{"id":"W4410543982","doi":"10.14778/3717755.3717766","title":"WeShap: Weak Supervision Source Evaluation with Shapley Values","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Shapley value; Mathematical economics; Mathematics; Game theory","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":[],"consensus_categories":[],"category_scores_codex":[0.0008368109,0.0001373774,0.0001250521,0.0000938663,0.0001018204,0.0002385477,0.0008951038,0.00003639151,0.00002317098],"category_scores_gemma":[0.00004736832,0.00008142887,0.00007182723,0.0003675145,0.00003506116,0.0005132367,0.0004353136,0.0001289268,0.00001493844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001085358,"about_ca_system_score_gemma":0.0000675686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004196499,"about_ca_topic_score_gemma":0.00000175485,"domain_scores_codex":[0.9982367,0.00001061775,0.0002256262,0.0004085453,0.0009108626,0.0002076949],"domain_scores_gemma":[0.9994029,0.00003514715,0.00007535826,0.0002179095,0.0002220242,0.00004665621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005294415,0.0002649612,0.006220908,0.0009672827,0.0002926803,0.000001966825,0.01864385,0.006066161,0.10847,0.3634877,0.01021641,0.4853151],"study_design_scores_gemma":[0.0003925363,0.0001476023,0.0007986063,0.000562084,0.0000663659,0.00003825684,0.0003347392,0.9207796,0.05092262,0.02075893,0.004988681,0.0002099412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8487367,0.00240409,0.1107299,0.01136972,0.001129404,0.001744686,0.000002733396,0.0006366245,0.02324619],"genre_scores_gemma":[0.9861711,0.00002041655,0.01298747,0.00009228596,0.00009480488,0.00005524435,4.230742e-7,0.0000131778,0.0005650326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9147135,"threshold_uncertainty_score":0.3320573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02403461430150674,"score_gpt":0.2549961208786427,"score_spread":0.230961506577136,"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."}}