{"id":"W4393747282","doi":"10.5281/zenodo.7008205","title":"Dataset for \"Towards Better Evaluation for Dynamic Link Prediction\"","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Link (geometry); Computer science; Computer network","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","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003694303,0.0002986946,0.0003186736,0.0004030334,0.003352288,0.001056878,0.003570845,0.0002130206,0.01519005],"category_scores_gemma":[0.0011951,0.0003023482,0.0001527509,0.0005792741,0.0001034781,0.0007516616,0.002471066,0.0004660592,0.001003751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006165668,"about_ca_system_score_gemma":0.00004899312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002452579,"about_ca_topic_score_gemma":8.403404e-7,"domain_scores_codex":[0.9963012,0.0005197273,0.0005744803,0.001073529,0.001010939,0.0005201144],"domain_scores_gemma":[0.9964318,0.0001026448,0.0003373172,0.001861192,0.001108937,0.0001580915],"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":[0.00004072369,0.00008520252,1.76985e-7,0.000406878,0.00006331089,0.000001484773,0.00008491133,0.0001201022,0.0000107418,0.00003553293,0.9102262,0.08892471],"study_design_scores_gemma":[0.0009016396,0.0005494251,0.00004582827,0.0000356878,0.00008037798,0.00005721698,0.00002503788,0.01922424,0.000008045527,0.0002944991,0.9784821,0.0002959538],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001696843,0.00008881275,0.06854694,0.001425005,0.001076063,0.002807843,0.9255201,0.0004185211,0.00009978651],"genre_scores_gemma":[0.00007655709,0.00008755586,0.001368239,0.0004003281,0.0003961798,0.00000658038,0.9970012,0.0005701511,0.00009316165],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08862876,"threshold_uncertainty_score":0.9999801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03956076580003284,"score_gpt":0.2906196007286284,"score_spread":0.2510588349285956,"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."}}