# MAGI benchmark run 20261015T171142Z-suite-causcibench_real-naive-d6494d

Status: `success`.

## Overview

A run of the plan `suite-causcibench_real` at commit `2925aeab226272b243436386a1c4e01d97c1377e` (tree clean: yes) with the agent `naive` (`naive-ols`):
153 task(s) of `causcibench_real` 0.1.2, 153 result line(s) (one per task, epoch and attempt). The per-suite
numbers are in `summary.json`, rendered as `summary.md`; each is defined by the code of `verify_bundle.py`,
which recomputes them from `results.jsonl`.

Anyone can run verify_bundle.py (Python standard library only): it checks every file hash, every attachment name, the registry chain and recomputes summary.json from results.jsonl. Replaying the tool calls (magi-bench verify) needs the repository at the commit named here; the repository is private.

## Data availability and provenance statements

No third-party data file is redistributed. Each dataset is fetched from its publisher at a pinned URL and
verified by the sha256 of its bytes, or regenerated from a seeded generator (`manifest.json` → `data`):

| dataset | kind | URL | sha256 of the file | licence |
|---|---|---|---|---|
| abadie_instrumental_variables | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/abadie_instrumental_variables.csv | `07f3f196b42e8b021c7ed300807753a0c7ee104d9466807fc298890879e73c38` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/file.xhtml?persistentId=doi:10.7910/DVN/XVADZ7/OYIAFS |
| abouchadi_causal_effect | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/abouchadi_causal_effect.csv | `d1326fd1180f16563bc4c0b2168ed9c9342616cc1e3baae3f152ad8d95b1097b` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/23624 |
| angrist_using_maimonides | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/angrist_using_maimonides.csv | `dc453570d77ed9822a3ba40616fc1e604dd805b036e71954a3a0bf894ca2f8b3` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/XRSUJU |
| angrist_vouchers | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/angrist_vouchers.csv | `40d8713a6c7abe4501d9e215e3af62cada0199b2782dd0d6fbabbee355d8535a` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/K57TOZ |
| autor_china_syndrome | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/autor_china_syndrome.csv | `603a026947701601a2216badd278060457f392a999eebf58ecbd09d41cb6b155` | CC BY 4.0 (CauSciBench data/README.md); original source https://www.openicpsr.org/openicpsr/project/112670/version/V1/view |
| barton_understanding | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/barton_understanding.csv | `b00ac4dada42bb315ba65081390d8eee2ec78b26113143b8fcc04ad895926af2` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/KULZYU |
| bokemper_experimental_evidence | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/bokemper_experimental_evidence.csv | `e94fe873cb4358fa045bc38ef25d976d69a12ed882c571b03327e0a5b7be7723` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/NZYWS5 |
| bowles_countering | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/bowles_countering.csv | `3107fc57c0d67588eccecf4788cf3600ab114f22fa27694bebd9c1892a8e5049` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/MDF4SO |
| brogaard_interpreting_performance1 | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/brogaard_interpreting_performance1.csv | `ec6ab45354ecb1bd53e4103fce3239d8d6b29f07243f0b5864cf6f83f10b3f83` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JLHLJG |
| brogaard_interpreting_performance2 | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/brogaard_interpreting_performance2.csv | `2934bd784f8c063e1818c11f66546004667e52a18203b5e601cfaea59e38ab88` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JLHLJG |
| broockman_black_politicians | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/broockman_black_politicians.csv | `414450c964cacbde724fd24906b61bb65232c0ae9c73a1bc021dbce1ea058022` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| broockman_black_politicians | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/broockman_black_politicians.csv | `414450c964cacbde724fd24906b61bb65232c0ae9c73a1bc021dbce1ea058022` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| broockman_do_congressional | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/broockman_do_congressional.csv | `22f2346a65c81d4a6c59f57d128b6aef85f798e9bc007bf69545c38ae9d5ae11` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/IOEQKE |
| broockman_do_female | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/broockman_do_female.csv | `79817fe2c223e23f2266493fa1deb84301c0cfa51da6444ae4ba7b40465cb2a8` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/23624 |
| butler_do_politicians | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/butler_do_politicians.csv | `da070187b161931eb60102008c9fe7907e4660438519fa9b9656a45d317d70df` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/VAHSO4 |
