{"id":"W3092086356","doi":"10.48550/arxiv.2010.03962","title":"Test-Cost Sensitive Methods for Identifying Nearby Points","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Feature (linguistics); Set (abstract data type); Artificial intelligence; Point (geometry); Machine learning; Data mining; Tree (set theory); Data set; Test set; Reinforcement learning; Test data; Decision tree; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007275165,0.0004217602,0.0005102059,0.000294259,0.0001974698,0.0003491509,0.002892026,0.0003213372,0.000007042428],"category_scores_gemma":[0.0007644122,0.0005302922,0.0002813521,0.0006696479,0.0001222099,0.0006108143,0.005616499,0.0006566539,0.00006729781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251783,"about_ca_system_score_gemma":0.000242847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000961965,"about_ca_topic_score_gemma":0.000009344402,"domain_scores_codex":[0.9970918,0.0002852806,0.0002678716,0.001799351,0.00009030195,0.0004654519],"domain_scores_gemma":[0.9963585,0.001036365,0.0003807156,0.001710152,0.0002775318,0.0002367167],"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":[0.0002201916,0.0005808631,0.001785892,0.001146582,0.001020586,0.002691364,0.004038967,0.004117623,0.006844882,0.8103559,0.03207193,0.1351252],"study_design_scores_gemma":[0.0005872996,0.0001594755,0.0005132135,0.0003084043,0.0001848714,0.00001886969,0.0001172479,0.717347,0.02048901,0.2540209,0.005170023,0.001083701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001494958,0.00001663308,0.9938051,0.000419653,0.0004869354,0.0008765634,0.0001905787,0.001144913,0.001564718],"genre_scores_gemma":[0.2899403,0.00003909772,0.7092011,0.0003077836,0.00008787189,0.000006566345,0.00008910373,0.00003710304,0.000291057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7132294,"threshold_uncertainty_score":0.9997149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2006222045870076,"score_gpt":0.3003322735108832,"score_spread":0.09971006892387557,"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."}}