{"id":"W4318147794","doi":"10.1109/bigdata55660.2022.10020299","title":"Temporal Graph Representation Learning via Maximal Cliques","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Clique; Computer science; Graph; Node (physics); Theoretical computer science; Embedding; Representation (politics); Graph embedding; Feature learning; Artificial intelligence; Mathematics; Combinatorics","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008250314,0.0002987366,0.0002605509,0.0004104453,0.0005251564,0.0004362739,0.01049551,0.0000609007,0.0002660603],"category_scores_gemma":[0.0001821376,0.0003266711,0.00006343421,0.0007853389,0.0001135658,0.002337157,0.007543416,0.001075525,0.00006935865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058924,"about_ca_system_score_gemma":0.0001509437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002501253,"about_ca_topic_score_gemma":0.0001769658,"domain_scores_codex":[0.995315,0.0004268783,0.0005414111,0.001767437,0.001528473,0.0004208479],"domain_scores_gemma":[0.9956364,0.0002036682,0.0004471705,0.003398478,0.0001751003,0.0001392023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003616462,0.0004428941,0.006417328,0.00001422713,0.000221227,0.0004506286,0.0002577544,0.005960971,0.004549197,0.05777858,0.06865,0.8548955],"study_design_scores_gemma":[0.0009909078,0.0004403842,0.001908886,0.00004522875,0.00002202583,0.000170424,0.0002166865,0.8289555,0.0006088278,0.02588478,0.1399221,0.0008342757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007484924,0.00009302594,0.9647464,0.005363283,0.01323283,0.0004665821,0.003843309,0.0005421861,0.004227418],"genre_scores_gemma":[0.9654011,0.0002495935,0.007581398,0.001037485,0.0009790782,0.00007939543,0.02382435,0.00003410158,0.0008135544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9579161,"threshold_uncertainty_score":0.9999185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.304841879149363,"score_gpt":0.3731440942115506,"score_spread":0.06830221506218759,"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."}}