key,doi_or_arxiv,verification_source,verified_utc,status
abadie2023clustering,doi:10.1093/qje/qjac038,https://api.crossref.org/works/10.1093/qje/qjac038,2026-11-02T23:42:23Z,verified
acemoglu2011skills,doi:10.1016/S0169-7218(11)02410-5,https://api.crossref.org/works/10.1016/S0169-7218(11)02410-5,2026-11-02T23:42:10Z,verified
acemoglu2018race,doi:10.1257/aer.20160696,https://api.crossref.org/works/10.1257/aer.20160696,2026-11-02T23:42:05Z,verified
acemoglu2019automation,doi:10.1257/jep.33.2.3,https://api.crossref.org/works/10.1257/jep.33.2.3,2026-11-02T23:42:06Z,verified
acemoglu2020robots,doi:10.1086/705716,https://api.crossref.org/works/10.1086/705716,2026-11-02T23:42:06Z,verified
acemoglu2025macroeconomics,doi:10.1093/epolic/eiae042,https://api.crossref.org/works/10.1093/epolic/eiae042,2026-11-02T23:42:12Z,verified
agarwal2023radiology,doi:10.3386/w31422,https://api.crossref.org/works/10.3386/w31422,2026-11-02T23:42:20Z,verified
agrawal2019prediction,doi:10.1257/jep.33.2.31,https://api.crossref.org/works/10.1257/jep.33.2.31,2026-11-02T23:42:17Z,verified
anthropic2024computeruse,url,https://www.anthropic.com/news/3-5-models-and-computer-use,2026-11-02T00:00:00Z,"verified (web, official publisher page)"
anthropic2025opus4card,url,https://assets.claude.com/6d8a8055020700718b0c49369f60816ba2a7c285.pdf,2026-11-02T00:00:00Z,"verified (web, official publisher page)"
appel2025uneven,arXiv:2511.15080,https://arxiv.org/abs/2511.15080,2026-11-02T23:47:45Z,verified
arntz2017revisiting,doi:10.1016/j.econlet.2017.07.001,https://api.crossref.org/works/10.1016/j.econlet.2017.07.001,2026-11-02T23:51:52Z,verified
athey2016econometrics,arXiv:1607.00698,https://arxiv.org/abs/1607.00698,2026-11-02T23:50:47Z,verified
athey2020allocation,doi:10.1257/pandp.20201034,https://api.crossref.org/works/10.1257/pandp.20201034,2026-11-02T23:42:19Z,verified
autor2003skill,doi:10.1162/003355303322552801,https://api.crossref.org/works/10.1162/003355303322552801,2026-11-02T23:42:04Z,verified
autor2015jobs,doi:10.1257/jep.29.3.3,https://api.crossref.org/works/10.1257/jep.29.3.3,2026-11-02T23:42:09Z,verified
backlund2025vendingbench,arXiv:2502.15840,https://arxiv.org/abs/2502.15840,2026-11-02T23:47:21Z,verified
bates2015lme4,doi:10.18637/jss.v067.i01,https://api.crossref.org/works/10.18637/jss.v067.i01,2026-11-02T23:42:28Z,verified
becker2025metr,arXiv:2507.09089,https://export.arxiv.org/api/query?id_list=2507.09089,2026-11-02T23:43:09Z,verified
bowman2022oversight,arXiv:2211.03540,https://export.arxiv.org/api/query?id_list=2211.03540,2026-11-02T23:43:52Z,verified
brynjolfsson2017workforce,doi:10.1126/science.aap8062,https://api.crossref.org/works/10.1126/science.aap8062,2026-11-02T23:42:08Z,verified
brynjolfsson2018machines,doi:10.1257/pandp.20181019,https://api.crossref.org/works/10.1257/pandp.20181019,2026-11-02T23:42:07Z,verified
brynjolfsson2025canaries,url,https://digitaleconomy.stanford.edu/publication/canaries-in-the-coal-mine-six-facts-about-the-recent-employment-effects-of-artificial-intelligence,2026-11-02T00:00:00Z,"verified (web, official publisher page)"
brynjolfsson2025generative,doi:10.1093/qje/qjae044,https://api.crossref.org/works/10.1093/qje/qjae044,2026-11-02T23:42:14Z,verified
cameron2008bootstrap,doi:10.1162/rest.90.3.414,https://api.crossref.org/works/10.1162/rest.90.3.414,2026-11-02T23:42:22Z,verified
