{"id":"W7082255170","doi":"10.48448/6tcr-a316","title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","year":2025,"lang":"en","type":"other","venue":"Open MIND","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pipeline (software); Pruning; Focus (optics); Identification (biology); Code (set theory); Process (computing); Code generation; Solver","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":[0.00221391,0.001634565,0.001170991,0.0007616106,0.0009679847,0.001730809,0.003110074,0.001698786,0.007735275],"category_scores_gemma":[0.00973575,0.001159241,0.001619532,0.0005487988,0.001594636,0.002649447,0.00494485,0.003445726,0.002838725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001475995,"about_ca_system_score_gemma":0.004052534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008067145,"about_ca_topic_score_gemma":0.01416093,"domain_scores_codex":[0.9984486,0.0004875918,0.00007447656,0.00037707,0.000403259,0.0002088871],"domain_scores_gemma":[0.9971214,0.001525824,0.0001541068,0.0006944673,0.0003508739,0.0001534002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003336294,0.0002318154,0.002742874,0.0002996143,0.0001324904,0.0002875571,0.0005372773,0.5355287,0.01194995,0.04037519,0.01224427,0.3953367],"study_design_scores_gemma":[0.0000178659,0.00002220408,0.0000526843,0.000006957568,0.000007929963,0.00001539278,0.00001457847,0.9880033,0.001900171,0.008377359,0.001574365,0.000007118657],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01426889,0.0001899899,0.9687363,0.0003453837,0.00004590015,0.0002030503,0.0001332068,0.01367282,0.002404548],"genre_scores_gemma":[0.2053751,0.0001065275,0.7876983,0.0004672103,0.00003946053,0.000326071,0.0006832007,0.002426104,0.002878111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008067145,"threshold_uncertainty_score":0.02587712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05109344600361556,"score_gpt":0.2886209715218027,"score_spread":0.2375275255181871,"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."}}