{"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.q175","table":null,"tool":null,"value":0.322,"weight":1.0,"where":null}],"datasets":{"bowles_countering":{"columns":null,"description":"The data aims to test whether trusted WhatsApp messages can counter COVID-19 misinformation in Zimbabwe. Partnering with Internews and Kubatana, the researchers crafted short weekly messages: Week 1 emphasized transmission and social distancing, Week 2 debunked fake cures. At the WhatsApp broadcast list level, timing was randomized: treatment groups received messages on Monday, control groups on Saturday. To measure effects, a survey was sent on Thursday. Knowledge was assessed through factual questions, and behavior through a list experiment, where respondents received either a short list (only non-sensitive activities) or a long list (the same activities plus a sensitive one: visiting others during lockdown). Broadcast lists were blocked in groups of four, with random assignment across timing (treatment vs. control) and list length (short vs. long).\n\nData variables\nResponseId: identifier for the responses from the individuals\nBehavior: number of activities the respondent participated in, coded from 0 to 5\nId: identifier for individuals participating\nList: binary variable, equals 1 if the WhatsApp broadcast list is assigned to the long experimental list\nqualtrics: binary variable indicating response mode (1 if Qualtrics, 0 if WhatsApp)\nT: treatment indicator, equals 1 if the WhatsApp broadcast list is assigned to the treatment group\nfemale: binary variable, equals 1 if the respondent is female\nc_Q4: survey question on factual knowledge about COVID-19 transmission or prevention\nc_Q5: survey question on factual knowledge about misinformation or fake cures\nKnowledge: z-score of the respondent's answers to the factual questions\nc_Q4_1: sub-item of Q4 (first option, coded 1 if correct, 0 otherwise)\nc_Q4_3: sub-item of Q4 (third option, coded 1 if correct, 0 otherwise)\nc_Q4_4: sub-item of Q4 (fourth option, coded 1 if correct, 0 otherwise)\nc_Q4_5: sub-item of Q4 (fifth option, coded 1 if correct, 0 otherwise)\nblock: randomization block (grouping of broadcast lists created at similar times)\nlength_subscribe: number of months the WhatsApp broadcast list had been active\nWeek: indicator for intervention week (1 = distancing message, 2 = misinformation/cures message)\nresponse_rate: fraction of weekly responses coming from WhatsApp per person\nWeek_id: numeric identifier for the week\nurban: binary variable, equals 1 if the individual lived in an urban district","file_sha256":"3107fc57c0d67588eccecf4788cf3600ab114f22fa27694bebd9c1892a8e5049","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/MDF4SO","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"3107fc57c0d67588eccecf4788cf3600ab114f22fa27694bebd9c1892a8e5049","transforms":[],"url":"https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/bowles_countering.csv"}},"difficulty":"M","id":"causcibench_real.q175","level":"T2","meta":{"agent_reach":{"blocked_by":["no_reference_path","needs_spec:control:TxList"],"dtypes":{"bowles_countering":{"Behavior":"float64","T":"int64"}},"named":{"outcome":["Behavior"],"treatment":["T"]},"reachable":false,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":null,"unit_scale":1.0},"cluster":"paper:Countering misinformation via whatsapp: Preliminary evidence from the covid-19 pandemic in Zimbabwe","gold":{"effect":0.322,"effect_as_stored":"0.322","is_significant":1,"source_id":"causcibench_real.gold.q175","std_error":0.079,"std_error_as_stored":"0.079"},"metadata":{"control_variables":"qualtrics,female,urban,Week,block,List,TxList","dataset_path":"data/csv_files/realdata/bowles_countering.csv","effect":0.322,"id":175,"instrument_var":null,"interaction_var":null,"is_rct":true,"is_significant":1,"method":"ols","name":"Countering misinformation via whatsapp: Preliminary evidence from the covid-19 pandemic in Zimbabwe","outcome_var":"Behavior","running_var":null,"state_var":null,"std_error":0.079,"temporal_var":null,"treatment_var":"T"},"naive":{"dataset":"bowles_countering","treatment":"T","y":"Behavior"},"name":"Countering misinformation via whatsapp: Preliminary evidence from the covid-19 pandemic in Zimbabwe","native_id":175,"outcome":"Behavior","pin":{"data_repo":"causal-nlp/causcibench","data_revision":"d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a","repo":"causalNLP/CauSciBench","revision":"d9bb43a2d90f261978cc5ac0b628c0484f6e8956"},"precision_limited":false,"reference_notes":["the control 'TxList' is not a column of the CSV"],"reference_path":{"calls":[],"needs":["needs_spec:control:TxList"],"provenance":"none","quotes":{"control:TxList":"control_variables: qualtrics,female,urban,Week,block,List,TxList"},"reference_datasets":[],"source_id":null},"reference_rule":"causcibench_metadata_rule/1","source":"causcibench","treatment":"T"},"question":"Does providing credible information improve compliance with Covid guidelines?","requires":[],"runner":null,"sources":["causcibench_real.gold.q175"],"split":"public","suite":"causcibench_real","tags":["econ-bench","external","causcibench","method:ols"],"target":"agent","tool":null,"truth":"CauSciBench real_input.json @ d9bb43a, id 175: effect 0.322"}