{"id":"W4383216495","doi":"10.1016/j.ins.2023.119371","title":"DyHNet: Learning dynamic heterogeneous network representations","year":2023,"lang":"en","type":"article","venue":"Information Sciences","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Ryerson University","keywords":"Computer science; Node (physics); Task (project management); Semantics (computer science); Representation (politics); Artificial intelligence; Baseline (sea); State (computer science); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004139223,0.00006474562,0.00007889192,0.0001582908,0.0005187843,0.0002133899,0.0002033179,0.00001249454,0.0002805332],"category_scores_gemma":[0.00001108184,0.00005907132,0.00006066414,0.001407361,0.00008012606,0.0007321939,0.00008028212,0.00007098362,0.0004130281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001028272,"about_ca_system_score_gemma":0.00002726362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001004218,"about_ca_topic_score_gemma":0.00001062372,"domain_scores_codex":[0.9991909,0.0000325414,0.0002394923,0.00009420701,0.0002286778,0.0002141263],"domain_scores_gemma":[0.9995915,0.00007803192,0.0001331037,0.0001136577,0.00005060948,0.00003306622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001243039,0.000004830482,0.04436999,0.000002172947,0.00002181441,2.390497e-7,0.0007086173,0.850854,0.00002015164,0.009987405,0.008870538,0.08515904],"study_design_scores_gemma":[0.0000706232,0.00002744813,0.009687222,0.00001076736,0.000009299587,9.839046e-7,0.0009671518,0.9330369,0.00007965823,0.01872609,0.03723649,0.000147428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.578838,0.00003844086,0.2617002,0.0009210408,0.0003980793,0.0004441312,0.00001441248,0.001425506,0.1562202],"genre_scores_gemma":[0.9985515,0.000004607258,0.0009131399,0.00004850018,0.00007216173,0.00002600765,0.00008627099,0.000002421685,0.0002954258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4197135,"threshold_uncertainty_score":0.5308779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01774159096312618,"score_gpt":0.3215969720319382,"score_spread":0.303855381068812,"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."}}