{"id":"W4313575157","doi":"10.3390/make5010004","title":"IPPT4KRL: Iterative Post-Processing Transfer for Knowledge Representation Learning","year":2023,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Embedding; Computer science; Benchmarking; Representation (politics); Artificial intelligence; Graph; Machine learning; Feature learning; Knowledge representation and reasoning; Iterative refinement; Task (project management); Transfer of learning; Theoretical computer science","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":[0.0005465964,0.000239809,0.0002327622,0.0003553156,0.0009746287,0.0002684078,0.000179197,0.0001198082,0.000007120046],"category_scores_gemma":[0.0003498064,0.0002339431,0.0001046193,0.001081995,0.00004797992,0.001055314,0.00009027306,0.0007063609,0.00005858113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004368819,"about_ca_system_score_gemma":0.00004252937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001184773,"about_ca_topic_score_gemma":0.0000470442,"domain_scores_codex":[0.9981967,0.0002906433,0.0002932785,0.0006566909,0.0001300529,0.0004326898],"domain_scores_gemma":[0.9986547,0.0007224363,0.00009752918,0.0001428999,0.0002678166,0.000114684],"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":[0.00009179237,0.00007878058,0.003284256,0.0001617267,0.00002689227,0.000008834158,0.01059956,0.008242996,0.01426234,0.002102303,0.0002412472,0.9608993],"study_design_scores_gemma":[0.0007291352,0.0003115342,0.004170518,0.00009506521,0.00001981027,0.00003715396,0.00045128,0.9526628,0.001195448,0.0009180579,0.03908361,0.0003256534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07738749,0.002346141,0.9143376,0.0007721506,0.0007759383,0.0004115544,0.000002493211,0.001528298,0.002438272],"genre_scores_gemma":[0.988169,0.0002207778,0.003446305,0.00002936641,0.0003104812,0.00008371683,0.00009057322,0.00004232512,0.007607504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9605736,"threshold_uncertainty_score":0.9539921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02632518861328091,"score_gpt":0.3401069038153142,"score_spread":0.3137817152020332,"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."}}