cameron2015practitioner,doi:10.3368/jhr.50.2.317,https://api.crossref.org/works/10.3368/jhr.50.2.317,2026-11-02T23:42:22Z,verified
catalini2026agi,arXiv:2602.20946,https://arxiv.org/abs/2602.20946,2026-11-02T23:47:48Z,verified
cazzaniga2024genai,doi:10.5089/9798400262548.006,https://api.crossref.org/works/10.5089/9798400262548.006,2026-11-02T23:42:11Z,verified
cemri2025fail,arXiv:2503.13657,https://export.arxiv.org/api/query?id_list=2503.13657,2026-11-02T23:43:35Z,verified
chan2024mlebench,arXiv:2410.07095,https://export.arxiv.org/api/query?id_list=2410.07095,2026-11-02T23:43:22Z,verified
chen2023selfdebug,arXiv:2304.05128,https://arxiv.org/abs/2304.05128,2026-11-02T23:46:35Z,verified
choi2023lawyering,doi:10.2139/ssrn.4626276,https://api.crossref.org/works/10.2139/ssrn.4626276,2026-11-02T23:42:42Z,verified
cox1972regression,doi:10.1111/j.2517-6161.1972.tb00899.x,https://api.crossref.org/works/10.1111/j.2517-6161.1972.tb00899.x,2026-11-02T23:42:26Z,verified
cui2024developers,doi:10.2139/ssrn.4945566,https://api.crossref.org/works/10.2139/ssrn.4945566,2026-11-02T23:42:15Z,verified
dellacqua2023jagged,doi:10.2139/ssrn.4573321,https://api.crossref.org/works/10.2139/ssrn.4573321,2026-11-02T23:42:15Z,verified
dellacqua2025cybernetic,doi:10.2139/ssrn.5188231,https://api.crossref.org/works/10.2139/ssrn.5188231,2026-11-02T23:42:41Z,verified
dietvorst2015aversion,doi:10.1037/xge0000033,https://api.crossref.org/works/10.1037/xge0000033,2026-11-02T23:42:20Z,verified
drouin2024workarena,arXiv:2403.07718,https://export.arxiv.org/api/query?id_list=2403.07718,2026-11-02T23:43:20Z,verified
dziri2023faith,arXiv:2305.18654,https://arxiv.org/abs/2305.18654,2026-11-02T23:46:43Z,verified
eloundou2024gpts,doi:10.1126/science.adj0998,https://api.crossref.org/works/10.1126/science.adj0998,2026-11-02T23:42:09Z,verified
felten2021exposure,doi:10.1002/smj.3286,https://api.crossref.org/works/10.1002/smj.3286,2026-11-02T23:42:08Z,verified
felten2023language,arXiv:2303.01157,https://export.arxiv.org/api/query?id_list=2303.01157,2026-11-02T23:42:44Z,verified
fine1999competing,doi:10.1080/01621459.1999.10474144,https://api.crossref.org/works/10.1080/01621459.1999.10474144,2026-11-02T23:42:27Z,verified
frey2017future,doi:10.1016/j.techfore.2016.08.019,https://api.crossref.org/works/10.1016/j.techfore.2016.08.019,2026-11-02T23:42:07Z,verified
gmyrek2023generative,doi:10.54394/FHEM8239,https://api.crossref.org/works/10.54394/FHEM8239,2026-11-02T23:42:11Z,verified
gmyrek2025refined,doi:10.54394/HETP0387,https://api.crossref.org/works/10.54394/HETP0387,2026-11-02T23:46:16Z,verified
gu2024survey,arXiv:2411.15594,https://arxiv.org/abs/2411.15594,2026-11-02T23:53:25Z,verified
guha2023legalbench,arXiv:2308.11462,https://export.arxiv.org/api/query?id_list=2308.11462,2026-11-02T23:43:49Z,verified
gwet2008interrater,doi:10.1348/000711006X126600,https://api.crossref.org/works/10.1348/000711006X126600,2026-11-02T23:42:25Z,verified
hadfield2025economy,arXiv:2509.01063,https://arxiv.org/abs/2509.01063,2026-11-02T23:48:22Z,verified
hampole2025labor,doi:10.3386/w33509,https://api.crossref.org/works/10.3386/w33509,2026-11-02T23:46:14Z,verified
handa2025economic,arXiv:2503.04761,https://export.arxiv.org/api/query?id_list=2503.04761,2026-11-02T23:43:01Z,verified
hayes2007reliability,doi:10.1080/19312450709336664,https://api.crossref.org/works/10.1080/19312450709336664,2026-11-02T23:42:25Z,verified