| cai_effect_microinsurance | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/cai_effect_microinsurance.csv | `e3249019db8a6d5cd72c88756b60b22681a35b469f71e420f6e49bfa747360da` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/27174 |
| calonico_regression | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/calonico_regression.csv | `32fd83152c3fa34ed8331f184098ff9e8b85dc7e99f59a0ecf027d4573e0d86f` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/LPZLBF |
| card_minimum_wages | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/card_minimum_wages.csv | `d60fdf3cbe6dc79b86bff0c6499806848793e9b6a642643cd9d5fbb390a80732` | No License Specified (CauSciBench data/README.md); original source https://davidcard.berkeley.edu/data_sets.html |
| card_using_geographic | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/card_using_geographic.csv | `dcfffbe5294890880a8ed65da6cbca819980978b844109f455b82a24df671da7` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| carpenter_the_minimum_legal | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/carpenter_the_minimum_legal.csv | `e49a7ad686067a4e4e119b7ab85a0dc1a8e562b1b5fc83d3f4e1d9b4b626d6e4` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/Q9VQIU |
| carpenter_the_minimum_legal_drinking | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/carpenter_the_minimum_legal_drinking.csv | `3083a3b3ad5ad5d822488e13fe0b49c98bcca2c9ab621e4fdec0abab049efd59` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/27070 |
| cheng_does_strengthening | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/cheng_does_strengthening.csv | `b84b3549a35f5322b7d6adaa8030c435fdcd26bbb63eea02e24883c1dc6f7fed` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| chi_improving | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/chi_improving.csv | `1acbd68c21bd7148a6cf25c9e94fba3aa8f78556f000e983b66449e83208e297` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/TBBV8R |
| cirone_cabinets | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/cirone_cabinets.csv | `667bb93d31b83716ba58ff8d36588e0dd813470a04931c6359a8ee1b00d3d4f0` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/F1VLBI |
| conley_inference_with_hope | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/conley_inference_with_hope.csv | `8c646a88e3c045b7ba1c179b5012dedcc34f8e64d901159ce4f2eca89e77f330` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/GCBK24 |
| conley_inference_with_merit | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/conley_inference_with_merit.csv | `ab17c09dc39124fed9d72a4c0801c5b7179696c2f1b894d8052ce8326f759ef1` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/GCBK24 |
| cunningham_the_long_run | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/cunningham_the_long_run.csv | `358683c6249459cb0e9bc1c562964a1ac7706ccc7e3da32cf795c42e6f48a5d6` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| dehejia_propensity_score | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/dehejia_propensity_score.csv | `301ac38a23accac1694b5be91c3967dc22fc38c70c3a82ab4d67786194a816eb` | CC BY-NC 2.0 (CauSciBench data/README.md); original source https://users.nber.org/~rdehejia/data/.nswdata2.html |
| deuchert_direct | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/deuchert_direct.csv | `67fe68b0268edd264164261c1503c0ed32651add2e52cdd3e332c791d4aff2f8` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/I57L3O |
| dhingra_immigration_policies | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/dhingra_immigration_policies.csv | `ae44e688368556ce9e91e3f64677586ff7b6e930c1b82680239c2a9419edc7e8` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/RGZWNJ |
| dorussen_the_influence | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/dorussen_the_influence.csv | `08184bd4fe64bbecf97d1896551a9f9adcb9b55fc6999acbcf130e7653e69ec9` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/AQYYNK |
| dwiputri_the_corruption | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/dwiputri_the_corruption.csv | `10cc9110630a581a2fe10095f748e14a6787c416f3b7367d9870c06ff4a18973` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/8VF8RV |
| eckhouse_metrics_management | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/eckhouse_metrics_management.csv | `b303608e3fc216acfb6520b968a7a6de354eb1248fdd53ac70671f7eb04f1298` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/3E7JXB |
| enache_demand_for | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/enache_demand_for.csv | `d1385394b66f1abe6a205119f2b6c743d2af84dc7ccfe92a5207249d8d3454e4` | CC BY 4.0 (CauSciBench data/README.md); original source https://www.openicpsr.org/openicpsr/project/186201/version/V1/view |
