{"id":"W6931075403","doi":"10.5281/zenodo.15581149","title":"RevDecode: Frankenbinary Evaluation Dataset","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Reproductive Health and Contraception","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Science Foundation","keywords":"Matching (statistics); Relevance (law); Artifact (error); Binary data; Graph; Function (biology)","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":[0.0024273,0.004095508,0.001990325,0.003013069,0.001717742,0.002361829,0.005662214,0.003985036,0.03426481],"category_scores_gemma":[0.00896324,0.0007532028,0.002235933,0.004131317,0.0009276413,0.001773168,0.002616022,0.002977769,0.05128701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003011995,"about_ca_system_score_gemma":0.00286793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0388167,"about_ca_topic_score_gemma":0.07379009,"domain_scores_codex":[0.9966456,0.0008583763,0.0003217143,0.0008320232,0.0009753765,0.0003668176],"domain_scores_gemma":[0.9967651,0.0008975437,0.0001880825,0.0009813929,0.0009041097,0.0002636369],"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":[0.0001770961,0.0001228176,0.0004193431,0.0005291359,0.00004825027,0.00003806968,0.00001773482,0.0008574067,0.0003152954,0.0005526642,0.9897255,0.007196774],"study_design_scores_gemma":[0.001166419,0.0002378606,0.007111862,0.0005285997,0.000137971,0.0004866922,0.0001943833,0.01120881,0.003670266,0.004594939,0.9705249,0.0001372866],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002504121,0.0007439388,0.001024788,0.0004310535,0.000208638,0.0002354458,0.9872259,0.003254661,0.004371354],"genre_scores_gemma":[0.001867096,0.00009613056,0.001470029,0.0001606807,0.00001730661,0.000265032,0.9942834,0.0002091427,0.001631293],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0388167,"threshold_uncertainty_score":0.1146272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06045268079645773,"score_gpt":0.3466453373751177,"score_spread":0.28619265657866,"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."}}