{"id":"W2975795857","doi":"10.3389/fdata.2019.00006","title":"Attending Over Triads for Learning Signed Network Embedding","year":2019,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Embedding; Leverage (statistics); Sign (mathematics); Enhanced Data Rates for GSM Evolution; Computer science; Node (physics); Theoretical computer science; Network topology; Topology (electrical circuits); Mathematics; Artificial intelligence; Combinatorics; Computer network; Engineering","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":[0.0007130798,0.0001917544,0.0003273293,0.0001634031,0.0001397716,0.0001396886,0.002403982,0.0001035138,0.000005128277],"category_scores_gemma":[0.0001368688,0.0001943796,0.00005866318,0.0007812623,0.0000297564,0.001183751,0.001184369,0.0003300559,0.00001006613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006329122,"about_ca_system_score_gemma":0.0000285469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003962135,"about_ca_topic_score_gemma":0.000004223771,"domain_scores_codex":[0.9978516,0.00009723629,0.0003109947,0.0008559683,0.0002219616,0.0006623141],"domain_scores_gemma":[0.9980276,0.0002710102,0.0001662468,0.00143569,0.00002159028,0.00007785811],"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":[0.0001704264,0.00004145643,0.155925,0.00006022334,0.00007596618,0.00002508375,0.0002308788,0.183437,0.0002936043,0.004753369,0.2436627,0.4113244],"study_design_scores_gemma":[0.001046374,0.00006723922,0.001042456,0.00008447434,0.000006664484,0.000002442941,0.00003154971,0.919406,0.00001741372,0.005374311,0.0726313,0.0002897657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003840221,0.0006464078,0.9869061,0.000129262,0.007611869,0.0004781898,0.00001317315,0.0001469614,0.0002278688],"genre_scores_gemma":[0.2267097,0.00009388884,0.7703555,0.0004371672,0.00108366,0.00003316065,0.000247904,0.00005047083,0.0009884913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7359691,"threshold_uncertainty_score":0.7926572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04617225981116451,"score_gpt":0.2949449555788986,"score_spread":0.2487726957677341,"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."}}