{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:12:28Z","timestamp":1783476748213,"version":"3.55.0"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["NFDI 27\/1 - 460037581 - BERD@NFDI"],"award-info":[{"award-number":["NFDI 27\/1 - 460037581 - BERD@NFDI"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["NFDI 27\/1 - 460037581 - BERD@NFDI"],"award-info":[{"award-number":["NFDI 27\/1 - 460037581 - BERD@NFDI"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["NFDI 27\/1 - 460037581 - BERD@NFDI"],"award-info":[{"award-number":["NFDI 27\/1 - 460037581 - BERD@NFDI"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["NFDI 27\/1 - 460037581 - BERD@NFDI"],"award-info":[{"award-number":["NFDI 27\/1 - 460037581 - BERD@NFDI"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007306","name":"Bayerische Akademie der Wissenschaften","doi-asserted-by":"publisher","award":["bidt - GreenDIA"],"award-info":[{"award-number":["bidt - GreenDIA"]}],"id":[{"id":"10.13039\/501100007306","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Reliable company-level greenhouse gas (GHG) emissions data are essential for stakeholders addressing the climate crisis. However, existing datasets are often fragmented, inconsistent, and lack transparent methodologies, making it difficult to obtain reliable emissions data. To address this challenge, we present a gold standard dataset containing emission metrics extracted from 139 sustainability reports collected from company websites. This dataset acts as an intermediate step to validate and fine-tune models for large-scale extraction of emissions data from thousands of reports. We employ a Large Language Model (LLM)-powered extraction pipeline to automatically extract emissions metrics. These values are then independently assessed by two non-expert annotators. Reports with full agreement are directly considered gold standard, while discrepancies undergo expert review in two stages, with remaining disagreements resolved through in-person discussions. This structured process ensures high data quality while reducing reliance on experts. Our dataset serves as a benchmark for human and automated annotation, with significant reuse potential for information extraction tasks in sustainable finance as well as other downstream tasks such as greenwashing analysis.<\/jats:p>","DOI":"10.1038\/s41597-025-05664-8","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T07:49:40Z","timestamp":1756280980000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Addressing data gaps in sustainability reporting: A benchmark dataset for greenhouse gas emission extraction"],"prefix":"10.1038","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7587-7064","authenticated-orcid":false,"given":"Jacob","family":"Beck","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Steinberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Dimmelmeier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laia","family":"Domenech Burin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Kormanyos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurice","family":"Fehr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4058-1543","authenticated-orcid":false,"given":"Malte","family":"Schierholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"5664_CR1","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1080\/14693062.2019.1641460","volume":"19","author":"J Skovgaard","year":"2019","unstructured":"Skovgaard, J., Ferrari, S. S. & Knagg\u00e5rd, \u212b Mapping and clustering the adoption of carbon pricing policies: What polities price carbon and why? Clim. Policy 19, 1173\u20131185, https:\/\/doi.org\/10.1080\/14693062.2019.1641460 (2019).","journal-title":"Clim. Policy"},{"key":"5664_CR2","unstructured":"Network for Greening the Financial System. Information Note: Improving Greenhouse Gas Emissions Data, https:\/\/www.ngfs.net\/system\/files\/import\/ngfs\/medias\/documents\/ngfs_information_note_on_improving_ghg_emission_data.pdf (2024)."},{"key":"5664_CR3","doi-asserted-by":"publisher","first-page":"e580","DOI":"10.1002\/wcc.580","volume":"10","author":"J Setzer","year":"2019","unstructured":"Setzer, J. & Vanhala, L. C. Climate change litigation: A review of research on courts and litigants in climate governance. WIREs Clim. Change 10, e580, https:\/\/doi.org\/10.1002\/wcc.580 (2019).","journal-title":"WIREs Clim. Change"},{"key":"5664_CR4","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1111\/jiec.13008","volume":"26","author":"T Busch","year":"2022","unstructured":"Busch, T., Johnson, M. & Pioch, T. Corporate carbon performance data: Quo vadis? J. Ind. Ecol. 26, 350\u2013363, https:\/\/doi.org\/10.1111\/jiec.13008 (2022).","journal-title":"J. Ind. Ecol."