| foos_all_in | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/foos_all_in.csv | `67e792b6f8707c142cdb7821eb133a831d25071f89a6963e837b78699aba4f5e` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/ZFLG25 |
| garcia_colored_perceptions | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/garcia_colored_perceptions.csv | `c9d403a8c02120d4b354d4b751a93273ecdfa2b55563238a0fa253796951e0e5` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/QTTA73 |
| garcia_colored_perceptions_ref | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/garcia_colored_perceptions.csv | `c9d403a8c02120d4b354d4b751a93273ecdfa2b55563238a0fa253796951e0e5` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/QTTA73 |
| gerber_social_pressure | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/gerber_social_pressure.csv | `bac3dfd61a4d09fd0e2256db8bac088ae6054b9e05990609b86665dceec9b6e8` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/CGMWNW |
| goldsmith_doing_well | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/goldsmith_doing_well.csv | `e45a2c15808d35983e45405dd1eb70737617764feccf2852c6c51ba329b094dc` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/IHMFPJ |
| goldstein_lobbyists_earmark | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/goldstein_lobbyists_earmark.csv | `1a9ddd6771f128adf44d7e0cf60fda2c56a420820a8b850bdf09450828424bf1` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JTSYV3 |
| goldstein_lobbyists_recovery | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/goldstein_lobbyists_recovery.csv | `ff62bb2c5a61db60bd55bdf9e04a082efc8d6aaad12733bf319b3fe3937767b4` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/RSD5BV |
| gonzalez_blame_shifting | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/gonzalez_blame_shifting.csv | `608c8167bc620dbb0e614d2a37512458559440537c20ad401d25603915e7727b` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/QNCYOQ |
| graddy_markets_fulton | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/graddy_markets_fulton.csv | `8483868338caa50ffd745475890ce33fd2c24bee6980c5b01f67827008ce6e04` | MIT License (CauSciBench data/README.md); original source https://github.com/scunning1975/mixtape |
| hansen_punishment | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/hansen_punishment.csv | `16b9aa8145387ae7818091846e56c7754b095fbcfc2e008a045a47bad7054e2c` | MIT License (CauSciBench data/README.md); original source https://github.com/scunning1975/mixtape |
| hartford_deepiv | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/hartford_deepiv.csv | `0aabfb5579727e6c1094a3e837924248194f9fbf32e9ed8a7db093a4f0dd632d` | MIT License (CauSciBench data/README.md); original source https://github.com/jhartford/DeepIV |
| hawes_give_us | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/hawes_give_us.csv | `dbd2ec92e684d3b5374d5971bcf3835571d7e0863fa970c92e235f7e1d411de5` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/L1V6BP |
| hawes_social_capital | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/hawes_social_capital.csv | `04fb48ac5f0d0709687b5a5013477e80ce7f00179a65d689ae7b633787a4fc33` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/B8NR76 |
| keele_do_term_limits | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/keele_do_term_limits.csv | `57dfc507d57b56b5790e4f71220a32a302ae01cc57be41652fbd60ce19e8ba99` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/23123 |
| kessler_dont_take | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/kessler_dont_take.csv | `b4b97dcdeaa6057f22f03248dc3a6e2251efe47be307d0807fa85ddc1c775c13` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| krasno_do_televised | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/krasno_do_televised.csv | `557f9bcc8be77116fb5f38df0e569469eadc7072aecd833022441be593288801` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/QJKB0I |
| lalonde_evaluating | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lalonde_evaluating.csv | `488cd9ba9eada1033c158df8fff9d86b57cab90710c3725a8e0db33da25ef3dc` | CC BY-NC 2.0 (CauSciBench data/README.md); original source https://users.nber.org/~rdehejia/data/.nswdata2.html |
| lalonde_evaluating_ref | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lalonde_evaluating.csv | `488cd9ba9eada1033c158df8fff9d86b57cab90710c3725a8e0db33da25ef3dc` | CC BY-NC 2.0 (CauSciBench data/README.md); original source https://users.nber.org/~rdehejia/data/.nswdata2.html |
| lee_do_voters | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lee_do_voters.csv | `93bbbf2757b5a306889b643aaee68f5e1ce9b42f12b64ff95b9aceb040ea8d5a` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| lee_impact | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lee_impact.csv | `1745419e067c9258af66c2ec5de4fd0428b8db184554eda40436ed9c96dc3eac` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/XZJZAN |
