{"id":"W4413133192","doi":"10.3390/computers14080319","title":"Optimizing Data Pipelines for Green AI: A Comparative Analysis of Pandas, Polars, and PySpark for CO2 Emission Prediction","year":2025,"lang":"en","type":"article","venue":"Computers","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pipeline (software); Computer science; Energy consumption; Pipeline transport; Geospatial analysis; Efficient energy use; Real-time computing; Engineering; Remote sensing; Operating system; Electrical engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001260435,0.00008941746,0.0002444272,0.0001731104,0.00007611041,0.00001858396,0.0001509924,0.00004505495,0.00000170791],"category_scores_gemma":[0.00000922722,0.00008183253,0.00004504711,0.0002970996,0.00001414862,0.0001288297,0.00006873548,0.00004772028,7.036391e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001420371,"about_ca_system_score_gemma":0.00001426709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001575091,"about_ca_topic_score_gemma":0.000007666908,"domain_scores_codex":[0.999474,0.000007570736,0.0002005612,0.0001637537,0.00004630312,0.0001077967],"domain_scores_gemma":[0.9994881,0.0001515115,0.00003239562,0.0002309522,0.00005717761,0.00003981882],"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":[0.0002462489,0.00006697638,0.02125297,0.001204934,0.002416671,4.115089e-7,0.002183958,0.7629178,0.01128325,0.0002219114,0.1195581,0.07864679],"study_design_scores_gemma":[0.0003666173,0.00002861495,0.002074512,0.0001220532,0.0002737887,2.529333e-7,0.00004741433,0.9682563,0.001103404,0.00002462666,0.02763302,0.00006937559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1367826,0.001102615,0.8605995,0.0001668785,0.0002485462,0.0002934524,0.0006683899,0.00008357545,0.00005439456],"genre_scores_gemma":[0.9679558,0.0001491623,0.03094062,0.00005116432,0.00007043973,0.00001738237,0.0007248726,0.000008488631,0.00008208864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8311732,"threshold_uncertainty_score":0.3337034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03732970444766449,"score_gpt":0.3054617075539457,"score_spread":0.2681320031062813,"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."}}