{"id":"W4394038155","doi":"10.5281/zenodo.8263732","title":"GEO-Bench: test-dataset","year":2023,"lang":"hu","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Test (biology); Computer science; Environmental science; Biology; Ecology","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","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.001125999,0.000494134,0.0004100949,0.0005871609,0.005219426,0.004552707,0.006278258,0.0002176829,0.006915006],"category_scores_gemma":[0.001028216,0.0005792444,0.0001595226,0.002524246,0.0003146067,0.0005521838,0.008112162,0.000960215,0.3877025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002418253,"about_ca_system_score_gemma":0.00003397877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001735619,"about_ca_topic_score_gemma":0.000002522615,"domain_scores_codex":[0.9953018,0.0004548787,0.000713345,0.00152789,0.001168983,0.0008330955],"domain_scores_gemma":[0.9950953,0.0003795293,0.0004439733,0.002442732,0.00113687,0.0005015858],"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":[0.000008892323,0.0003726065,9.842366e-8,0.0001226684,0.00006857234,0.00003709867,0.0001878719,0.0003056892,0.0001075743,0.009176869,0.9573147,0.03229734],"study_design_scores_gemma":[0.0003678871,0.000274374,0.0001715982,0.0000725633,0.00004493224,0.000112575,0.00004403888,0.005942339,0.00001313008,0.003848032,0.9885228,0.0005857593],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001670748,0.00006646857,0.02977287,0.00302285,0.0004365008,0.0008950732,0.9593768,0.001128187,0.005284518],"genre_scores_gemma":[0.0004970655,0.0003153003,0.00065587,0.0006046916,0.000693541,2.752343e-7,0.9946259,0.00167928,0.0009280922],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3807875,"threshold_uncertainty_score":0.9999101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05235524093384973,"score_gpt":0.2812710911375829,"score_spread":0.2289158502037331,"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."}}