| lee_impact_ref | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lee_impact.csv | `1745419e067c9258af66c2ec5de4fd0428b8db184554eda40436ed9c96dc3eac` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/XZJZAN |
| lee_randomized_experiments | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/lee_randomized_experiments.csv | `ceb5dd7ef24d21d461cb986e95dde201c67e773f2c40e26b8a7e6278b9036813` | GPL 3.0 (CauSciBench data/README.md); original source https://search.r-project.org/CRAN/refmans/RATest/html/lee2008.html |
| leigh_estimating_the_impact | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/leigh_estimating_the_impact.csv | `29dc7a900c78bf24b67811856cb3d85d5759a0288211332d090607e89b6e451d` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JPDQ5P |
| liu_public_trust1 | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/liu_public_trust1.csv | `cf9e09515de1eefd2f8632f50f8bba346bb07de38a86d54334beae321106e59f` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/ATDFQN |
| liu_public_trust2 | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/liu_public_trust2.csv | `fc860c838198dcffd59dcd954f0a1f1743f18b6fdb1a88ee81b4490493d3c3cf` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/ATDFQN |
| malesky_foreign | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/malesky_foreign.csv | `514f7e8d581e7cc774641215ce1cff267e111982a781740ef6d880a1b312774d` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/PDVSW5 |
| malesky_impact_of_recentralization | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/malesky_impact_of_recentralization.csv | `5565ce8bca2be787ed656ffbcfe7e687c2cb261d782415ed56204fca110eff25` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/IUG2C4 |
| manacorda_gov_transfers | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/manacorda_gov_transfers.csv | `a25fd9493a2f57e990d7769905fe56374bc6ddad9534e88c8d01085812fb0334` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| newman_global_costs | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/newman_global_costs.csv | `b5566c38a3ac6ecba6cc014aea2af8aaa376b6fed658c546a704080cb4a8240d` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/N3ED1N |
| oswald_computational | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/oswald_computational.csv | `62eba7a6255f94d594b8652e718bf7feae28b5228729ce0205ee7351eed9b52e` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/G37BHE |
| panagopolous_field_experiments | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/panagopolous_field_experiments.csv | `4752df417db23bf5ef74fdf35be37e544f94fd7b8c6eb3769e309feea61b4e65` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/NTMEZU |
| panagopoulos_timing | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/panagopoulos_timing.csv | `37ac4466ad26ac40012073e833298d7e3f2f8e8fbe8eb1fa90268ec2e1181ad7` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.yale.edu/dataset.xhtml?persistentId=doi:10.60600/YU/STKD55 |
| pereira_does_electing | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/pereira_does_electing.csv | `74a6871902721ee1f5f27d22d7a7559e8a772595879125b3ee473ce231dc7887` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/NSALSE |
| rebeira_does_rising | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/rebeira_does_rising.csv | `a45e6b911277627d6b75a1c955aef5765405b77452b959c26188af44c238bd91` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/E3X2NO |
| reinsberg_does_earmarked | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/reinsberg_does_earmarked.csv | `c6e6f76a45840b38e6b9ab7ca8618731926c8df7c3c57d54ce2a34d8d362f330` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/23624 |
| rickard_incumbents | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/rickard_incumbents.csv | `0746afc96c5d923f64d1274eef4643ebc91c4f02dfd9a91d4782fa220e709f22` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/X1JL2H |
| ruth_partisan_conflict | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/ruth_partisan_conflict.csv | `97f2e2f94f0bea8dd79810f7624094eb1ae26f0442154f22e5db878a16abfa2b` | CC BY 4.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/UM4VAJ |
| sabia_are_minimum | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/sabia_are_minimum.csv | `0d9a4af36a05239b8ea0d51a0377cea6749a51873e6544b689c4b84f41c0bc53` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/6AYLVO |
| sharkey_community | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/sharkey_community.csv | `a9f721b6ac4dc365e59b6317eec13c501a81614bbc3fe13448a09f19a9a5a1b5` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/46WIH0 |
