{"id":"W4393883849","doi":"10.5281/zenodo.10215592","title":"Dataset and model weights for the paper \"Combining Natural Language and Images for Garbage Classification: A Public Benchmark\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Knowledge Management and Technology","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Benchmark (surveying); Garbage; Computer science; Artificial intelligence; Natural language processing; Geography; Cartography; Programming language","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002724891,0.0002323893,0.0002785554,0.0005961771,0.002689275,0.002713411,0.002405734,0.0001531655,0.0008843384],"category_scores_gemma":[0.00576352,0.0001672468,0.00006505044,0.0006613401,0.0004059466,0.0004370909,0.003072593,0.0003620976,0.001480283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004274344,"about_ca_system_score_gemma":0.000007319118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001012612,"about_ca_topic_score_gemma":0.000008874342,"domain_scores_codex":[0.9975575,0.0001997778,0.0004305281,0.0008566774,0.0005430151,0.0004125019],"domain_scores_gemma":[0.9971691,0.000770976,0.0002634764,0.001152294,0.0005358417,0.0001083032],"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":[0.00003069975,0.00002748465,2.66209e-7,0.00006414489,0.00005157603,0.000002805567,0.0001142605,8.660189e-7,0.00004586751,0.003382484,0.9260958,0.07018367],"study_design_scores_gemma":[0.0005210484,0.00008978709,0.00005538099,0.00001637163,0.00005445272,0.00001418581,0.0008415788,0.01108485,0.000003947696,0.002760718,0.9843602,0.0001974871],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00006233505,0.0007324251,0.003339701,0.004708857,0.0002262974,0.00128184,0.9884186,0.0002576916,0.0009722548],"genre_scores_gemma":[0.002252268,0.0004210654,0.0003196449,0.0002087133,0.000160324,0.000001849462,0.9930787,0.0004267888,0.003130655],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06998619,"threshold_uncertainty_score":0.9992972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1199545755614023,"score_gpt":0.3439115011221104,"score_spread":0.2239569255607081,"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."}}