{"id":"W4406058764","doi":"10.48550/arxiv.2407.13070","title":"The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Law, Economics, and Judicial Systems","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Arbitrariness; Multiplicity (mathematics); Computer science; Epistemology; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07613596,0.0006283098,0.002008068,0.001835687,0.002879751,0.007270493,0.00427308,0.004150091,0.004359068],"category_scores_gemma":[0.3140439,0.0007390142,0.001651113,0.001654998,0.0113948,0.01137791,0.01047995,0.008031177,0.0003320375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003440703,"about_ca_system_score_gemma":0.004711278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00514186,"about_ca_topic_score_gemma":0.005056399,"domain_scores_codex":[0.9517229,0.03603297,0.001699565,0.00413919,0.004659448,0.001746043],"domain_scores_gemma":[0.5197573,0.4233007,0.02033577,0.02737464,0.005600827,0.0036308],"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":[0.0001381097,0.0001019959,0.0160791,0.0001280493,0.0002604874,0.0005874807,0.001304675,0.1442085,0.0003645921,0.8088572,0.001538823,0.02643094],"study_design_scores_gemma":[0.0000466035,0.00005840791,0.001533232,0.0001017784,0.0000569295,0.0001739244,0.0003546243,0.2934262,0.0003701882,0.7017787,0.002053773,0.00004564474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2277438,0.001641198,0.71692,0.03475234,0.0002026535,0.0001704528,0.0001664595,0.0002083712,0.01819466],"genre_scores_gemma":[0.9411219,0.0003684027,0.05596272,0.001114784,0.0002192194,0.0001550205,0.00006330576,0.00007185923,0.0009227542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07613596,"threshold_uncertainty_score":0.4026503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.156910895173592,"score_gpt":0.210624496190394,"score_spread":0.053713601016802,"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."}}