| snyder_partisan_imbalance | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/snyder_partisan_imbalance.csv | `99e59a95d25976b16c17acb02da90f6473f2fee0dd67abf9ffe30180d3ea76de` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/23624 |
| song_estimating_incumbency | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/song_estimating_incumbency.csv | `f9455065815897f357981f2f97871fe8b7137acf6ef1b2772241d4bf05de9b10` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JSOWUR |
| soules_call_to | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/soules_call_to.csv | `98f408c51ef5d93f296879abc4a896f99ff204c566c714c7a77a9359218f78af` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/6BZSKR |
| taddeo_causal | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/taddeo_causal.csv | `993a5c5eb299039f6a093885c9befad4b9084a6f4aebe615c5b7a64b7057fe29` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/ENG0IY |
| tan_causal_effect | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/tan_causal_effect.csv | `ec5125a0cd4b71a89f79610bc4761f043c3af0ba9ee7f963898acfb357c61c9f` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/KCSVWH |
| thomas_effects_of | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/thomas_effects_of.csv | `4f4de9dbacecbfc6a5234e9fd8e9000d07aae7490af851fc4a6037813cb4e89a` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/CIPVBK |
| thompson_how_partisan | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/thompson_how_partisan.csv | `219663aca0ff32ad5332456ddeda6a08da8f5cf849f07b1041ea7b63465abd99` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/CFASH6 |
| thornton_the_demand | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/thornton_the_demand.csv | `2bdbdab798a2f6566ff2fa4d7bbb107f6b2a6c04b3056eb619f01bc77d0466d4` | MIT License (CauSciBench data/README.md); original source https://cran.r-project.org/web/packages/causaldata/index.html |
| uji_comparing_public | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/uji_comparing_public.csv | `0e30ede65f1813f395da3b4d7651a61c9175218a40234d89387f16625a25b596` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/HM1KXT |
| urdinez_china | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/urdinez_china.csv | `f74c78cc3d6c50207291c4826731647739aeb407a77c31665ce9255c74deb420` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/EIAXSE |
| urdinez_undermining | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/urdinez_undermining.csv | `0d804a4b724492f48aeb435e50c458467d1633762f28d7877e8d78bf85daf286` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/KNG7CY |
| venkatramani_early_medicaid | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/venkatramani_early_medicaid.csv | `dee9b05cee4a75414abe6d4bad0127a61bc4480035d05324d4d3fb3cdcbb1039` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/9ZS4KR |
| vernby_can_immigrants | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/vernby_can_immigrants.csv | `6b86133cb042567bcf438fed9ac968ded163b85e3608000503564ddb195541c6` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/HVRL0S |
| white_evaluating_the_minority | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/white_evaluating_the_minority.csv | `acae1a36b9f4d0e127a3407e5312a7c6bc9790faefc40c09c9dc42bfecb6420e` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/U5PDBR |
| wilson_internet | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/wilson_internet.csv | `99071e6ae11d90f18960a444f53f0cdd4eb82342c0484b7d6a63263a243b0d10` | CC BY 4.0 (CauSciBench data/README.md); original source https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1002479 |
| xiong_effect_of | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/xiong_effect_of.csv | `9f3ae5d6ca9461cc595be7c9b567c126215c2388ed7e73a9777f3016a813261f` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/HHSREH |
| xu_does_mislabelling | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/xu_does_mislabelling.csv | `7432cf2fb45b00f547e433f243fdbd8ecadf01b8141adbba4130824522108855` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/CDUROD |
| zoorob_does_right | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/zoorob_does_right.csv | `084e55af44aa47af396b25c1a5f50154f0296498873f751c2da4782c2a2f3b18` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/UVCZ5D |
| zoorob_privatization | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/zoorob_privatization.csv | `a19815d97b84a2939eb7755f92d0d7ce86211e6e322345eebf312c5bd2204a70` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/91S9AP |
| zoorob_privatization_va | file | https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/zoorob_privatization_va.csv | `fd97c37ee8a2eb7a1c11bea45945d6f8fbfb8faea581af2ad0e100d4ba708492` | CC0 1.0 (CauSciBench data/README.md); original source https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/91S9AP |