},{"key":"5664_CR5","unstructured":"Kob, J. & Dittrich, K. Carbonising financial assets: Between commodification and assetization of carbon relations, https:\/\/warwick.ac.uk\/fac\/soc\/wbs\/research\/ikon\/research\/climate-finance\/publications-and-working-papers\/kob__dittrich_2024_carbonising_financial_assets_wcfr_working_paper.pdf (2024)."},{"key":"5664_CR6","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1080\/17530350.2021.1935297","volume":"14","author":"J Walenta","year":"2021","unstructured":"Walenta, J. The making of the corporate carbon footprint: The politics behind emission scoping. J. Cult. Econ. 14, 533\u2013548, https:\/\/doi.org\/10.1080\/17530350.2021.1935297 (2021).","journal-title":"J. Cult. Econ."},{"key":"5664_CR7","first-page":"5","volume":"5","author":"J Andrew","year":"2011","unstructured":"Andrew, J. & Cortese, C. L. Carbon disclosures: Comparability, the carbon disclosure project and the greenhouse gas protocol. Aust. Account. Bus. Financ. J. 5, 5\u201318 https:\/\/www.uowoajournals.org\/aabfj\/article\/1200\/galley\/1186\/download\/ (2011).","journal-title":"Aust. Account. Bus. Financ. J."},{"key":"5664_CR8","doi-asserted-by":"publisher","unstructured":"Jia, J., Ranger, N. & Chaudhury, A. Designing for comparability: A foundational principle of analysis missing in carbon reporting systems. SSRN, https:\/\/doi.org\/10.2139\/ssrn.4258460 (2022).","DOI":"10.2139\/ssrn.4258460"},{"key":"5664_CR9","unstructured":"WRI & WBCSD. The greenhouse gas protocol: A corporate reporting and accounting standard - revised version, https:\/\/ghgprotocol.org\/sites\/default\/files\/standards\/ghg-protocol-revised.pdf (2011)."},{"key":"5664_CR10","unstructured":"Sotos, M. E. GHG Protocol Scope 2 Guidance - An amendment to the GHG Protocol Corporate Standard, https:\/\/files.wri.org\/d8\/s3fs-public\/ghg-protocol-scope-2-guidance.pdf (2015)."},{"key":"5664_CR11","unstructured":"WRI & WBCSD. Technical guidance for calculating Scope 3 emissions (version 1.0), https:\/\/ghgprotocol.org\/sites\/default\/files\/standards\/Scope3_Calculation_Guidance_0.pdf (2013)."},{"key":"5664_CR12","unstructured":"Tang, K., Shrimali, G. & Christiaen, C. SDQI Discussion Paper - Data Quality Considerations for Estimating Financed Emissions. Smith School of Enterprise and the Environment, https:\/\/coilink.org\/20.500.12592\/nbf0sn (2023)."},{"key":"5664_CR13","doi-asserted-by":"publisher","unstructured":"Mishra, L. et al. Statements: Universal information extraction from tables with large language models for ESG KPIs. In Proc. 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024), 193\u2013214, https:\/\/doi.org\/10.18653\/v1\/2024.climatenlp-1.15 (2024).","DOI":"10.18653\/v1\/2024.climatenlp-1.15"},{"key":"5664_CR14","doi-asserted-by":"publisher","unstructured":"OECD. Global Corporate Sustainability Report 2024 https:\/\/doi.org\/10.1787\/8416b635-en (2024).","DOI":"10.1787\/8416b635-en"},{"key":"5664_CR15","doi-asserted-by":"publisher","unstructured":"Dimmelmeier, A. et al. Informing climate risk analysis using textual information \u2013 A research agenda. In Proc. 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024), 12\u201326, https:\/\/doi.org\/10.18653\/v1\/2024.climatenlp-1.2 (2024).","DOI":"10.18653\/v1\/2024.climatenlp-1.2"},{"key":"5664_CR16","doi-asserted-by":"publisher","unstructured":"Beck, J. et al. Gold Standard and Annotation Dataset for CO2 Emissions Annotation. Zenodo, https:\/\/doi.org\/10.5281\/zenodo.14035800 (2025).","DOI":"10.5281\/zenodo.14035800"},{"key":"5664_CR17","unstructured":"Lepere, M. et al. Emissions gaming?: A gap in the GHG Protocol may be facilitating gaming in accounting of GHG emissions. KBS Research Impact Papers, https:\/\/www.kcl.ac.uk\/business\/assets\/pdf\/research-papers\/kbs-research-impact-paper-1-emissions-gaming.pdf (2023)."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05664-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05664-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05664-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T07:49:46Z","timestamp":1756280986000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-05664-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["5664"],"URL":"https:\/\/doi.org\/10.1038\/s41597-025-05664-8","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"17 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This paper represents the authors\u2019 personal opinions and does not reflect the views of the Deutsche Bundesbank or the Eurosystem.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1497"}}