{"args":{},"checks":[{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"tool_called","min_lre":null,"note":"the canonical tool for this design","open_interval":false,"rel_tol":null,"required":false,"source_id":null,"table":null,"tool":"infer.ate","value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"any_of","min_lre":null,"note":"infer.ate (or infer.neyman)","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":[{"abs_tol":null,"bind":"any","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":"infer.ate","value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","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":"infer.neyman","value":null,"weight":1.0,"where":null}],"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"any_of","min_lre":null,"note":"headline figure against the truth","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":[{"abs_tol":0.18895315710176505,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"ate","kind":"figure_close","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"infer.ate","value":0.32,"weight":1.0,"where":null},{"abs_tol":0.18895315710176505,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"ate","kind":"figure_close","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"infer.neyman","value":0.32,"weight":1.0,"where":null}],"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_backed","min_lre":null,"note":"every number traced to a tool call or the question","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":"any_of","min_lre":null,"note":"the answer cites the expected tool's figures","open_interval":false,"rel_tol":null,"required":false,"source_id":null,"table":null,"tool":null,"value":[{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_cites","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"infer.ate","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":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"infer.neyman","value":null,"weight":1.0,"where":null}],"weight":1.0,"where":null}],"datasets":{"dados":{"columns":null,"description":"Uma linha por aluno inscrito no programa. nota: nota padronizada na prova municipal de matem\u00e1tica ao fim do ano; tratado: 1 se o aluno recebeu o refor\u00e7o, 0 se ficou na lista de espera; nota_base: nota padronizada na mesma prova no in\u00edcio do ano, antes do programa.","file_sha256":null,"format":null,"frame_sha256":null,"generator":"magi_bench.generators:rct","kind":"generator","licence":null,"member":null,"object":null,"params":{"effect":0.32,"n":2000,"seed":635839296},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":null,"transforms":[],"url":null}},"difficulty":"E","id":"tool_selection.rct_individual.test.s1003","level":"T2","meta":{"acceptable_tools":["infer.neyman"],"expected_tool":"infer.ate","family":"rct_individual","features":["random_assignment","individual_assignment","cross_section"],"headline_keys":{"infer.ate":["ate"],"infer.neyman":["ate"]},"lesson":"Random assignment with full take-up identifies the effect as a difference in means: infer.ate (infer.neyman for the design-based variance).","params":{"effect":0.32,"n":2000,"seed":635839296},"reference":{"cite":1,"note":"","steps":[{"args":{"dataset":"dados","treatment":"tratado","y":"nota"},"tool":"infer.ate","why":"Atribui\u00e7\u00e3o por sorteio com ades\u00e3o completa: diferen\u00e7a de m\u00e9dias."}]},"seed":1003,"tolerance":0.18895315710176505,"trap_tools":[],"truth_value":0.32,"variant":1},"question":"As vagas do programa de tutoria foram distribu\u00eddas por sorteio entre os alunos inscritos, e todos os sorteados participaram. Quanto a tutoria mudou, em m\u00e9dia, a nota de matem\u00e1tica?","requires":[],"runner":null,"sources":[],"split":"test","suite":"tool_selection","tags":["tool_selection","rct_individual","test"],"target":"agent","tool":null,"truth":"DGP generators.rct(n=2000, effect=0.32); truth = effect; tolerance 4 \u00d7 SE of the difference in means (statsmodels OLS, HC1) = 0.1890"}