Published values quoted for verification are in `sources/`, each with its locator and an excerpt of at most
15 words; a benchmark's own gold is quoted from its pinned release with its licence.

## Computational requirements

`env/platform.json` lists the Python version, the operating system and architecture, the BLAS, `uv
--version`, the sha256 of `uv.lock` and every installed package as name==version. Tool replay
(`magi-bench verify`) needs the repository at the commit above and `uv sync --frozen --all-packages`.

## Description of the files

- `manifest.json`: what was run, by which code, agent and model, with which environment, at what cost.
- `results.jsonl`: one task result per task, epoch and attempt, sorted.
- `specs/`: each task exactly as it ran (canonical JSON; its sha256 is the result's `task_sha256`).
- `traces/`: the raw records of every call (the source of truth); `trajectories/`: the event view derived
  from them.
- `attachments/`: prompts, tool declarations, vendor contents and raw responses, each named by the sha256
  of its canonical bytes.
- `sources/`, `native/`, `tools/registry.json`, `env/platform.json`.
- `SHA256SUMS`: the sha256 of every other file; its own sha256 is the run digest.

Canonical JSON: keys sorted, no whitespace, ASCII, floats as Python's `repr`, non-finite numbers as the
strings `"NaN"`, `"Infinity"` and `"-Infinity"`.

## Instructions to replicators

1. Integrity, without the repository: `python3 verify_bundle.py` (standard library only).
2. With the repository at the commit: `uv sync --frozen --all-packages`, then
   `uv run magi-bench verify <this folder>` replays the tool calls and rescores every task.

