{"id":"W2245362805","doi":"10.48550/arxiv.1506.03318","title":"Noisy data clusters are hollow","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Cluster (spacecraft); Computer science; Data science","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":[0.00710261,0.001137195,0.003346075,0.00572023,0.004904012,0.009535353,0.003274546,0.003002605,0.007181232],"category_scores_gemma":[0.04891966,0.00185163,0.001647246,0.007366506,0.009772219,0.01476205,0.01211739,0.004169468,0.003382007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003139345,"about_ca_system_score_gemma":0.002328901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003643609,"about_ca_topic_score_gemma":0.002410341,"domain_scores_codex":[0.9875534,0.002461583,0.0009799768,0.004231135,0.003959364,0.0008146409],"domain_scores_gemma":[0.9686928,0.01029748,0.002534707,0.01277789,0.004520086,0.00117707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001087262,0.0001247597,0.01193051,0.001018258,0.0004992471,0.0008712256,0.00405891,0.07211196,0.004598791,0.6860215,0.05460425,0.1630733],"study_design_scores_gemma":[0.00004931393,0.00007887855,0.003097687,0.000203509,0.00006439463,0.0005715022,0.001061223,0.1089789,0.003185967,0.833293,0.04930301,0.0001125578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06226761,0.004912272,0.9012866,0.01067402,0.0009864002,0.0002601113,0.003837314,0.002812635,0.01296299],"genre_scores_gemma":[0.6593349,0.003937503,0.3041054,0.004466631,0.001689147,0.000741677,0.007347997,0.001754067,0.0166226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009535353,"threshold_uncertainty_score":0.03756261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2173035908849107,"score_gpt":0.2176799927275834,"score_spread":0.0003764018426727356,"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."}}