{"id":"W7043375682","doi":"","title":"From social networks to biological graphs: Addressing design issues and exploring practical applications in graph representation learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Graph; Representation (politics); Knowledge representation and reasoning; Social network (sociolinguistics); Feature learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007374529,0.0006791288,0.0007884151,0.0008038357,0.001586495,0.000363442,0.0008950225,0.0007609991,0.000007963329],"category_scores_gemma":[0.0008492077,0.0007249532,0.0002134588,0.002714631,0.00006846548,0.001840778,0.0004478687,0.002451307,0.000008821728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002036902,"about_ca_system_score_gemma":0.00003527855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002391424,"about_ca_topic_score_gemma":0.0002727301,"domain_scores_codex":[0.9946462,0.001141463,0.0009046618,0.001975765,0.0005411784,0.0007907341],"domain_scores_gemma":[0.9966477,0.001716284,0.0005133835,0.0006090947,0.0002422181,0.0002712902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004303234,0.0002859344,0.0007466449,0.0001004307,0.0002082598,0.000142984,0.0002618954,0.02451625,0.007164134,0.2198084,0.00002334117,0.7463114],"study_design_scores_gemma":[0.002576505,0.000648528,0.03640891,0.002603228,0.0003450818,0.00002995682,0.004128167,0.02079696,0.02259789,0.8937699,0.0108626,0.005232282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9356329,0.00217261,0.05041818,0.0003685391,0.002286092,0.004224248,0.0001185396,0.001712835,0.003066058],"genre_scores_gemma":[0.9179187,0.0014015,0.07771076,0.00022708,0.0001708039,0.001580822,0.0006316768,0.0000944951,0.0002641024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7410791,"threshold_uncertainty_score":0.9998501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216793841106491,"score_gpt":0.3474987738074528,"score_spread":0.2258193896968038,"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."}}