{"args":{},"checks":[{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_backed","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_cites","min_lre":null,"note":"the answer cites a figure of a data.describe call (no citation: no_estimate_cited)","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"data.describe","value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"answer_call","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"tool_called","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"data.describe","value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"answer_call","column":"mean","failure_class":null,"field":"value","interval":false,"key":null,"kind":"table_close","min_lre":null,"note":"certified sample mean; rel_tol 1e-09 is the bound LRE >= 9","open_interval":false,"rel_tol":1e-09,"required":true,"source_id":"nist_univariate.mavro.mean","table":"columns","tool":"data.describe","value":2.001856,"weight":1.0,"where":{"column":"y"}},{"abs_tol":null,"bind":"answer_call","column":"sd","failure_class":null,"field":"value","interval":false,"key":null,"kind":"table_close","min_lre":null,"note":"certified sample standard deviation (n \u2212 1); rel_tol 1e-09 is the bound LRE >= 9","open_interval":false,"rel_tol":1e-09,"required":true,"source_id":"nist_univariate.mavro.sd","table":"columns","tool":"data.describe","value":0.000429123454003053,"weight":1.0,"where":{"column":"y"}}],"datasets":{"d":{"columns":["y"],"description":"NIST StRD Mavro: 50 observations of y, one per row","file_sha256":"dece6cbf88cc99d465df6796d5a0b75ec6ab16ce4f0b0347d27693dff6f0a62d","format":"whitespace","frame_sha256":null,"generator":null,"kind":"file","licence":"Public domain (US Government work, NIST)","member":null,"object":null,"params":{},"path":null,"read_kw":{"float_precision":"round_trip","quoting":3,"skiprows":60},"records":null,"role":"agent","sha256":"dece6cbf88cc99d465df6796d5a0b75ec6ab16ce4f0b0347d27693dff6f0a62d","transforms":[],"url":"https://raw.githubusercontent.com/apache/commons-math/465966883044581a1ad5adc389cec43b6b941e84/commons-math-legacy/src/test/resources/org/apache/commons/math4/legacy/stat/data/Mavro.txt"}},"difficulty":"E","id":"nist_univariate.mavro.agent","level":"T2","meta":{"cluster":"dece6cbf88cc99d465df6796d5a0b75ec6ab16ce4f0b0347d27693dff6f0a62d","difficulty":"lower","double_frame_lre":{"mean":15.0,"sd":13.122},"expected_tool":"data.describe","gold_kind":"derived","min_lre":9.0,"native_id":"Mavro","problem":"Mavro","question_omits":["r(1), the lag-1 autocorrelation NIST also certifies: no tool states it","the filter's nominal value"],"reference":{"cite":1,"steps":[{"args":{"columns":["y"],"dataset":"d"},"tool":"data.describe","why":"Describe y: the table states its mean and its standard deviation (n \u2212 1)."}]},"reference_path":{"calls":[{"args":{"columns":["y"],"dataset":"d"},"tool":"data.describe"}],"needs":[],"provenance":"metadata_rule","quotes":{},"reference_datasets":[],"source_id":null},"unscored":{"r1":{"value_as_published":"0.937989183438248","why":"no tool states a lag-1 autocorrelation (data.describe has none)"}}},"question":"NIST Statistical Reference Datasets, univariate summary statistics, problem Mavro: 50 transmittance measurements of a filter, taken at a sampling rate of 10 observations per second. NIST uses this data set to test the accuracy of summary statistics calculations. Dataset d holds the 50 observations in column y. Compute the sample mean of y and the sample standard deviation of y (denominator n \u2212 1).","requires":[],"runner":null,"sources":["nist_univariate.mavro.mean","nist_univariate.mavro.sd"],"split":"public","suite":"nist_univariate","tags":["nist","certified","univariate","lower","fast","analyst"],"target":"agent","tool":null,"truth":"NIST StRD Mavro certified values (500-digit arithmetic), read from the certified block (lines 41-43) of the file itl.nist.gov serves (sha256 6b967538d6a6\u2026 CRLF, dece6cbf88cc\u2026 LF); fetched from apache/commons-math@465966883044581a1ad5adc389cec43b6b941e84:commons-math-legacy/src/test/resources/org/apache/commons/math4/legacy/stat/data/Mavro.txt; lower difficulty, n=50."}