{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IU2UQMNTT5K7SJNYGTMGFTVYDK","short_pith_number":"pith:IU2UQMNT","schema_version":"1.0","canonical_sha256":"45354831b39f55f925b834d862ceb81a9e9f290fb02b6982589f58d62b12ebe2","source":{"kind":"arxiv","id":"2310.02932","version":2},"attestation_state":"computed","paper":{"title":"Assessing Large Language Models on Climate Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Ben Gaiarin, Christian Buck, Heidi Lam, Jannis Bulian, Markus Leippold, Massimiliano Ciaramita, Michelle Chen H\\\"ubscher, Mike S. Sch\\\"afer, Nadine Strau{\\ss}, Niels G. Mede","submitted_at":"2023-10-04T16:09:48Z","abstract_excerpt":"As Large Language Models (LLMs) rise in popularity, it is necessary to assess their capability in critically relevant domains. We present a comprehensive evaluation framework, grounded in science communication research, to assess LLM responses to questions about climate change. Our framework emphasizes both presentational and epistemological adequacy, offering a fine-grained analysis of LLM generations spanning 8 dimensions and 30 issues. Our evaluation task is a real-world example of a growing number of challenging problems where AI can complement and lift human performance. We introduce a no"},"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":"2310.02932","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:09:48Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"2c94cc523d40e6a998cfc5af8e80c76ad1b5a21ae0bb56ca646e56d48a8f0d8c","abstract_canon_sha256":"339e0efadcea8ab43b5a616641e6598ffa184bfe63cccf6a968f9cf9997d3445"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:56.239984Z","signature_b64":"e33nR7GDK/YV9MB5678Vi/HJh1Zj2iE1E8Fp/9fLyKfHWUn9LWOhHbeclXIkyVN7zbOFTDHp2PFFAXSx8qOnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45354831b39f55f925b834d862ceb81a9e9f290fb02b6982589f58d62b12ebe2","last_reissued_at":"2026-07-05T08:23:56.239445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:56.239445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing Large Language Models on Climate Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Ben Gaiarin, Christian Buck, Heidi Lam, Jannis Bulian, Markus Leippold, Massimiliano Ciaramita, Michelle Chen H\\\"ubscher, Mike S. Sch\\\"afer, Nadine Strau{\\ss}, Niels G. Mede","submitted_at":"2023-10-04T16:09:48Z","abstract_excerpt":"As Large Language Models (LLMs) rise in popularity, it is necessary to assess their capability in critically relevant domains. We present a comprehensive evaluation framework, grounded in science communication research, to assess LLM responses to questions about climate change. Our framework emphasizes both presentational and epistemological adequacy, offering a fine-grained analysis of LLM generations spanning 8 dimensions and 30 issues. Our evaluation task is a real-world example of a growing number of challenging problems where AI can complement and lift human performance. We introduce a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02932","kind":"arxiv","version":2},"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/2310.02932/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":"2310.02932","created_at":"2026-07-05T08:23:56.239505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02932v2","created_at":"2026-07-05T08:23:56.239505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02932","created_at":"2026-07-05T08:23:56.239505+00:00"},{"alias_kind":"pith_short_12","alias_value":"IU2UQMNTT5K7","created_at":"2026-07-05T08:23:56.239505+00:00"},{"alias_kind":"pith_short_16","alias_value":"IU2UQMNTT5K7SJNY","created_at":"2026-07-05T08:23:56.239505+00:00"},{"alias_kind":"pith_short_8","alias_value":"IU2UQMNT","created_at":"2026-07-05T08:23:56.239505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08181","citing_title":"Challenges in Guardrailing Large Language Models for Science","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK","json":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK.json","graph_json":"https://pith.science/api/pith-number/IU2UQMNTT5K7SJNYGTMGFTVYDK/graph.json","events_json":"https://pith.science/api/pith-number/IU2UQMNTT5K7SJNYGTMGFTVYDK/events.json","paper":"https://pith.science/paper/IU2UQMNT"},"agent_actions":{"view_html":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK","download_json":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK.json","view_paper":"https://pith.science/paper/IU2UQMNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02932&json=true","fetch_graph":"https://pith.science/api/pith-number/IU2UQMNTT5K7SJNYGTMGFTVYDK/graph.json","fetch_events":"https://pith.science/api/pith-number/IU2UQMNTT5K7SJNYGTMGFTVYDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK/action/storage_attestation","attest_author":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK/action/author_attestation","sign_citation":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK/action/citation_signature","submit_replication":"https://pith.science/pith/IU2UQMNTT5K7SJNYGTMGFTVYDK/action/replication_record"}},"created_at":"2026-07-05T08:23:56.239505+00:00","updated_at":"2026-07-05T08:23:56.239505+00:00"}