{"id":"W4415230897","doi":"10.1609/aies.v8i2.36609","title":"Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Economic Development and Digital Transformation","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Arbitrariness; Terminology; Causation; Classifier (UML); Perspective (graphical); Set (abstract data type)","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":[0.001676399,0.0001171775,0.0002992949,0.00006466054,0.0002200864,0.0000960813,0.0003054563,0.0001508066,0.000006209274],"category_scores_gemma":[0.000416431,0.00008918413,0.0001058693,0.0002250353,0.0001433383,0.0002007256,0.0001538336,0.0007837476,0.000001625029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004078939,"about_ca_system_score_gemma":0.00005004655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000391621,"about_ca_topic_score_gemma":0.00004247998,"domain_scores_codex":[0.9990639,0.000008002634,0.0005517902,0.0001951488,0.00003891048,0.0001422374],"domain_scores_gemma":[0.9991972,0.0002164443,0.0003415452,0.0001091942,0.0001158883,0.00001973799],"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":[0.00001339074,0.00003497453,0.07704409,0.00063695,0.00004571875,2.29215e-7,0.01368154,0.00001854475,0.0001008341,0.9077632,0.00005617227,0.0006043394],"study_design_scores_gemma":[0.004493495,0.0001766489,0.06510226,0.002966995,0.00006105518,0.00005607407,0.02765333,0.2140179,0.005023449,0.6744133,0.004990988,0.001044556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9364071,0.0002883712,0.00007392432,0.007653459,0.0001203073,0.0002871542,0.00002012385,0.00001361951,0.05513596],"genre_scores_gemma":[0.9979413,0.0007271414,0.0001590345,0.0006719438,0.000007609363,0.0000143276,0.000001419379,0.000006233456,0.0004709481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2333499,"threshold_uncertainty_score":0.3636823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06059464723472948,"score_gpt":0.2718064147037274,"score_spread":0.2112117674689979,"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."}}