{"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":"every number of the answer is stated by a tool call","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":"answer_call","column":null,"failure_class":null,"field":"value","interval":true,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"QRData eval.py: strictly inside gold \u00b1 3% (a '%' gold divided by 100), on the answer figure after meta.answer_format","open_interval":true,"rel_tol":null,"required":true,"source_id":"qrdata.gold.368","table":null,"tool":null,"value":[6.3244,6.715599999999999],"weight":1.0,"where":null}],"datasets":{"billboard_impact":{"columns":null,"description":"The dataset billboard_impact.csv details information from a quasi-experiment assessing the influence of billboards on bank deposits in two cities: Porto Alegre (treatment group) and Florianopolis (control group). The csv file contains records with three variables: deposits (average bank deposits in Brazilian Reais), poa (A dummy indicator for the city of Porto Alegre. When it is zero, it means the samples are from Florianopolis.), and jul (A dummy for the month of July, or for the post intervention period. When it is zero it refers to samples from May, the pre-intervention period).","file_sha256":"3c3a97cca6fdd96f6856f7856b5f8bc786a31d1a9be78c9f610ef3070783e970","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"CC BY-NC 4.0","member":"data/billboard_impact.csv","object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"3c3a97cca6fdd96f6856f7856b5f8bc786a31d1a9be78c9f610ef3070783e970","transforms":[],"url":"https://raw.githubusercontent.com/xxxiaol/QRData/de450af45ff7101b328bb064c6b475f73414a7ed/benchmark/data.zip"}},"difficulty":"M","id":"qrdata_socsci.368","level":"T2","meta":{"agent_reach":{"blocked_by":[],"dtypes":{"billboard_impact":{"deposits":"int64","jul":"int64","poa":"int64"}},"named":{"outcome":["deposits"],"treatment":["poa"]},"reachable":true,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":2,"unit_scale":1.0},"answer_format_from":{"figure_transform":null,"round_to":"nearest hundredth","unit_scale":"1.0: an estimator's figure is on the gold's own scale"},"cluster":"billboard_impact.csv","expected_tool":"infer.did_2x2","family":"numerical","headline_keys":{"infer.did_2x2":["did"]},"naive":{"dataset":"billboard_impact","treatment":"poa","y":"deposits"},"native":{"answer":"6.52","keywords":["Causality","Observational data","Difference in differences"],"multiple_choices":null,"question_type":"numerical","reference":"Causal Inference for the Brave and True 13"},"native_id":368,"reference":{"cite":1,"note":"Caminho de refer\u00eancia inferido \u00e0 m\u00e3o.","steps":[{"args":{"dataset":"billboard_impact","post":"jul","treated":"poa","y":"deposits"},"tool":"infer.did_2x2","why":"Two-group, two-period difference in differences of deposits: Porto Alegre against Florianopolis, July against May."}]},"reference_path":{"calls":[{"args":{"dataset":"billboard_impact","post":"jul","treated":"poa","y":"deposits"},"tool":"infer.did_2x2"}],"needs":[],"provenance":"hand_inferred","quotes":{},"reference_datasets":[],"source_id":null},"reference_why":"Two-group, two-period difference in differences of deposits: Porto Alegre against Florianopolis, July against May."},"question":"What was the average increase in bank deposits per customer in Porto Alegre after the billboard intervention, as estimated by the difference-in-differences approach? Please round the final answer to the nearest hundredth.","requires":[],"runner":null,"sources":["qrdata.gold.368","qrdata.eval_py"],"split":"public","suite":"qrdata_socsci","tags":["econ-bench","external","qrdata","brave_and_true","numerical","reference_path","agent_reachable","naive"],"target":"agent","tool":null,"truth":"QRData gold: benchmark/QRData.json item 368 at de450af45ff7101b328bb064c6b475f73414a7ed"}