{"id":"W6966350018","doi":"10.48448/2fkc-k105","title":"ECBD: Evidence-Centered Benchmark Design for NLP","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmark (surveying); Benchmarking; Process (computing); Measure (data warehouse); Documentation","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003568083,0.0007463637,0.0006616656,0.002350227,0.000260606,0.0007347954,0.002538056,0.0003878948,0.003382436],"category_scores_gemma":[0.001487902,0.0006520392,0.0002196198,0.002692257,0.001939608,0.0005043495,0.0004834669,0.0004597575,0.02077679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008509611,"about_ca_system_score_gemma":0.002233383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001839038,"about_ca_topic_score_gemma":0.0003626981,"domain_scores_codex":[0.9940857,0.0001201563,0.0006148948,0.002084714,0.001708986,0.0013855],"domain_scores_gemma":[0.9969972,0.0004226616,0.0004522326,0.001377619,0.0003163218,0.0004339032],"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":[0.00003900673,0.00009157424,0.00001038456,0.0002340324,0.00005843021,0.00001914159,0.0001027764,0.00004999461,0.002908424,0.002235368,0.9916626,0.002588316],"study_design_scores_gemma":[0.0006055142,0.0004927684,0.000008782135,0.003888905,0.0002867963,0.00003506382,0.0001466782,0.02462419,0.000955508,0.007083888,0.9606319,0.001239968],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00003873781,0.0235295,0.127174,0.002008097,0.0141522,0.01292846,0.002529781,0.005527169,0.8121121],"genre_scores_gemma":[0.003694373,0.0001834629,0.1272852,0.0004192909,0.001856243,0.0004499229,0.0001103283,0.002603394,0.8633978],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.05128577,"threshold_uncertainty_score":0.9995931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1571169989981255,"score_gpt":0.3803313389014374,"score_spread":0.2232143399033119,"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."}}