{"id":"W7106833073","doi":"10.48448/qfw9-bf83","title":"Reliable and Cost-Effective Exploratory Data Analysis via Graph-Guided RAG","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Executable; Workflow; Usability; Python (programming language); Security token; Semantics (computer science); Code (set theory); Graph; Code generation","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":[0.003165826,0.001734564,0.0006356987,0.002781285,0.00109049,0.002669557,0.002986288,0.001154612,0.004451316],"category_scores_gemma":[0.01582547,0.0007730095,0.002480649,0.001900523,0.001799908,0.004296327,0.004959922,0.002073248,0.003571476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001168189,"about_ca_system_score_gemma":0.003415112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005222254,"about_ca_topic_score_gemma":0.01107466,"domain_scores_codex":[0.9967445,0.00102813,0.0002057994,0.0008967941,0.0009375015,0.0001871946],"domain_scores_gemma":[0.9903587,0.004050464,0.0006834555,0.003784303,0.0008853512,0.0002377927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006333482,0.0006118291,0.00980767,0.00124875,0.0002409898,0.0006595604,0.001733526,0.0600681,0.0361211,0.05317432,0.06112602,0.7745746],"study_design_scores_gemma":[0.0001760091,0.0002183146,0.002182881,0.0001721965,0.0001115803,0.0004985828,0.000672296,0.7371224,0.0468963,0.154102,0.05771182,0.0001356899],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02014261,0.0004004437,0.8793911,0.001005628,0.00007755115,0.0005301795,0.002933772,0.0918951,0.003623415],"genre_scores_gemma":[0.1013516,0.0001672303,0.8843729,0.0003697083,0.00002748583,0.0003363281,0.007229052,0.004109446,0.00203619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005222254,"threshold_uncertainty_score":0.01674271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08636174637641099,"score_gpt":0.3686195995702256,"score_spread":0.2822578531938146,"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."}}