{"id":"W4393703399","doi":"10.5281/zenodo.8008748","title":"GEO-Bench: m-pv4ger","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Geological Modeling and Analysis","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Environmental science","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":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007462974,0.0002176865,0.0002627159,0.0003395603,0.002004779,0.0008039045,0.001498324,0.0001988952,0.09864061],"category_scores_gemma":[0.0007218937,0.000190226,0.0001209959,0.0007511392,0.0001323332,0.0001119392,0.0003974171,0.0005425502,0.3480889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001369869,"about_ca_system_score_gemma":0.000003899338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001463013,"about_ca_topic_score_gemma":0.00004761989,"domain_scores_codex":[0.997749,0.0003251654,0.0002978281,0.0006004571,0.0005301536,0.0004973722],"domain_scores_gemma":[0.9987303,0.00004916296,0.0001277144,0.0005886542,0.0002594121,0.0002447428],"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":[0.00001072163,0.00002122941,0.000002388034,0.00003995407,0.00004315764,0.00003589622,0.00002190322,0.001587364,0.000001321622,0.000006982102,0.9725381,0.02569101],"study_design_scores_gemma":[0.000108383,0.0001366885,0.0005448465,0.00002288267,0.00004513785,0.00002880935,0.00005265168,0.002053387,6.442433e-7,0.0001442279,0.996626,0.0002363681],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001686973,0.0001358144,0.0001315787,0.0006105684,0.0002618946,0.0001670432,0.9878398,0.0006343414,0.01005025],"genre_scores_gemma":[0.001557009,0.0005346439,0.00004175662,0.000233844,0.0003403564,5.673844e-9,0.9956529,0.0002247664,0.001414767],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2494483,"threshold_uncertainty_score":0.9992945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05436327821856646,"score_gpt":0.2364994271383783,"score_spread":0.1821361489198118,"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."}}