{"id":"W6891619348","doi":"10.48448/e9m0-fx58","title":"Weaker Than You Think: A Critical Look at Weakly Supervised Learning","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Supervised learning; Training set; Labeled data; Semi-supervised learning; Value (mathematics); Training (meteorology)","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","sts","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.002950396,0.0008959029,0.0008312179,0.001996774,0.00176384,0.000478497,0.002860766,0.0004183489,0.1151742],"category_scores_gemma":[0.002171404,0.0008592281,0.0002475272,0.002895671,0.004738962,0.0004845924,0.002699882,0.002005394,0.02305646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00180152,"about_ca_system_score_gemma":0.00215262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007285019,"about_ca_topic_score_gemma":0.001255665,"domain_scores_codex":[0.9907206,0.0004532049,0.0006444991,0.002336901,0.003845049,0.001999783],"domain_scores_gemma":[0.9967058,0.0003432798,0.0003320226,0.001628535,0.0002468311,0.0007435806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001181133,0.0007742763,0.005833368,0.0002256371,0.0001437241,0.0004779774,0.002133409,0.000455681,0.01888314,0.0268777,0.9411883,0.002888667],"study_design_scores_gemma":[0.0007458613,0.000312791,0.0002347594,0.0001730718,0.0001288173,0.0001533369,0.001928811,0.016836,0.0001448582,0.0005531739,0.9773993,0.001389199],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001555956,0.001288306,0.0002424622,0.00127764,0.001776077,0.0009158725,0.0004060789,0.002772162,0.9897655],"genre_scores_gemma":[0.03930619,0.00005414265,0.007226352,0.0007619528,0.001004638,0.00008935974,0.0004558332,0.002431389,0.9486701],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.09211772,"threshold_uncertainty_score":0.9995357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02425668053140697,"score_gpt":0.3000103918301679,"score_spread":0.2757537112987609,"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."}}