{"id":"W4402569628","doi":"10.1109/access.2024.3462635","title":"Knowledge Graph Generation and Application for Unstructured Data Using Data Processing Pipeline","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cistel Technology (Canada); Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Unstructured data; Pipeline (software); Graph; Data modeling; Graph database; Data mining; Big data; Database; Theoretical computer science; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003405378,0.0001031935,0.00009246212,0.00009380088,0.0002394245,0.001384083,0.00260479,0.00004297089,6.889459e-7],"category_scores_gemma":[0.00001964889,0.00009364561,0.000008938414,0.0005402999,0.00003632988,0.00343431,0.0009339004,0.00006631351,0.000002330334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001329571,"about_ca_system_score_gemma":0.0001292644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004901108,"about_ca_topic_score_gemma":0.00005043521,"domain_scores_codex":[0.9987315,0.00001281115,0.0001909075,0.0008296935,0.00009562796,0.0001394382],"domain_scores_gemma":[0.9982017,0.00004456126,0.00005735723,0.001574774,0.00007385167,0.00004780921],"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":[6.460067e-7,0.0000159333,0.00001101864,0.00008677023,0.000006969845,3.530887e-7,0.00009029515,0.0000759957,0.005686735,0.00223983,0.008440872,0.9833446],"study_design_scores_gemma":[0.00008166218,0.000003668968,0.00002731901,0.00002970093,0.00002453325,0.00001185286,0.000004215142,0.9633909,0.001361269,0.001653939,0.03329418,0.000116795],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001947728,0.001509517,0.9948637,0.0003045266,0.0003570254,0.0003180096,0.0005052206,0.0001616048,0.00003267311],"genre_scores_gemma":[0.4651782,0.00008571172,0.5293853,0.0001248775,0.001440629,0.00009291951,0.003611011,0.00002955488,0.00005184801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9832278,"threshold_uncertainty_score":0.9996526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.208256562006371,"score_gpt":0.4276106568465334,"score_spread":0.2193540948401625,"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."}}