holmstrom1979moral,doi:10.2307/3003320,https://api.crossref.org/works/10.2307/3003320,2026-11-02T23:42:18Z,verified
holmstrom1991multitask,doi:10.1093/jleo/7.special_issue.24,https://api.crossref.org/works/10.1093/jleo/7.special_issue.24,2026-11-02T23:42:18Z,verified
horton2023silicus,doi:10.3386/w31122,https://api.crossref.org/works/10.3386/w31122,2026-11-02T23:42:30Z,verified
huang2023selfcorrect,arXiv:2310.01798,https://arxiv.org/abs/2310.01798,2026-11-02T23:46:38Z,verified
humlum2025still,doi:10.3386/w33777,https://api.crossref.org/works/10.3386/w33777,2026-11-02T23:46:13Z,verified
ide2025knowledge,doi:10.1086/737233,https://api.crossref.org/works/10.1086/737233,2026-11-02T23:46:14Z,verified
immorlica2024agents,arXiv:2406.00477,https://arxiv.org/abs/2406.00477,2026-11-02T23:47:29Z,verified
jimenez2024swebench,arXiv:2310.06770,https://export.arxiv.org/api/query?id_list=2310.06770,2026-11-02T23:43:13Z,verified
kaplan1958nonparametric,doi:10.1080/01621459.1958.10501452,https://api.crossref.org/works/10.1080/01621459.1958.10501452,2026-11-02T23:42:27Z,verified
kapoor2024matter,arXiv:2407.01502,https://export.arxiv.org/api/query?id_list=2407.01502,2026-11-02T23:43:27Z,verified
kolt2025governing,arXiv:2501.07913,https://arxiv.org/abs/2501.07913,2026-11-02T23:48:27Z,verified
korinek2023generative,doi:10.1257/jel.20231736,https://api.crossref.org/works/10.1257/jel.20231736,2026-11-02T23:42:16Z,verified
krippendorff2004reliability,doi:10.1111/j.1468-2958.2004.tb00738.x,https://api.crossref.org/works/10.1111/j.1468-2958.2004.tb00738.x,2026-11-02T23:42:24Z,verified
kwa2025horizon,arXiv:2503.14499,https://export.arxiv.org/api/query?id_list=2503.14499,2026-11-02T23:43:10Z,verified
list2019multiple,doi:10.1007/s10683-018-09597-5,https://api.crossref.org/works/10.1007/s10683-018-09597-5,2026-11-02T23:42:34Z,verified
liu2024agentbench,arXiv:2308.03688,https://export.arxiv.org/api/query?id_list=2308.03688,2026-11-02T23:43:15Z,verified
liu2026claudecode,arXiv:2604.14228,https://arxiv.org/abs/2604.14228,2026-11-02T23:48:37Z,verified
ma2024spreadsheetbench,arXiv:2406.14991,https://arxiv.org/abs/2406.14991,2026-11-02T23:47:08Z,verified
madaan2023selfrefine,arXiv:2303.17651,https://export.arxiv.org/api/query?id_list=2303.17651,2026-11-02T23:43:32Z,verified
merrill2026terminalbench,arXiv:2601.11868,https://arxiv.org/abs/2601.11868,2026-11-02T23:47:42Z,verified
mialon2023gaia,arXiv:2311.12983,https://export.arxiv.org/api/query?id_list=2311.12983,2026-11-02T23:43:16Z,verified
miller2024errorbars,arXiv:2411.00640,https://export.arxiv.org/api/query?id_list=2411.00640,2026-11-02T23:43:39Z,verified
miserendino2025swelancer,arXiv:2502.12115,https://export.arxiv.org/api/query?id_list=2502.12115,2026-11-02T23:43:44Z,verified
nosek2018preregistration,doi:10.1073/pnas.1708274114,https://api.crossref.org/works/10.1073/pnas.1708274114,2026-11-02T23:42:23Z,verified
noy2023experimental,doi:10.1126/science.adh2586,https://api.crossref.org/works/10.1126/science.adh2586,2026-11-02T23:42:13Z,verified
olken2015preanalysis,doi:10.1257/jep.29.3.61,https://api.crossref.org/works/10.1257/jep.29.3.61,2026-11-02T23:42:24Z,verified
otis2024entrepreneurial,doi:10.2139/ssrn.4671369,https://api.crossref.org/works/10.2139/ssrn.4671369,2026-11-02T23:42:16Z,verified
panickssery2024selfpreference,arXiv:2404.13076,https://export.arxiv.org/api/query?id_list=2404.13076,2026-11-02T23:43:31Z,verified
