{"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 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":"answer_call","column":null,"failure_class":null,"field":"value","interval":true,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"CRB estimate_within_solution_ci: the answer figure inside the gold 95% interval effect \u00b1 1.96\u00b7|SE| of source crb_papers.q075.gold (closed, evaluate_result.py; no --auto-rescale)","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":[0.004194364416815366,0.05896056542436018],"weight":1.0,"where":null},{"abs_tol":1.397096964478184e-08,"bind":"answer_call","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"replication cell: the gold effect to rel 1e-6 (abs floor 1e-6\u00b7SE); never required","open_interval":false,"rel_tol":1e-06,"required":false,"source_id":"crb_papers.q075.gold","table":null,"tool":null,"value":0.03157746492058777,"weight":1.0,"where":null},{"abs_tol":1.397096964478184e-08,"bind":"answer_call","column":null,"failure_class":null,"field":"se","interval":false,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"replication cell: the gold SE to rel 1e-6; never required","open_interval":false,"rel_tol":1e-06,"required":false,"source_id":"crb_papers.q075.gold","table":null,"tool":null,"value":0.01397096964478184,"weight":1.0,"where":null}],"datasets":{"ds_0045":{"columns":null,"description":"| Variable Name      | Description                                                                 |\n|--------------------|-----------------------------------------------------------------------------|\n| (unnamed)          | Row identifier / dataset index (row number)                                 |\n| D                  | Log of the number of broadband providers in the county (natural log of provider count from FCC records) |\n| outcome            | Rescaled measure of partisan affect: difference in feeling\u2011thermometer scores toward the in\u2011 and out\u2011party presidential candidates (scaled 0\u20131) |\n| Total_log          | Log of the state right\u2011of\u2011way (ROW) regulation index (Beyer & Kende 2003)    |\n| region             | Census region categorical label (e.g., \"1: Northeast\", \"2: Midwest\", \"3: South\", \"4: West\") |\n| percent_black      | Proportion of the county population identifying as Black (fraction between 0 and 1) |\n| percent_white      | Proportion of the county population identifying as White (fraction between 0 and 1) |\n| percent_male       | Proportion of the county population that is male (fraction between 0 and 1)  |\n| lowed              | Indicator for low\u2011education county status (e.g., \"0: Not low\u2011education type\") |\n| unemploymentrate   | County unemployment rate (percent)                                          |\n| density            | County population density (as provided in the ICPSR County Characteristics file) |\n| HHINC_log          | Log of median household income in the county (natural log of HH income)     |\n| year               | Survey year (2004 or 2008)                                                  |\n| state              | U.S. state name (state of residence / county mapping)                       |\n\nData Description: This merged file brings together individual survey records from national rolling\u2011cross\u2011section studies (NAES 2004 and 2008) with county\u2011level socioeconomic indicators (ICPSR County Characteristics), broadband provider counts (FCC Form 477), and a state\u2011level right\u2011of\u2011way (ROW) regulation index (Beyer & Kende 2003). Each row represents a respondent observation linked to county and state characteristics for the survey year; variables include a constructed index of partisan affect, log\u2011transformed measures of broadband/provider and income, regional codes, and standard county demographic and economic controls. The data were assembled to enable descriptive and comparative analyses of regional policy indicators, local broadband availability, and survey\u2011measured attitudes.","file_sha256":"36b44bf602af6eec1054d3cfc3659122577e1a00422a6c5d5bfd6a18280aa1ff","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"redistributed by CausalReasoningBenchmark (MIT) under the original replication data's terms","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"36b44bf602af6eec1054d3cfc3659122577e1a00422a6c5d5bfd6a18280aa1ff","transforms":[],"url":"https://huggingface.co/datasets/syrgkanislab/CausalReasoningBenchmark/resolve/edd0fe1c1d1c5c0a4f0e3e67a50481ac679fb888/data/ds_0045/data/data.csv"},"ref_iv":{"columns":null,"description":"Every