{"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 in the answer was 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":false,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"CauSciBench effect accuracy: |answer figure \u2212 gold| \u2264 5% of |gold|","open_interval":false,"rel_tol":0.05,"required":true,"source_id":"causcibench_real.gold.q001","table":null,"tool":null,"value":0.025,"weight":1.0,"where":null}],"datasets":{"gerber_social_pressure":{"columns":null,"description":"The randomized experiment aims to analyze the effect of different types of social pressures on voter behavior. A field experiment was conducted in Michigan ahead of the August 2006 primary election. Households were randomly assigned to a control group or one of four treatment groups: Civic Duty, Hawthorne, Self, Neighbors. Eleven days before the election, each treatment group received a different mailing: Civic Duty: Emphasized the recipient's responsibility as a citizen to vote. Hawthorne: Notified recipients that their voting behavior would be studied using public records, introducing mild social pressure. Self: Listed the voting history of all registered voters in the household and noted that an updated chart would be mailed after the election. Neighbors: Included both the household's and neighbors' voting records, implying public exposure of voting behavior. Control Group: Received no mailing.\nVariables in the Dataset:\nsex: Participant's sex (male or female)\ng2000, g2002, g2004: Voted in the 2000, 2002, and 2004 gubernatorial elections\np2000, p2002, p2004: Voted in the 2000, 2002, and 2004 primary elections\ntreatment: Assigned group (Civic Duty, Hawthorne, Neighbors, Self, or Control)\ncluster: Cluster identifier for the unit\nvoted: Indicator for voting in the 2006 primary election\nhh_id: Household ID\nhh_size: Number of individuals in the household\nyob: Year of birth of the participant","file_sha256":"bac3dfd61a4d09fd0e2256db8bac088ae6054b9e05990609b86665dceec9b6e8","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/CGMWNW","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"bac3dfd61a4d09fd0e2256db8bac088ae6054b9e05990609b86665dceec9b6e8","transforms":[],"url":"https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/gerber_social_pressure.csv"}},"difficulty":"M","id":"causcibench_real.q001","level":"T2","meta":{"agent_reach":{"blocked_by":["no_reference_path","needs_spec:treatment_arm","not_numeric:gerber_social_pressure.treatment:str"],"dtypes":{"gerber_social_pressure":{"treatment":"str","voted":"int64"}},"named":{"outcome":["voted"],"treatment":["treatment"]},"reachable":false,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":null,"unit_scale":1.0},"cluster":"paper:Social pressure and voter turnout: Evidence from a large-scale field experiment","gold":{"effect":0.025,"effect_as_stored":"0.025","is_significant":1,"source_id":"causcibench_real.gold.q001","std_error":0.003,"std_error_as_stored":"0.003"},"item_caveats":[{"kind":"multirct_treatment","note":"a multi-RCT item: CauSciBench scores its treatment against a constructed multirct_treatment name the pinned CSV lacks; the port scores it against 'treatment' by substring, so any predicted name containing 'treatment' matches"}],"metadata":{"control_variables":"g2000,g2002,p2000,p2002,p2004","dataset_path":"data/csv_files/realdata/gerber_social_pressure.csv","effect":0.025,"id":1,"instrument_var":null,"interaction_var":null,"is_rct":true,"is_significant":1,"method":"ols","name":"Social pressure and voter turnout: Evidence from a large-scale field experiment","outcome_var":"voted","running_var":null,"state_var":null,"std_error":0.003,"temporal_var":null,"treatment_var":"treatment"},"naive":null,"name":"Social pressure and voter turnout: Evidence from a large-scale field experiment","native_id":1,"outcome":"voted","pin":{"data_repo":"causal-nlp/causcibench","data_revision":"d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a","repo":"causalNLP/CauSciBench","revision":"d9bb43a2d90f261978cc5ac0b628c0484f6e8956"},"precision_limited":false,"reference_notes":["the treatment 'treatment' is a categorical column; which arm against which is named only in the query"],"reference_path":{"calls":[],"needs":["needs_spec:treatment_arm"],"provenance":"none","quotes":{"treatment_arm":"treatment_var: treatment"},"reference_datasets":[],"source_id":null},"reference_rule":"causcibench_metadata_rule/1","source":"causcibench","treatment":"treatment"},"question":"Does the Hawthorne scheme lead to an increase in voter turnout?","requires":[],"runner":null,"sources":["causcibench_real.gold.q001"],"split":"public","suite":"causcibench_real","tags":["econ-bench","external","causcibench","method:ols"],"target":"agent","tool":null,"truth":"CauSciBench real_input.json @ d9bb43a, id 1: effect 0.025"}