{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09457918,0.001544484,0.0032387,0.004556827,0.004842794,0.01560507,0.005396064,0.007144845,0.00394775],"category_scores_gemma":[0.2357629,0.001950237,0.002914981,0.003466068,0.05372121,0.04208198,0.01918045,0.01450294,0.0006409758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004268058,"about_ca_system_score_gemma":0.006381311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002090141,"about_ca_topic_score_gemma":0.001773916,"domain_scores_codex":[0.9024466,0.06469842,0.006092812,0.01294666,0.01198302,0.001832456],"domain_scores_gemma":[0.6553183,0.2679104,0.01336874,0.05418255,0.006958408,0.002261606],"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":[0.00005505566,0.0000234446,0.0020302,0.0001873206,0.0001337746,0.0001328463,0.002254695,0.009070931,0.0003010133,0.9682847,0.0009118334,0.01661414],"study_design_scores_gemma":[0.00001188603,0.0000127351,0.0001294911,0.00007204065,0.00001704447,0.00004928123,0.0001345351,0.01200144,0.0002242674,0.9849947,0.002328483,0.00002409029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02811718,0.003196064,0.9232892,0.03240119,0.0002607745,0.0001134284,0.0001647137,0.0003850409,0.01207239],"genre_scores_gemma":[0.7263666,0.002000043,0.2640954,0.003886445,0.0008840386,0.0005242047,0.0001759848,0.0003773104,0.001689828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09457918,"threshold_uncertainty_score":0.5001885,"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."}}