{"id":"W4393749247","doi":"10.5281/zenodo.6979991","title":"GENEA Challenge 2022 objective evaluation data","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Electronic Arts (Canada)","funders":"","keywords":"Computer science; Data 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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001594062,0.0003129462,0.0002614741,0.0004352026,0.001723927,0.0005178343,0.004163618,0.0001629755,0.1563392],"category_scores_gemma":[0.0009792214,0.0003877264,0.00003750891,0.0006313217,0.0001024793,0.0006360456,0.006205671,0.001028666,0.002235458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007329709,"about_ca_system_score_gemma":0.00001228803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001716165,"about_ca_topic_score_gemma":0.000001746932,"domain_scores_codex":[0.9969956,0.000433521,0.0003486598,0.0008263973,0.0009774058,0.0004183726],"domain_scores_gemma":[0.9968119,0.00003164079,0.0001489107,0.00246774,0.0004146162,0.0001252554],"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":[0.00001243455,0.0000577605,6.539603e-9,0.0001614377,0.00006434185,0.00001194723,0.00007597262,0.0004200314,0.00006803991,0.00002424969,0.9141983,0.08490545],"study_design_scores_gemma":[0.0002244028,0.0001144524,0.000001821918,0.00003476995,0.00005840129,0.00005536621,0.00008519319,0.003795204,0.00003924904,0.000223789,0.994988,0.0003794052],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000004034075,0.001345093,0.00382493,0.00006392659,0.0002819503,0.0007519595,0.9841594,0.002349601,0.007219126],"genre_scores_gemma":[0.0000919935,0.00343929,0.0005202177,0.00003701731,0.0002201852,5.642819e-7,0.9936166,0.002034994,0.00003912371],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1541037,"threshold_uncertainty_score":0.9998575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08138887783894873,"score_gpt":0.3070438007439275,"score_spread":0.2256549229049788,"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."}}