## List of tasks

- `causcibench_real.q001` (T2, agent, split public)
- `causcibench_real.q002` (T2, agent, split public)
- `causcibench_real.q003` (T2, agent, split public)
- `causcibench_real.q004` (T2, agent, split public)
- `causcibench_real.q005` (T2, agent, split public)
- `causcibench_real.q007` (T2, agent, split public)
- `causcibench_real.q008` (T2, agent, split public)
- `causcibench_real.q009` (T2, agent, split public)
- `causcibench_real.q010` (T2, agent, split public)
- `causcibench_real.q011` (T2, agent, split public)
- `causcibench_real.q012` (T2, agent, split public)
- `causcibench_real.q013` (T2, agent, split public)
- `causcibench_real.q014` (T2, agent, split public)
- `causcibench_real.q015` (T2, agent, split public)
- `causcibench_real.q016` (T2, agent, split public)
- `causcibench_real.q017` (T2, agent, split public)
- `causcibench_real.q018` (T2, agent, split public)
- `causcibench_real.q019` (T2, agent, split public)
- `causcibench_real.q020` (T2, agent, split public)
- `causcibench_real.q021` (T2, agent, split public)
- `causcibench_real.q022` (T2, agent, split public)
- `causcibench_real.q023` (T2, agent, split public)
- `causcibench_real.q024` (T2, agent, split public)
- `causcibench_real.q025` (T2, agent, split public)
- `causcibench_real.q026` (T2, agent, split public)
- `causcibench_real.q027` (T2, agent, split public)
- `causcibench_real.q028` (T2, agent, split public)
- `causcibench_real.q030` (T2, agent, split public)
- `causcibench_real.q031` (T2, agent, split public)
- `causcibench_real.q032` (T2, agent, split public)
- `causcibench_real.q033` (T2, agent, split public)
- `causcibench_real.q034` (T2, agent, split public)
- `causcibench_real.q035` (T2, agent, split public)
- `causcibench_real.q036` (T2, agent, split public)
- `causcibench_real.q037` (T2, agent, split public)
- `causcibench_real.q038` (T2, agent, split public)
- `causcibench_real.q039` (T2, agent, split public)
- `causcibench_real.q040` (T2, agent, split public)
- `causcibench_real.q042` (T2, agent, split public)
- `causcibench_real.q043` (T2, agent, split public)
- `causcibench_real.q044` (T2, agent, split public)
- `causcibench_real.q046` (T2, agent, split public)
- `causcibench_real.q047` (T2, agent, split public)
- `causcibench_real.q048` (T2, agent, split public)
- `causcibench_real.q049` (T2, agent, split public)
- `causcibench_real.q050` (T2, agent, split public)
- `causcibench_real.q052` (T2, agent, split public)
- `causcibench_real.q053` (T2, agent, split public)
- `causcibench_real.q054` (T2, agent, split public)
- `causcibench_real.q055` (T2, agent, split public)
- `causcibench_real.q056` (T2, agent, split public)
- `causcibench_real.q057` (T2, agent, split public)
- `causcibench_real.q058` (T2, agent, split public)
- `causcibench_real.q069` (T2, agent, split public)
- `causcibench_real.q071` (T2, agent, split public)
- `causcibench_real.q072` (T2, agent, split public)
- `causcibench_real.q073` (T2, agent, split public)
- `causcibench_real.q074` (T2, agent, split public)
- `causcibench_real.q075` (T2, agent, split public)
- `causcibench_real.q076` (T2, agent, split public)
- `causcibench_real.q077` (T2, agent, split public)
- `causcibench_real.q078` (T2, agent, split public)
- `causcibench_real.q079` (T2, agent, split public)
- `causcibench_real.q080` (T2, agent, split public)
- `causcibench_real.q081` (T2, agent, split public)
- `causcibench_real.q082` (T2, agent, split public)
- `causcibench_real.q083` (T2, agent, split public)
- `causcibench_real.q084` (T2, agent, split public)
- `causcibench_real.q085` (T2, agent, split public)
- `causcibench_real.q086` (T2, agent, split public)
- `causcibench_real.q087` (T2, agent, split public)
- `causcibench_real.q088` (T2, agent, split public)
- `causcibench_real.q089` (T2, agent, split public)
- `causcibench_real.q091` (T2, agent, split public)
- `causcibench_real.q093` (T2, agent, split public)
- `causcibench_real.q097` (T2, agent, split public)
