{"id":"W6894383489","doi":"10.5683/sp3/8fxngm","title":"The CSTH Dataset","year":2025,"lang":"en","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Benchmark (surveying); Instrumentation (computer programming); Time series; Process (computing); Fault detection and isolation; Series (stratigraphy); Multivariate statistics","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":[0.001661599,0.003581219,0.00173478,0.003642557,0.001121785,0.002322587,0.004363008,0.003203793,0.01804503],"category_scores_gemma":[0.006546474,0.0005345662,0.002163331,0.0049811,0.0006510535,0.001722926,0.001869905,0.002418349,0.03546416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002045398,"about_ca_system_score_gemma":0.002498923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02775259,"about_ca_topic_score_gemma":0.04702221,"domain_scores_codex":[0.997646,0.0004447226,0.0002856392,0.0006831179,0.0006435345,0.0002968773],"domain_scores_gemma":[0.9977811,0.0005311192,0.0001550244,0.0006257641,0.0007080088,0.0001990317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002209044,0.0002144805,0.003296381,0.00090322,0.0001319435,0.0001319058,0.00003747617,0.003618428,0.0004275391,0.0007417123,0.9782722,0.01200389],"study_design_scores_gemma":[0.000604807,0.0002516708,0.01293396,0.0004489515,0.0001466211,0.0004455204,0.0002936258,0.01493132,0.002101572,0.00307519,0.9646273,0.0001395612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002631342,0.0004573705,0.0005169627,0.0002906772,0.0001708472,0.00007240981,0.9926931,0.001574581,0.001592628],"genre_scores_gemma":[0.001871842,0.0001044461,0.0008027794,0.00007784634,0.00001652531,0.00008792834,0.9964234,0.00005245546,0.0005626908],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02775259,"threshold_uncertainty_score":0.06036669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01835573125133849,"score_gpt":0.3040487314707264,"score_spread":0.2856930002193879,"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."}}