{"id":"W4403344783","doi":"10.4230/lipics.forc.2024.8","title":"Score Design for Multi-Criteria Incentivization","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Process engineering; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003505514,0.0002663469,0.0002338915,0.0003278964,0.0001140545,0.0003025332,0.001851271,0.0002732764,0.000009220739],"category_scores_gemma":[0.00006346784,0.0003147955,0.0001363841,0.0005446976,0.00007370581,0.0003999902,0.002140058,0.0003362176,0.00008288299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766419,"about_ca_system_score_gemma":0.0002403581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650618,"about_ca_topic_score_gemma":0.000004293878,"domain_scores_codex":[0.9981266,0.0001198791,0.0002072031,0.001207199,0.00006929776,0.0002698269],"domain_scores_gemma":[0.9981047,0.00008494245,0.0001990815,0.001288493,0.0002395273,0.00008327026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004401465,0.0002224826,0.0002330332,0.0005740983,0.000115387,0.00008978364,0.0003389938,0.01577338,0.001652964,0.9611303,0.01529836,0.004527172],"study_design_scores_gemma":[0.0002055913,0.00002902134,0.0001387169,0.0001486983,0.00003630335,0.000001337882,0.000008253137,0.8787256,0.003915086,0.115332,0.001145003,0.0003143431],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001481746,0.00005788792,0.9951631,0.0001380528,0.0008355141,0.0009455315,0.0001050945,0.001118555,0.0001544946],"genre_scores_gemma":[0.7540629,0.00009741273,0.2439951,0.00007595742,0.00006169417,0.00001524382,0.0001378409,0.00002838015,0.001525523],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8629523,"threshold_uncertainty_score":0.9999304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2440666164831968,"score_gpt":0.2563206409561086,"score_spread":0.01225402447291174,"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."}}