patwardhan2025gdpval,arXiv:2510.04374,https://arxiv.org/abs/2510.04374,2026-11-02T23:47:40Z,verified
peng2023copilot,arXiv:2302.06590,https://export.arxiv.org/api/query?id_list=2302.06590,2026-11-02T23:43:09Z,verified
pizzinelli2023exposure,doi:10.5089/9798400254802.001,https://api.crossref.org/works/10.5089/9798400254802.001,2026-11-02T23:50:10Z,verified
polo2024tinybenchmarks,arXiv:2402.14992,https://arxiv.org/abs/2402.14992,2026-11-02T23:46:49Z,verified
rein2025hcast,arXiv:2503.17354,https://export.arxiv.org/api/query?id_list=2503.17354,2026-11-02T23:43:12Z,verified
restrepo2025missed,doi:10.3386/w34423,https://api.crossref.org/works/10.3386/w34423,2026-11-02T23:46:15Z,verified
shinn2023reflexion,arXiv:2303.11366,https://export.arxiv.org/api/query?id_list=2303.11366,2026-11-02T23:43:32Z,verified
simmons2011falsepositive,doi:10.1177/0956797611417632,https://api.crossref.org/works/10.1177/0956797611417632,2026-11-02T23:42:33Z,verified
sinha2025horizon,arXiv:2509.09677,https://arxiv.org/abs/2509.09677,2026-11-02T23:46:46Z,verified
sreenivas2026contracting,arXiv:2608.18232,https://arxiv.org/abs/2608.18232,2026-11-02T23:48:19Z,verified
stroebl2024flaws,arXiv:2411.17501,https://arxiv.org/abs/2411.17501,2026-11-02T23:46:40Z,verified
svanberg2024costeffective,doi:10.2139/ssrn.4700751,https://api.crossref.org/works/10.2139/ssrn.4700751,2026-11-02T23:42:32Z,verified
tomlinson2025working,arXiv:2507.07935,https://export.arxiv.org/api/query?id_list=2507.07935,2026-11-02T23:43:07Z,verified
trivedi2024appworld,doi:10.18653/v1/2024.acl-long.850,https://api.crossref.org/works/10.18653/v1/2024.acl-long.850,2026-11-02T23:42:38Z,verified
vaccaro2024combinations,doi:10.1038/s41562-024-02024-1,https://api.crossref.org/works/10.1038/s41562-024-02024-1,2026-11-02T23:42:21Z,verified
vania2021irt,doi:10.18653/v1/2021.acl-long.92,https://api.crossref.org/works/10.18653/v1/2021.acl-long.92,2026-11-02T23:42:39Z,verified
wang2024fair,doi:10.18653/v1/2024.acl-long.511,https://api.crossref.org/works/10.18653/v1/2024.acl-long.511,2026-11-02T23:42:39Z,verified
wang2024officebench,arXiv:2407.19056,https://arxiv.org/abs/2407.19056,2026-11-02T23:47:03Z,verified
wang2024openhands,arXiv:2407.16741,https://export.arxiv.org/api/query?id_list=2407.16741,2026-11-02T23:43:24Z,verified
wijk2024rebench,arXiv:2411.15114,https://export.arxiv.org/api/query?id_list=2411.15114,2026-11-02T23:43:11Z,verified
xie2024osworld,arXiv:2404.07972,https://export.arxiv.org/api/query?id_list=2404.07972,2026-11-02T23:43:14Z,verified
xu2024agentcompany,arXiv:2412.14161,https://export.arxiv.org/api/query?id_list=2412.14161,2026-11-02T23:43:17Z,verified
yang2024sweagent,arXiv:2405.15793,https://export.arxiv.org/api/query?id_list=2405.15793,2026-11-02T23:43:23Z,verified
yao2024taubench,arXiv:2406.12045,https://export.arxiv.org/api/query?id_list=2406.12045,2026-11-02T23:43:17Z,verified
yuan2026osworld2,arXiv:2606.29537,https://arxiv.org/abs/2606.29537,2026-11-02T23:48:40Z,verified
zheng2023judge,arXiv:2306.05685,https://export.arxiv.org/api/query?id_list=2306.05685,2026-11-02T23:43:28Z,verified
zhou2024webarena,arXiv:2307.13854,https://export.arxiv.org/api/query?id_list=2307.13854,2026-11-02T23:43:14Z,verified
zhou2025lost,arXiv:2505.15055,https://arxiv.org/abs/2505.15055,2026-11-02T23:48:29Z,verified
zhu2025rigorous,arXiv:2507.02825,https://arxiv.org/abs/2507.02825,2026-11-02T23:47:50Z,verified