{"id":"W4394877201","doi":"10.1145/3658673","title":"CGKPN: Cross-Graph Knowledge Propagation Network with Adaptive Connection for Reasoning-Based Machine Reading Comprehension","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Central China Normal University; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Theoretical computer science; Graph; Comprehension; Semantic memory; Natural language processing; Cognition; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0002712431,0.0001900214,0.000219272,0.0004723747,0.0003739215,0.0001852441,0.0002906604,0.0002009806,0.000002527752],"category_scores_gemma":[0.00001738387,0.0001548446,0.00005411318,0.0007966211,0.00008998811,0.000191874,0.0000131764,0.0002765894,0.000007777197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009217649,"about_ca_system_score_gemma":0.00005960156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006385998,"about_ca_topic_score_gemma":0.00006999091,"domain_scores_codex":[0.998697,0.00004334265,0.0003008003,0.0005826048,0.0001135053,0.0002627932],"domain_scores_gemma":[0.9989491,0.0002203745,0.00007333086,0.0005290877,0.0001794127,0.0000486764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001981502,0.0001683211,0.0003783588,0.0005373809,0.0002514848,0.00001839969,0.0004600722,0.2832667,0.0004109305,0.3984492,0.000121191,0.3157398],"study_design_scores_gemma":[0.0002419748,0.0006669142,0.00001255489,0.0007366664,0.00003022004,0.00008881544,0.00009273598,0.9856922,0.003533493,0.004341596,0.004372002,0.0001908332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003957329,0.002247476,0.9902279,0.0006814194,0.001204985,0.0007710706,0.000006714904,0.0008450443,0.00005809394],"genre_scores_gemma":[0.9700148,0.00005313983,0.02933429,0.00001797115,0.00005884278,0.0003240468,0.000004839897,0.00002139086,0.0001706705],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9660575,"threshold_uncertainty_score":0.6314378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582332152472658,"score_gpt":0.2784440367811473,"score_spread":0.2526207152564207,"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."}}