row, with region, low-education-type and year dummies","file_sha256":"36b44bf602af6eec1054d3cfc3659122577e1a00422a6c5d5bfd6a18280aa1ff","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"redistributed by CausalReasoningBenchmark (MIT) under the original replication data's terms","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"reference","sha256":"36b44bf602af6eec1054d3cfc3659122577e1a00422a6c5d5bfd6a18280aa1ff","transforms":[{"args":{"columns":["outcome","D","Total_log","percent_black","percent_white","percent_male","unemploymentrate","density","HHINC_log","region","lowed","year","state"]},"op":"select"},{"args":{"column":"region","drop_first":true,"prefix":"region"},"op":"dummies"},{"args":{"column":"lowed","drop_first":true,"prefix":"lowed"},"op":"dummies"},{"args":{"column":"year","drop_first":true,"prefix":"year"},"op":"dummies"}],"url":"https://huggingface.co/datasets/syrgkanislab/CausalReasoningBenchmark/resolve/edd0fe1c1d1c5c0a4f0e3e67a50481ac679fb888/data/ds_0045/data/data.csv"}},"difficulty":"M","id":"crb_papers.q075","level":"T2","meta":{"agent_reach":{"blocked_by":["reference_frame:ref_iv","needs_op:iv_cluster_cr0"],"dtypes":{"ds_0045":{"D":"float64","outcome":"float64"}},"named":{"outcome":["outcome"],"treatment":["D"]},"reachable":false,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":null,"unit_scale":1.0},"cluster":"ds_0045","crb":{"data_path":"data/ds_0045/data/data.csv","dataset_id":"ds_0045","gold":{"ci95":[0.004194364416815366,0.05896056542436018],"ci_rule":"effect \u00b1 1.96\u00b7|standard_error| (evaluate_result.ci_bounds)","effect":0.03157746492058777,"standard_error":0.01397096964478184},"identification":{"causal_quantity":"LATE","controls":["region","percent_black","percent_white","percent_male","lowed","unemploymentrate","density","HHINC_log"],"instrument":["Total_log"],"is_encouragement_design":false,"minimal_controlling_set":["region","percent_black","percent_white","percent_male","lowed","unemploymentrate","density","HHINC_log","year"],"outcomes":["outcome"],"reason_for_minimal_controlling_set":"\u201cWe also present results in which we add key exogenous county-level features thought to predict broadband access (e.g., racial composition, income, population density, education) to the equation to strengthen the case that the variation in broadband access due to ROW is idiosyncratic.\u201d (p. 8, Identifying the Effect of Broadband Internet on Affective Polarization)","strategy":"Instrumental Variable","treatments":["D"]},"identification_strategy":"Instrumental Variable"},"headline_keys":{"infer.iv_2sls":["coef.D"]},"naive":{"dataset":"ds_0045","treatment":"D","y":"outcome"},"native_id":"75","reference":{"cite":1,"note":"Reference path transcribed from the item's own estimation script.","steps":[{"args":{"cluster":"state","dataset":"ref_iv","endog":["D"],"exog":["percent_black","percent_white","percent_male","unemploymentrate","density","HHINC_log","region_2: Midwest","region_3: South","region_4: West","lowed_1: Low-education type","year_2008.0"],"instruments":["Total_log"],"y":"outcome"},"tool":"infer.iv_2sls","why":"IV2SLS.from_formula('outcome ~ 1 + controls + C(region) + C(lowed) + C(year) + [D ~ Total_log]').fit(cov_type='clustered', clusters=state)"}]},"reference_path":{"calls":[{"args":{"cluster":"state","dataset":"ref_iv","endog":["D"],"exog":["percent_black","percent_white","percent_male","unemploymentrate","density","HHINC_log","region_2: Midwest","region_3: South","region_4: West","lowed_1: Low-education type","year_2008.0"],"instruments":["Total_log"],"y":"outcome"},"tool":"infer.iv_2sls"}],"needs":["needs_op:iv_cluster_cr0"],"provenance":"benchmark_script","quotes":{},"reference_datasets":["ref_iv"],"source_id":"crb_papers.q075.script"}},"question":"What is the causal effect of a one-unit increase in log(number of broadband providers) on affective partisan polarization (outcome scaled 0-1), estimated for compliers using county-level data pooled across 2004 and 2008?","requires":[],"runner":null,"sources":["crb_papers.q075.gold","crb_papers.q075.script"],"split":"public","suite":"crb_papers","tags":["econ-bench","external","crb","iv","ref_benchmark_script"],"target":"agent","tool":null,"truth":"CausalReasoningBenchmark gold at the pinned revision: causal_queries.json effect and standard_error (the value the item's estimation.py prints), scored as evaluate_result.py scores estimate_within_solution_ci"}