category_scores_gemma":[0.0001871642,0.00003063036,0.00002667848,0.000344497,0.0005221951,0.0001896711,0.0001329903,0.0002580172,0.000001558042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004402119,"about_ca_system_score_gemma":0.0001248877,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005027867,"about_ca_topic_score_gemma":0.01953808,"domain_scores_codex":[0.9983569,0.0006941769,0.0001702249,0.000137087,0.0004103798,0.0002312815],"domain_scores_gemma":[0.9995058,0.0002109328,0.00004148025,0.0001204121,0.00009319884,0.00002814771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005203654,0.0001799749,0.005474005,0.00004171701,0.000007877953,0.000008210091,0.169504,0.000003436337,0.01210114,0.8090513,0.003310121,0.0002662487],"study_design_scores_gemma":[0.004290482,0.0001065301,0.0645452,0.001436099,0.00003444927,0.000001046878,0.5811375,0.0003881428,0.002854019,0.3438716,0.00103146,0.0003034765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804843,0.0005176769,0.000006851235,0.001780669,0.00007673415,0.0003788217,0.000004483328,0.00001168903,0.01673876],"genre_scores_gemma":[0.9807488,0.00001548537,0.000009867642,0.00007944251,0.00004177056,0.00004861892,0.000006265535,0.000002370156,0.01904742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4651797,"threshold_uncertainty_score":0.9983528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04688727258968862,"score_gpt":0.4379177941996059,"score_spread":0.3910305216099173,"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."}}