{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001763779,0.005124429,0.002041285,0.004112141,0.001539871,0.002143238,0.005228864,0.004695183,0.02995962],"category_scores_gemma":[0.007392412,0.000875095,0.00332252,0.00503647,0.001013111,0.001531693,0.002364352,0.003234309,0.03799679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003077088,"about_ca_system_score_gemma":0.003771368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05184364,"about_ca_topic_score_gemma":0.09377723,"domain_scores_codex":[0.9978357,0.0003798778,0.0002221129,0.0005744702,0.0006915329,0.0002962842],"domain_scores_gemma":[0.9968215,0.0008880137,0.0002073826,0.0007630772,0.00100531,0.0003147024],"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":[0.00015843,0.0001731745,0.000650866,0.000689449,0.0000777383,0.00006416858,0.0000221611,0.00163918,0.0004007972,0.000372193,0.9891989,0.006552999],"study_design_scores_gemma":[0.002083884,0.0001947692,0.01159712,0.0007152833,0.0002630515,0.0004383491,0.0003706156,0.0160034,0.00418552,0.005273701,0.9586792,0.0001951232],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001739236,0.0002312498,0.0005773107,0.0003183401,0.0001321748,0.0001501803,0.9931713,0.002009721,0.001670481],"genre_scores_gemma":[0.0009693745,0.0000507394,0.001055214,0.00007225663,0.000009944571,0.0001918045,0.9968887,0.00009050237,0.0006715218],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05184364,"threshold_uncertainty_score":0.1030837,"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."}}