{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4XH5HMS5AZ7ACW2NORD2THT2LW","short_pith_number":"pith:4XH5HMS5","schema_version":"1.0","canonical_sha256":"e5cfd3b25d067e015b4d7447a99e7a5dbf06c50659e7e7e3d33859c9cc593196","source":{"kind":"arxiv","id":"2505.18653","version":1},"attestation_state":"computed","paper":{"title":"Climate-Eval: A Comprehensive Benchmark for NLP Tasks Related to Climate Change","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriele Messori, Joakim Nivre, Murathan Kurfal{\\i}, Shorouq Zahra","submitted_at":"2025-05-24T11:45:46Z","abstract_excerpt":"Climate-Eval is a comprehensive benchmark designed to evaluate natural language processing models across a broad range of tasks related to climate change. Climate-Eval aggregates existing datasets along with a newly developed news classification dataset, created specifically for this release. This results in a benchmark of 25 tasks based on 13 datasets, covering key aspects of climate discourse, including text classification, question answering, and information extraction. Our benchmark provides a standardized evaluation suite for systematically assessing the performance of large language mode"},"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":"2505.18653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T11:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"0df4d0e63c3cdb23229bc58d5a9cf7bba6bf55cbb56af7f68951593cdb8fbeac","abstract_canon_sha256":"52675aae9152997c09953f8d3a51b9ec2e2885094d8367ceef0c7f9df6327692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:17.127139Z","signature_b64":"KNNHj6gONdxftyS/6rM2Nu3wUJA9W1O66L4kKaBMN0FTQ6sG41ZYuzJbdE1AEG9KoYRySRigb0fG84hHYqyUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5cfd3b25d067e015b4d7447a99e7a5dbf06c50659e7e7e3d33859c9cc593196","last_reissued_at":"2026-07-05T11:09:17.126646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:17.126646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Climate-Eval: A Comprehensive Benchmark for NLP Tasks Related to Climate Change","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriele Messori, Joakim Nivre, Murathan Kurfal{\\i}, Shorouq Zahra","submitted_at":"2025-05-24T11:45:46Z","abstract_excerpt":"Climate-Eval is a comprehensive benchmark designed to evaluate natural language processing models across a broad range of tasks related to climate change. Climate-Eval aggregates existing datasets along with a newly developed news classification dataset, created specifically for this release. This results in a benchmark of 25 tasks based on 13 datasets, covering key aspects of climate discourse, including text classification, question answering, and information extraction. Our benchmark provides a standardized evaluation suite for systematically assessing the performance of large language mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18653","kind":"arxiv","version":1},"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/2505.18653/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":"2505.18653","created_at":"2026-07-05T11:09:17.126704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18653v1","created_at":"2026-07-05T11:09:17.126704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18653","created_at":"2026-07-05T11:09:17.126704+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XH5HMS5AZ7A","created_at":"2026-07-05T11:09:17.126704+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XH5HMS5AZ7ACW2N","created_at":"2026-07-05T11:09:17.126704+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XH5HMS5","created_at":"2026-07-05T11:09:17.126704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW","json":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW.json","graph_json":"https://pith.science/api/pith-number/4XH5HMS5AZ7ACW2NORD2THT2LW/graph.json","events_json":"https://pith.science/api/pith-number/4XH5HMS5AZ7ACW2NORD2THT2LW/events.json","paper":"https://pith.science/paper/4XH5HMS5"},"agent_actions":{"view_html":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW","download_json":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW.json","view_paper":"https://pith.science/paper/4XH5HMS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18653&json=true","fetch_graph":"https://pith.science/api/pith-number/4XH5HMS5AZ7ACW2NORD2THT2LW/graph.json","fetch_events":"https://pith.science/api/pith-number/4XH5HMS5AZ7ACW2NORD2THT2LW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW/action/storage_attestation","attest_author":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW/action/author_attestation","sign_citation":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW/action/citation_signature","submit_replication":"https://pith.science/pith/4XH5HMS5AZ7ACW2NORD2THT2LW/action/replication_record"}},"created_at":"2026-07-05T11:09:17.126704+00:00","updated_at":"2026-07-05T11:09:17.126704+00:00"}