{"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.q097","table":null,"tool":null,"value":0.265,"weight":1.0,"where":null}],"datasets":{"wilson_internet":{"columns":null,"description":"The data comes from a randomized control trial conducted to assess the impact of Internet-accessed sexually transmitted infection testing (e-STI testing) through the sh24 platform. Sexually active individuals between the ages of 16 and 30 were recruited. The participants were then randomly sent text messages inviting them to participate in the testing. The treatment group was asked to order the test online while the control group was asked to visit a walk-in clinic and take the test. The main outcome of interest was the self-reported diagnosis of STIs, supported by medical reports.\n\nVariables include:\nanon_id: Participant id\ngroup: Allocation group ('Control' denotes control group and 'SH_24' denotes treatment group)\nimd_decile: Index of Multiple Deprivation decile rankings on scale of 1-10; 1 represents the most deprived and 10 represents the least deprived\npartners: Number of sexual partners in past 12 months at baseline\ngender: Gender (Male or Female)\nmsm: Men who have sex with men ('msm'=Yes; 'other'=No; 99=Not Known)\nethnicgrp: Ethnic group\nage: Age in completed years at baseline\nanytest_sr: Binary variable indicating whether the participant self-reported the completion of the STI test or not (1=tested, 0=not tested)\nanydiag_sr: Binary variable indicating whether the participant self-reported the diagnosis of STI test or not (1=diagnosed, 0=not diagnosed)\nanytreat_sr: Binary variable indicating whether the participant self-reported receiving STI treatment or not (1=treated, 0=not treated)\nanytest: Objectively verified binary indicator of STI testing completion (1 = tested, 0 = not tested)\nanydiag: Objectively verified binary indicator of STI diagnosis (1 = diagnosed, 0 = not diagnosed)\nanytreat: Objectively verified binary indicator of STI treatment (1 = treated, 0 = not treated)\ntime_test: Time from randomization to test in days\ntime_treat: Time from randomization to treatment in days\nsh24_launch: Binary variable indicating whether the randomization occurred before or after SH:24 was made publicly available (1 = yes, 0 = no)","file_sha256":"99071e6ae11d90f18960a444f53f0cdd4eb82342c0484b7d6a63263a243b0d10","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"CC BY 4.0 (CauSciBench data/README.md); original source https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1002479","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"99071e6ae11d90f18960a444f53f0cdd4eb82342c0484b7d6a63263a243b0d10","transforms":[],"url":"https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/wilson_internet.csv"}},"difficulty":"M","id":"causcibench_real.q097","level":"T2","meta":{"agent_reach":{"blocked_by":["no_reference_path","needs_spec:treatment","missing_column:wilson_internet.tx"],"dtypes":{"wilson_internet":{"anytest":"float64","tx":null}},"named":{"outcome":["anytest"],"treatment":["tx"]},"reachable":false,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":null,"unit_scale":1.0},"cluster":"paper:Internet-accessed sexually transmitted infection (e-sti) testing and results service: A randomised, single-blind, controlled trial","gold":{"effect":0.265,"effect_as_stored":"0.265","is_significant":1,"source_id":"causcibench_real.gold.q097","std_error":0.022,"std_error_as_stored":"0.022"},"metadata":{"control_variables":null,"dataset_path":"data/csv_files/realdata/wilson_internet.csv","effect":0.265,"id":97,"instrument_var":null,"interaction_var":null,"is_rct":true,"is_significant":1,"method":"ols","name":"Internet-accessed sexually transmitted infection (e-sti) testing and results service: A randomised, single-blind, controlled trial","outcome_var":"anytest","running_var":null,"state_var":null,"std_error":0.022,"temporal_var":null,"treatment_var":"tx"},"naive":null,"name":"Internet-accessed sexually transmitted infection (e-sti) testing and results service: A randomised, single-blind, controlled trial","native_id":97,"outcome":"anytest","pin":{"data_repo":"causal-nlp/causcibench","data_revision":"d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a","repo":"causalNLP/CauSciBench","revision":"d9bb43a2d90f261978cc5ac0b628c0484f6e8956"},"precision_limited":false,"reference_notes":["the treatment 'tx' is not a column of the CSV"],"reference_path":{"calls":[],"needs":["needs_spec:treatment"],"provenance":"none","quotes":{"treatment":"treatment_var: tx"},"reference_datasets":[],"source_id":null},"reference_rule":"causcibench_metadata_rule/1","source":"causcibench","treatment":"tx"},"question":"What is the effect of the e-STI testing service on the probability of getting tested for an STI by 6 weeks?","requires":[],"runner":null,"sources":["causcibench_real.gold.q097"],"split":"public","suite":"causcibench_real","tags":["econ-bench","external","causcibench","method:ols"],"target":"agent","tool":null,"truth":"CauSciBench real_input.json @ d9bb43a, id 97: effect 0.265"}