{"id":"W4200584380","doi":"10.1016/j.biortech.2021.126468","title":"Machine learning-aided causal inference for unraveling chemical dispersant and salinity effects on crude oil biodegradation","year":2021,"lang":"en","type":"article","venue":"Bioresource Technology","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Fisheries and Oceans Canada; National Research Council Canada; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fisheries and Oceans Canada; Canada Foundation for Innovation; Dairy Farmers of Ontario","keywords":"Dispersant; Biodegradation; Salinity; Environmental science; Petroleum; Biochemical engineering; Causal inference; Chemistry; Petroleum engineering; Ecology; Engineering; Biology; Mathematics; Organic chemistry","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":[0.00009590719,0.0001837673,0.0001921241,0.0000159875,0.0001468623,0.00001648742,0.000146061,0.0002460628,0.00007334138],"category_scores_gemma":[0.0003240801,0.0001696084,0.00004107845,0.0002085435,0.0003697957,0.00003596431,0.0003032407,0.0002692111,0.00003395047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001423494,"about_ca_system_score_gemma":0.000006354281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000874505,"about_ca_topic_score_gemma":0.00002549975,"domain_scores_codex":[0.9989142,0.00003335128,0.0001664611,0.000450627,0.0001428505,0.0002925434],"domain_scores_gemma":[0.9994761,0.0001475932,0.00007460687,0.0002197656,0.000004299321,0.00007761415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001345869,0.0002278111,0.2855099,0.00005739155,0.0000365687,0.00003994559,0.0002292268,0.002847734,0.4065339,0.001053799,0.00005506947,0.3032741],"study_design_scores_gemma":[0.005462772,0.00182937,0.104736,0.0002322409,0.0002509945,0.0001936141,0.001237291,0.253987,0.5604956,0.005380577,0.06398569,0.00220893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887961,0.0001482273,0.009708002,0.000836667,0.00004230621,0.0000941215,0.000004919359,0.0001483688,0.0002212854],"genre_scores_gemma":[0.9840199,0.0001423608,0.01514469,0.0002029798,0.00002398939,0.00003178391,0.0000329616,0.0000220278,0.0003792572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3010651,"threshold_uncertainty_score":0.6916431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006995791084794535,"score_gpt":0.2207018298235999,"score_spread":0.2137060387388054,"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."}}