{"id":"W4412522544","doi":"10.1038/s41598-025-10012-2","title":"Modeling residue formation from crude oil oxidation using tree-based machine learning approaches","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Petroleum Processing and Analysis","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Gradient boosting; Leverage (statistics); Random forest; Combustion; Computer science; Crude oil; Boosting (machine learning); Artificial intelligence; Residual oil; Machine learning; Chemistry; Petroleum engineering; Engineering; Organic chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007195093,0.0006592909,0.0005252421,0.0007262311,0.0001812658,0.000579083,0.0005841564,0.0006132109,0.0005047457],"category_scores_gemma":[0.001084789,0.0002603534,0.000926316,0.0006126224,0.0002094784,0.0005512872,0.0002756515,0.0006073881,0.0002178209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004308564,"about_ca_system_score_gemma":0.000582877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006848988,"about_ca_topic_score_gemma":0.006533562,"domain_scores_codex":[0.9998338,0.00003546474,0.0000132255,0.00005226669,0.00003812229,0.00002705606],"domain_scores_gemma":[0.9996327,0.0002258241,0.00004996483,0.00002103352,0.0000604088,0.00001000475],"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":[0.00004659922,0.00005089435,0.004356612,0.00007088598,0.00004694777,0.00004744545,0.00002224086,0.9697379,0.004070056,0.0004753002,0.00015656,0.02091856],"study_design_scores_gemma":[7.525316e-7,0.000008650421,0.0005119287,0.000001965319,0.000003623755,0.000004485927,0.000002654442,0.998447,0.0007218468,0.000219838,0.00007508176,0.000002230788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5444311,0.000912076,0.4508806,0.0001244818,0.00004752539,0.00007552868,0.0008877562,0.0007165134,0.001924444],"genre_scores_gemma":[0.9574962,0.0003581344,0.04021828,0.00003030918,0.00001531609,0.00008315696,0.0008046989,0.00003265427,0.0009611908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006848988,"threshold_uncertainty_score":0.01361823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03714794488492984,"score_gpt":0.2501063096974144,"score_spread":0.2129583648124846,"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."}}