- `causcibench_real.q098` (T2, agent, split public)
- `causcibench_real.q099` (T2, agent, split public)
- `causcibench_real.q100` (T2, agent, split public)
- `causcibench_real.q101` (T2, agent, split public)
- `causcibench_real.q102` (T2, agent, split public)
- `causcibench_real.q103` (T2, agent, split public)
- `causcibench_real.q104` (T2, agent, split public)
- `causcibench_real.q105` (T2, agent, split public)
- `causcibench_real.q106` (T2, agent, split public)
- `causcibench_real.q107` (T2, agent, split public)
- `causcibench_real.q108` (T2, agent, split public)
- `causcibench_real.q109` (T2, agent, split public)
- `causcibench_real.q110` (T2, agent, split public)
- `causcibench_real.q112` (T2, agent, split public)
- `causcibench_real.q113` (T2, agent, split public)
- `causcibench_real.q114` (T2, agent, split public)
- `causcibench_real.q115` (T2, agent, split public)
- `causcibench_real.q116` (T2, agent, split public)
- `causcibench_real.q117` (T2, agent, split public)
- `causcibench_real.q118` (T2, agent, split public)
- `causcibench_real.q119` (T2, agent, split public)
- `causcibench_real.q120` (T2, agent, split public)
- `causcibench_real.q121` (T2, agent, split public)
- `causcibench_real.q122` (T2, agent, split public)
- `causcibench_real.q123` (T2, agent, split public)
- `causcibench_real.q124` (T2, agent, split public)
- `causcibench_real.q125` (T2, agent, split public)
- `causcibench_real.q126` (T2, agent, split public)
- `causcibench_real.q127` (T2, agent, split public)
- `causcibench_real.q128` (T2, agent, split public)
- `causcibench_real.q129` (T2, agent, split public)
- `causcibench_real.q130` (T2, agent, split public)
- `causcibench_real.q131` (T2, agent, split public)
- `causcibench_real.q132` (T2, agent, split public)
- `causcibench_real.q133` (T2, agent, split public)
- `causcibench_real.q134` (T2, agent, split public)
- `causcibench_real.q135` (T2, agent, split public)
- `causcibench_real.q136` (T2, agent, split public)
- `causcibench_real.q137` (T2, agent, split public)
- `causcibench_real.q138` (T2, agent, split public)
- `causcibench_real.q139` (T2, agent, split public)
- `causcibench_real.q140` (T2, agent, split public)
- `causcibench_real.q141` (T2, agent, split public)
- `causcibench_real.q142` (T2, agent, split public)
- `causcibench_real.q143` (T2, agent, split public)
- `causcibench_real.q144` (T2, agent, split public)
- `causcibench_real.q145` (T2, agent, split public)
- `causcibench_real.q146` (T2, agent, split public)
- `causcibench_real.q147` (T2, agent, split public)
- `causcibench_real.q148` (T2, agent, split public)
- `causcibench_real.q149` (T2, agent, split public)
- `causcibench_real.q150` (T2, agent, split public)
- `causcibench_real.q151` (T2, agent, split public)
- `causcibench_real.q152` (T2, agent, split public)
- `causcibench_real.q153` (T2, agent, split public)
- `causcibench_real.q154` (T2, agent, split public)
- `causcibench_real.q155` (T2, agent, split public)
- `causcibench_real.q156` (T2, agent, split public)
- `causcibench_real.q157` (T2, agent, split public)
- `causcibench_real.q158` (T2, agent, split public)
- `causcibench_real.q159` (T2, agent, split public)
- `causcibench_real.q160` (T2, agent, split public)
- `causcibench_real.q161` (T2, agent, split public)
- `causcibench_real.q162` (T2, agent, split public)
- `causcibench_real.q163` (T2, agent, split public)
- `causcibench_real.q164` (T2, agent, split public)
- `causcibench_real.q165` (T2, agent, split public)
- `causcibench_real.q166` (T2, agent, split public)
- `causcibench_real.q167` (T2, agent, split public)
- `causcibench_real.q168` (T2, agent, split public)
- `causcibench_real.q169` (T2, agent, split public)
- `causcibench_real.q170` (T2, agent, split public)
- `causcibench_real.q171` (T2, agent, split public)
- `causcibench_real.q172` (T2, agent, split public)
- `causcibench_real.q173` (T2, agent, split public)
- `causcibench_real.q174` (T2, agent, split public)
- `causcibench_real.q175` (T2, agent, split public)
