{"id":"W4393282086","doi":"10.1016/j.compchemeng.2024.108677","title":"Multi-source heterogeneous data integration for incident likelihood analysis","year":2024,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; Memorial University of Newfoundland","funders":"Canada Excellence Research Chairs, Government of Canada; Mary Kay O'Connor Process Safety Center; Genome Canada","keywords":"Leverage (statistics); Computer science; Incident report; Data mining; Hazardous waste; Data extraction; Data source; Data science; Risk analysis (engineering); Engineering; Computer security; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.000890128,0.0001854525,0.0003908161,0.0005013095,0.00004982644,0.0004708042,0.001259622,0.00008972318,0.00002448857],"category_scores_gemma":[0.00072889,0.0001484607,0.0004099243,0.001739121,0.00002176444,0.0002789435,0.0004314618,0.0001652874,0.00004568338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007391678,"about_ca_system_score_gemma":0.00002309578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001994779,"about_ca_topic_score_gemma":0.000009432143,"domain_scores_codex":[0.9978161,0.00002186756,0.0005733212,0.0007822266,0.0005325625,0.0002738533],"domain_scores_gemma":[0.9976713,0.001062498,0.00005773356,0.0009498784,0.0001030897,0.0001555054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001249347,0.00004522842,0.0001049581,0.00002387215,0.0009433067,0.00001772283,0.0004682925,0.6134824,0.03060373,0.00005632431,0.002300484,0.3519412],"study_design_scores_gemma":[0.0001018509,0.00000892601,0.00006617109,0.0000233023,0.0003137595,0.000005997631,0.00001944727,0.9850224,0.005047712,0.0001546647,0.009063785,0.0001720145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04249154,0.000781061,0.9556679,0.0003628222,0.0003737496,0.00009366721,0.00003939541,0.0001854624,0.000004394769],"genre_scores_gemma":[0.8841764,0.00002552752,0.1152362,0.00005626696,0.0002184341,0.00001035054,0.0001989161,0.00001915892,0.00005877071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8416849,"threshold_uncertainty_score":0.605405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0723116031823647,"score_gpt":0.3479328123944992,"score_spread":0.2756212092121345,"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."}}