{"id":"W2770285924","doi":"10.1002/sta4.167","title":"Bump hunting by topological data analysis","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Studienstiftung des Deutschen Volkes","keywords":"Statistical inference; Persistent homology; Topological data analysis; Inference; Kernel density estimation; Computer science; Kernel (algebra); Data set; Statistical hypothesis testing; Statistical analysis; Algorithm; Mathematics; Data mining; Topology (electrical circuits); Statistics; Discrete mathematics; Artificial intelligence; Combinatorics","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004828981,0.000103395,0.0002593464,0.0001525423,0.0005481624,0.0007078116,0.00558001,0.00005441949,0.000320855],"category_scores_gemma":[0.0009452458,0.00007191251,0.00009977363,0.0008083986,0.0001396532,0.0008953024,0.003314095,0.0001115632,0.0001232572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009901897,"about_ca_system_score_gemma":0.00001191305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008703967,"about_ca_topic_score_gemma":0.0001219842,"domain_scores_codex":[0.9985317,0.00004634419,0.0001856548,0.0006672135,0.0002661862,0.0003029166],"domain_scores_gemma":[0.9960227,0.0001574849,0.0001616727,0.003511539,0.00003448856,0.0001121136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000009763733,0.0003659007,0.3903705,0.000009248495,0.001751183,0.000171082,0.0001219309,0.00005809475,0.0002377104,0.1101126,0.06801969,0.4287724],"study_design_scores_gemma":[0.0006842316,0.0001890178,0.4107007,0.000005762033,0.001015382,0.000007978079,0.0001280655,0.189515,0.0003774202,0.03056442,0.3657519,0.00106013],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03150123,0.0003446935,0.9540554,0.006349409,0.0001834045,0.00005053561,0.00033952,0.0001401524,0.007035626],"genre_scores_gemma":[0.9760015,0.00006240905,0.02161041,0.0003477878,0.00005162359,0.000001824135,0.0001976994,0.000002134472,0.001724595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445003,"threshold_uncertainty_score":0.9998003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07395390870928459,"score_gpt":0.3424577054442873,"score_spread":0.2685037967350027,"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."}}