{"id":"W6967746612","doi":"10.5281/zenodo.11480521","title":"TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs","year":2024,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Linguistic, Cultural, and Literary Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmarking; Benchmark (surveying); Graph; Knowledge graph; Scale (ratio)","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":[0.006097155,0.003005967,0.001035498,0.008281395,0.001539685,0.003560724,0.004719117,0.003008702,0.004984383],"category_scores_gemma":[0.03476505,0.0007181225,0.00182434,0.008737876,0.001201269,0.005556382,0.003290245,0.002588634,0.003667591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002340875,"about_ca_system_score_gemma":0.002654172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01877169,"about_ca_topic_score_gemma":0.02711139,"domain_scores_codex":[0.9930814,0.002687027,0.0006223443,0.001626057,0.001553717,0.0004295595],"domain_scores_gemma":[0.9859519,0.006658155,0.000975107,0.003624683,0.002145992,0.00064422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001079887,0.001488278,0.01671317,0.005390685,0.001084826,0.0006421245,0.0006900235,0.1723973,0.006268279,0.03233561,0.5153162,0.2465936],"study_design_scores_gemma":[0.000507951,0.0005846631,0.01322981,0.0007769061,0.0002515125,0.0008389105,0.00102429,0.6831036,0.01326802,0.08110361,0.2051484,0.0001623127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1878256,0.01103599,0.2562564,0.00514088,0.001887736,0.002188484,0.3892648,0.1050264,0.04137362],"genre_scores_gemma":[0.1481998,0.00177078,0.2411563,0.0008350766,0.000157781,0.001303217,0.5983294,0.004196893,0.00405065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01877169,"threshold_uncertainty_score":0.03732491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04964009162905055,"score_gpt":0.3078839255239702,"score_spread":0.2582438338949197,"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."}}