{"id":"W7045818181","doi":"","title":"Benchmarking Foundation Evaluation Practices 2020","year":2020,"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); Function (biology); Investment (military); Survey data collection; Data collection; 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":[0.002428955,0.0007315057,0.0007550574,0.0003276247,0.0003450949,0.0007294965,0.0008757355,0.0005946523,0.02022536],"category_scores_gemma":[0.00485883,0.0007914657,0.0001525292,0.00115883,0.0001032519,0.001040925,0.0003329597,0.001103727,0.1072664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009601952,"about_ca_system_score_gemma":0.0009512856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00341341,"about_ca_topic_score_gemma":0.004986897,"domain_scores_codex":[0.9935564,0.001143954,0.0008456363,0.001339807,0.002515011,0.0005991686],"domain_scores_gemma":[0.993928,0.0004579063,0.003557449,0.001211345,0.0005673757,0.0002779175],"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":[0.0001821192,0.0001053474,0.00003555215,0.0003121648,0.0002589145,0.00006503403,0.0001986748,0.00006700762,0.0001512145,0.000007313929,0.9929902,0.005626481],"study_design_scores_gemma":[0.001076014,0.0001961243,0.0001755021,0.0002632468,0.001614373,0.00002436479,0.00009652385,0.002645043,0.0000562759,0.0001280388,0.9929146,0.0008099172],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007764299,0.0007824945,0.00001075912,0.001557774,0.002189037,0.001710391,0.9915596,0.0002349821,0.001877339],"genre_scores_gemma":[0.0003199226,0.0005162811,0.000374977,0.0005482127,0.006641044,0.0002800736,0.9909062,0.0001783713,0.0002349163],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08704106,"threshold_uncertainty_score":0.9994536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05436349869071153,"score_gpt":0.3736739790814738,"score_spread":0.3193104803907623,"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."}}