{"id":"W7017672079","doi":"","title":"Benchmarking Foundation Evaluation Practices","year":2016,"lang":"en","type":"dataset","venue":"Issue Lab (Candid)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Foundation (evidence); Staffing; General partnership; Data collection; Best practice; Evaluation methods","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003872539,0.0006435701,0.0005962466,0.0005950702,0.0003375591,0.000495912,0.0007684377,0.0006229333,0.03454288],"category_scores_gemma":[0.003618863,0.0005570409,0.0001231394,0.0005342397,0.0001281204,0.001253922,0.0002320584,0.0005697358,0.06284764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293366,"about_ca_system_score_gemma":0.0007931002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003346338,"about_ca_topic_score_gemma":0.005984861,"domain_scores_codex":[0.9942349,0.001043481,0.0007273884,0.001091164,0.002249586,0.0006534707],"domain_scores_gemma":[0.9932666,0.0006030423,0.003641249,0.00160155,0.0007116758,0.0001758662],"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":[0.000118747,0.00009919749,0.00004445674,0.0001498601,0.0001834662,0.00001688762,0.00007127696,0.000007142019,0.0001952224,0.00001410649,0.9812466,0.01785307],"study_design_scores_gemma":[0.001242338,0.0001211809,0.0001805715,0.0005494082,0.001026361,0.00002101856,0.00003100619,0.0002415448,0.0000817253,0.0003253001,0.9954501,0.0007293972],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001414857,0.0007415569,0.00001597494,0.0005810434,0.002599207,0.001410324,0.9906393,0.000175251,0.003695845],"genre_scores_gemma":[0.0002856258,0.0004228254,0.0001546036,0.0001607281,0.005381819,0.0003109541,0.9919788,0.0001550172,0.001149618],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02830477,"threshold_uncertainty_score":0.9996881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05451462902368857,"score_gpt":0.3848028726989512,"score_spread":0.3302882436752626,"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."}}