{"id":"W4411122144","doi":"10.1016/j.compositesb.2025.112701","title":"Tackling data scarcity in machine learning-based CFRP drilling performance prediction through a broad learning system with virtual sample generation (BLS-VSG)","year":2025,"lang":"en","type":"article","venue":"Composites Part B Engineering","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; UK Research and Innovation; Horizon 2020 Framework Programme; European Commission; Queen's University; Queen's University Belfast","keywords":"Scarcity; Materials science; Sample (material); Drilling; Composite material; Machine learning; Artificial intelligence; Computer science; Metallurgy; Chromatography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004358958,0.0004525014,0.0004523832,0.0003653179,0.0002434018,0.0001749805,0.0003743011,0.0001603985,0.000005347125],"category_scores_gemma":[0.0000870703,0.0004930052,0.00005516928,0.0007752737,0.00002397471,0.0006141284,0.0001070979,0.0009154587,0.000007793603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003197124,"about_ca_system_score_gemma":0.00003828719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009180771,"about_ca_topic_score_gemma":0.00003276774,"domain_scores_codex":[0.9979783,0.00004400862,0.0005608111,0.0005499316,0.0002820374,0.0005848526],"domain_scores_gemma":[0.9990307,0.0002331434,0.00006084341,0.0005291202,0.00005887151,0.00008730599],"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":[0.00001827456,0.00001668488,0.01608478,0.0006192887,0.00007289997,0.000006723945,0.000141263,0.9708875,0.01129255,0.00008395581,0.00002064355,0.000755388],"study_design_scores_gemma":[0.0007114742,0.00009823764,0.0006961251,0.001449178,0.00004842344,0.000009492087,0.0000340117,0.983501,0.009362999,3.362223e-7,0.003652495,0.0004361926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3209368,0.0009223497,0.6756626,0.000008715055,0.0006079401,0.0002053757,0.00002655139,0.00148724,0.0001424751],"genre_scores_gemma":[0.9903762,0.0001552602,0.008087293,0.000008418094,0.0003035888,0.00005198101,0.0008693191,0.0001080306,0.00003991439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6694394,"threshold_uncertainty_score":0.9997522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0130678098305929,"score_gpt":0.1974670495603057,"score_spread":0.1843992397297128,"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."}}