{"id":"W4391093649","doi":"10.1109/bigdata59044.2023.10386776","title":"Unstructured Transportation Safety Board Findings Categorization Using the Knowledge Graph Pipeline","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Categorization; Computer science; Pipeline (software); Graph; Knowledge graph; Data science; Information retrieval; Artificial intelligence; Theoretical computer science; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002794976,0.0001016523,0.000140037,0.0002741316,0.0003365122,0.0002073826,0.0005349893,0.00004803506,0.0005504574],"category_scores_gemma":[0.0003175295,0.0000588749,0.0000792775,0.002553111,0.00007307342,0.0003939592,0.00004639262,0.00007195248,0.0003267729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002199498,"about_ca_system_score_gemma":0.00003263911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001710129,"about_ca_topic_score_gemma":0.001204475,"domain_scores_codex":[0.9980966,0.0001489986,0.0005475113,0.0003301589,0.0006873966,0.000189325],"domain_scores_gemma":[0.9989104,0.0003548722,0.0001026235,0.0004288343,0.0001570907,0.0000461241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001218651,0.00007922764,0.003948697,0.00004056042,0.00006364127,0.00001004805,0.01412294,0.01756286,0.002688148,0.517214,0.2266889,0.2174592],"study_design_scores_gemma":[0.001076718,0.00004161757,0.1759717,0.00002080903,0.0001055255,0.000001663366,0.0169823,0.0948162,0.001939324,0.2317669,0.4767714,0.0005059476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1152389,0.00002829838,0.8713537,0.004188138,0.001367498,0.0004768789,0.00016367,0.000266967,0.006915952],"genre_scores_gemma":[0.9903997,0.00003369046,0.0007730992,0.0003766306,0.00007934874,0.000004774314,0.000253996,0.000009284554,0.008069471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8751608,"threshold_uncertainty_score":0.6027122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.14575456692883,"score_gpt":0.4031670788603776,"score_spread":0.2574125119315476,"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."}}