{"id":"W4414878045","doi":"","title":"A graph-structured distance for heterogeneous datasets with meta variables","year":2024,"lang":"en","type":"other","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis; HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Office National d'études et de Recherches Aérospatiales; Fonds de recherche du Québec – Nature et technologies; European Commission","keywords":"Weighting; Feature (linguistics); Hyperparameter; Regression; Variable (mathematics); Multilayer perceptron; Data point; Regression analysis; Meta learning (computer science)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004995261,0.0008992282,0.0009704986,0.0008756144,0.0001686654,0.000655097,0.002348267,0.0005396463,0.00009783217],"category_scores_gemma":[0.00003888661,0.00069529,0.0004956939,0.000967607,0.0001769442,0.0002675292,0.0004434475,0.0005097127,0.00002595401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058749,"about_ca_system_score_gemma":0.0001878475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001200206,"about_ca_topic_score_gemma":0.003278807,"domain_scores_codex":[0.9965578,0.0001405423,0.0004423053,0.001434495,0.0004620904,0.0009628212],"domain_scores_gemma":[0.9965544,0.0001102413,0.000380734,0.00255821,0.00005836389,0.0003380433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000968808,0.0001741836,0.00002144352,0.0005903055,0.003428416,0.0006780453,0.0001285277,0.0005408038,0.0001954584,0.5703247,0.4170166,0.00680469],"study_design_scores_gemma":[0.00078317,0.0004207304,0.0000113377,0.0004526261,0.001593194,0.0008896156,0.00001263228,0.03246715,0.002335948,0.2153713,0.7437001,0.001962217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003337411,0.01601789,0.9708473,0.0005948802,0.0004350953,0.001547336,0.004662116,0.002390818,0.003501192],"genre_scores_gemma":[0.002621776,0.0004041462,0.8768944,0.001911785,0.0004277013,0.003527368,0.0008186915,0.00124556,0.1121486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3549534,"threshold_uncertainty_score":0.9995498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009909839266732981,"score_gpt":0.2242475920476452,"score_spread":0.2143377527809122,"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."}}