{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/climabench-a-benchmark-dataset-for-climate","title":"Towards Answering Climate Questionnaires from Unstructured Climate Reports","arxiv_id":"2301.04253","date":"2023-01-11","proceeding":null,"authors":["Daniel Spokoyny","Tanmay Laud","Tom Corringham","Taylor Berg-Kirkpatrick"],"abstract":"The topic of Climate Change (CC) has received limited attention in NLP despite its urgency. Activists and policymakers need NLP tools to effectively process the vast and rapidly growing unstructured textual climate reports into structured form. To tackle this challenge we introduce two new large-scale climate questionnaire datasets and use their existing structure to train self-supervised models. We conduct experiments to show that these models can learn to generalize to climate disclosures of different organizations types than seen during training. We then use these models to help align texts from unstructured climate documents to the semi-structured questionnaires in a human pilot study. Finally, to support further NLP research in the climate domain we introduce a benchmark of existing climate text classification datasets to better evaluate and compare existing models.","url_abs":"https://arxiv.org/abs/2301.04253v2","url_pdf":"https://arxiv.org/pdf/2301.04253v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"climabench-a-benchmark-dataset-for-climate","repo_url":"https://github.com/climabench/climabench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"climabench-a-benchmark-dataset-for-climate","repo_url":"https://github.com/nlp-rise/climateeval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"climabench-a-benchmark-dataset-for-climate","repo_url":"https://github.com/spokoyny/spokoyny.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[{"slug":"climabench","name":"Climabench","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04253"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/climabench/climabench","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlp-rise/climateeval","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spokoyny/spokoyny.github.io","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"0e02018211d1cae7","entry":"compute_metrics","repo":"climabench/climabench","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/climabench/climabench/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e02018211d1cae7"}},{"code_sha256_prefix":"281cccb95f744714","entry":"find_best_acc_and_threshold","repo":"climabench/climabench","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/climabench/climabench/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"281cccb95f744714"}},{"code_sha256_prefix":"839625e8e0ae2d43","entry":"find_best_f1_and_threshold","repo":"climabench/climabench","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/climabench/climabench/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"839625e8e0ae2d43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}