{"id":"W4415230309","doi":"10.1609/aies.v8i3.36776","title":"From Model Multiplicity to Prompt Multiplicity: Emerging Arbitrariness Concerns in the Age of Generative AI","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Arbitrariness; Generative grammar; Phenomenon; Multiplicity (mathematics); Generative model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06739119,0.001009555,0.001440808,0.002857709,0.004770737,0.01965785,0.004009295,0.00813673,0.006884726],"category_scores_gemma":[0.158418,0.001647349,0.001278657,0.001850385,0.04492744,0.04727412,0.01703192,0.01494523,0.001008027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00544766,"about_ca_system_score_gemma":0.004170662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001619753,"about_ca_topic_score_gemma":0.001026967,"domain_scores_codex":[0.952723,0.03108048,0.002101705,0.004555183,0.008066584,0.001473126],"domain_scores_gemma":[0.760978,0.1851427,0.008189807,0.03312616,0.008804679,0.003758706],"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":[0.00004598025,0.00001730704,0.0007012017,0.00007415342,0.00001400413,0.00009001647,0.005722919,0.002072998,0.0003547212,0.9786379,0.0007360334,0.01153274],"study_design_scores_gemma":[0.00001391218,0.00002618464,0.0001427695,0.00009532181,0.000009257185,0.0001081072,0.0007932262,0.006848891,0.0006188248,0.9799938,0.01131986,0.00002982021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04153443,0.00588372,0.8395872,0.06683199,0.0005626932,0.0001033864,0.0001285411,0.001099376,0.04426882],"genre_scores_gemma":[0.8687381,0.001794608,0.1206415,0.0039134,0.000650591,0.0002315583,0.00007894303,0.0007329568,0.003218374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06739119,"threshold_uncertainty_score":0.3564029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1243715393619598,"score_gpt":0.4205873121364219,"score_spread":0.2962157727744621,"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."}}