{"id":"W4402029541","doi":"10.1007/978-3-031-70368-3_12","title":"MEGA: Multi-encoder GNN Architecture for Stronger Task Collaboration and Generalization","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generalization; Task (project management); Mega-; Architecture; Encoder; Artificial intelligence; Computer architecture; Operating system; Systems engineering; Mathematics; Engineering; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006045459,0.0004301488,0.0003547808,0.0007463938,0.0003048748,0.001232506,0.0009442479,0.0002788774,0.000009718815],"category_scores_gemma":[0.00009701485,0.000389674,0.00008186429,0.0006179709,0.0003281592,0.0005474535,0.0004699939,0.0005116597,0.0000109995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001776415,"about_ca_system_score_gemma":0.0003677691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007954821,"about_ca_topic_score_gemma":0.0001590789,"domain_scores_codex":[0.9971328,0.00003263912,0.0004160032,0.001383768,0.0005903312,0.0004444954],"domain_scores_gemma":[0.9985117,0.0002464627,0.0002017651,0.0005786239,0.0003156284,0.0001458084],"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":[0.0000128827,0.00002664388,0.00002312182,0.0001516763,0.00003068389,0.00002759013,0.004511235,0.2911292,0.001055703,0.1603681,0.0001582839,0.5425048],"study_design_scores_gemma":[0.0003411833,0.0001147188,0.00003841352,0.0001758042,0.00001368984,0.00002514184,9.844917e-7,0.9034638,0.0002357538,0.07492191,0.02021329,0.0004553303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003205068,0.001156476,0.9934537,0.001942654,0.001859316,0.000671951,0.00001622769,0.0001920321,0.0006755816],"genre_scores_gemma":[0.03172313,0.00006457095,0.9626279,0.001583377,0.0005584205,0.00004251616,0.00003990958,0.00006061171,0.0032996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6123346,"threshold_uncertainty_score":0.9998555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.018507009773168,"score_gpt":0.2667492491617782,"score_spread":0.2482422393886102,"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."}}