{"id":"W4393470740","doi":"10.5281/zenodo.8008738","title":"GEO-Bench: m-eurosat","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Regional Development and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008783754,0.001688825,0.001040921,0.002440276,0.0005552886,0.002387669,0.002177172,0.001645222,0.07511972],"category_scores_gemma":[0.00401439,0.0006166606,0.001025638,0.00522147,0.0003839561,0.001872498,0.001959448,0.001792154,0.1444329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350351,"about_ca_system_score_gemma":0.001644784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03088492,"about_ca_topic_score_gemma":0.04192721,"domain_scores_codex":[0.9991376,0.0001573887,0.00008555094,0.0002399637,0.0002316365,0.0001478199],"domain_scores_gemma":[0.9983715,0.0002428557,0.0001649403,0.0004470901,0.0006241695,0.0001494802],"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":[0.00002488729,0.000007327576,0.0004832204,0.0001830253,0.00001931165,0.00001050739,0.00001601052,0.000277625,0.00007621323,0.0006940794,0.9970673,0.001140532],"study_design_scores_gemma":[0.0000813559,0.000005305304,0.002730797,0.0001224301,0.00001152397,0.00002357505,0.00006902235,0.0003304774,0.0002437315,0.001308719,0.9950507,0.00002224849],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00009914167,0.00003318243,0.0001134166,0.0000720868,0.00002986609,0.000005654045,0.9981517,0.0004869682,0.001007927],"genre_scores_gemma":[0.0004386069,0.0000299449,0.0002528359,0.0000439257,0.000009021898,0.00002843417,0.9982702,0.0002017772,0.0007252861],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.07511972,"threshold_uncertainty_score":0.2513005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08718932592298496,"score_gpt":0.3223248411268862,"score_spread":0.2351355152039012,"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."}}