{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01186556,0.002104456,0.001605361,0.002353991,0.00167651,0.003421476,0.003614582,0.002656722,0.007847093],"category_scores_gemma":[0.03918682,0.0009118741,0.001352123,0.001888027,0.002541406,0.006261868,0.005349298,0.0043949,0.00171836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003044328,"about_ca_system_score_gemma":0.005270746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003306917,"about_ca_topic_score_gemma":0.00541851,"domain_scores_codex":[0.9942194,0.002512013,0.0003349709,0.001050842,0.001522431,0.000360385],"domain_scores_gemma":[0.9817356,0.01174529,0.0007999783,0.003053088,0.002087905,0.0005780731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009694865,0.0004139285,0.007216698,0.0006843637,0.0002639135,0.0002393418,0.0004187387,0.4878576,0.005512333,0.0876551,0.02366127,0.3851073],"study_design_scores_gemma":[0.00005569296,0.0001096303,0.0003124887,0.00005008503,0.00002127373,0.00004220185,0.00004894455,0.9111509,0.003968902,0.08223721,0.001982528,0.00002013333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04708299,0.0007501257,0.9351886,0.001128432,0.0001993849,0.0003510299,0.0009115106,0.0069814,0.00740659],"genre_scores_gemma":[0.4816069,0.000302271,0.5088531,0.0006636356,0.0001383778,0.0005412253,0.00249813,0.00145119,0.003945245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01186556,"threshold_uncertainty_score":0.06275183,"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."}}