{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PMWWISBURTQFFJZTDRZ42WY73C","short_pith_number":"pith:PMWWISBU","schema_version":"1.0","canonical_sha256":"7b2d6448348ce052a7331c73cd5b1fd8af57e46504811900c2edc934b9515b37","source":{"kind":"arxiv","id":"2110.12010","version":3},"attestation_state":"computed","paper":{"title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Julia Anna Bingler, Markus Leippold, Mathias Kraus, Nicolas Webersinke","submitted_at":"2021-10-22T18:47:34Z","abstract_excerpt":"Over the recent years, large pretrained language models (LM) have revolutionized the field of natural language processing (NLP). However, while pretraining on general language has been shown to work very well for common language, it has been observed that niche language poses problems. In particular, climate-related texts include specific language that common LMs can not represent accurately. We argue that this shortcoming of today's LMs limits the applicability of modern NLP to the broad field of text processing of climate-related texts. As a remedy, we propose CLIMATEBERT, a transformer-base"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.12010","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-22T18:47:34Z","cross_cats_sorted":[],"title_canon_sha256":"824210d2f0285e7ffdb138b5d83ad8af7cf0606c800f6bf567de54239a2e7679","abstract_canon_sha256":"c38099226915576dd1e92416d99270d8370cc2754433f919f40226b4973502a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:03.042296Z","signature_b64":"o2VRkYr6HWMq8xC5zrcU0mVgYDQJ6YLv+RRNCnH3b8sqDJ4UOp6toiSGbAUpAWgYvmcga1yDtz0CpeZHPJrxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b2d6448348ce052a7331c73cd5b1fd8af57e46504811900c2edc934b9515b37","last_reissued_at":"2026-07-05T05:26:03.041853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:03.041853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Julia Anna Bingler, Markus Leippold, Mathias Kraus, Nicolas Webersinke","submitted_at":"2021-10-22T18:47:34Z","abstract_excerpt":"Over the recent years, large pretrained language models (LM) have revolutionized the field of natural language processing (NLP). However, while pretraining on general language has been shown to work very well for common language, it has been observed that niche language poses problems. In particular, climate-related texts include specific language that common LMs can not represent accurately. We argue that this shortcoming of today's LMs limits the applicability of modern NLP to the broad field of text processing of climate-related texts. As a remedy, we propose CLIMATEBERT, a transformer-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12010","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.12010/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.12010","created_at":"2026-07-05T05:26:03.041912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12010v3","created_at":"2026-07-05T05:26:03.041912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12010","created_at":"2026-07-05T05:26:03.041912+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMWWISBURTQF","created_at":"2026-07-05T05:26:03.041912+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMWWISBURTQFFJZT","created_at":"2026-07-05T05:26:03.041912+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMWWISBU","created_at":"2026-07-05T05:26:03.041912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28538","citing_title":"Legal Domain Adaptation of Modern BERT Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13743","citing_title":"GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17792","citing_title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07177","citing_title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12512","citing_title":"Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13743","citing_title":"GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20454","citing_title":"Not all ANIMALs are equal: metaphorical framing through source domains and semantic frames","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C","json":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C.json","graph_json":"https://pith.science/api/pith-number/PMWWISBURTQFFJZTDRZ42WY73C/graph.json","events_json":"https://pith.science/api/pith-number/PMWWISBURTQFFJZTDRZ42WY73C/events.json","paper":"https://pith.science/paper/PMWWISBU"},"agent_actions":{"view_html":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C","download_json":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C.json","view_paper":"https://pith.science/paper/PMWWISBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12010&json=true","fetch_graph":"https://pith.science/api/pith-number/PMWWISBURTQFFJZTDRZ42WY73C/graph.json","fetch_events":"https://pith.science/api/pith-number/PMWWISBURTQFFJZTDRZ42WY73C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C/action/storage_attestation","attest_author":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C/action/author_attestation","sign_citation":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C/action/citation_signature","submit_replication":"https://pith.science/pith/PMWWISBURTQFFJZTDRZ42WY73C/action/replication_record"}},"created_at":"2026-07-05T05:26:03.041912+00:00","updated_at":"2026-07-05T05:26:03.041912+00:00"}