{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IU2UQMNTT5K7SJNYGTMGFTVYDK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"339e0efadcea8ab43b5a616641e6598ffa184bfe63cccf6a968f9cf9997d3445","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:09:48Z","title_canon_sha256":"2c94cc523d40e6a998cfc5af8e80c76ad1b5a21ae0bb56ca646e56d48a8f0d8c"},"schema_version":"1.0","source":{"id":"2310.02932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02932","created_at":"2026-07-05T08:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02932v2","created_at":"2026-07-05T08:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02932","created_at":"2026-07-05T08:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"IU2UQMNTT5K7","created_at":"2026-07-05T08:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"IU2UQMNTT5K7SJNY","created_at":"2026-07-05T08:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"IU2UQMNT","created_at":"2026-07-05T08:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:e9000a17eea762ef6d594c7f50367a56850a19951e028a871f9f342469d3e2a9","target":"graph","created_at":"2026-07-05T08:23:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.02932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:09:48Z","title":"Assessing Large Language Models on Climate Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02932","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9d31322ebe1d72e9c8de159979fc201e6e493a489cb66db98a1841747a399ff0","target":"record","created_at":"2026-07-05T08:23:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"339e0efadcea8ab43b5a616641e6598ffa184bfe63cccf6a968f9cf9997d3445","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:09:48Z","title_canon_sha256":"2c94cc523d40e6a998cfc5af8e80c76ad1b5a21ae0bb56ca646e56d48a8f0d8c"},"schema_version":"1.0","source":{"id":"2310.02932","kind":"arxiv","version":2}},"canonical_sha256":"45354831b39f55f925b834d862ceb81a9e9f290fb02b6982589f58d62b12ebe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45354831b39f55f925b834d862ceb81a9e9f290fb02b6982589f58d62b12ebe2","first_computed_at":"2026-07-05T08:23:56.239445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:56.239445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e33nR7GDK/YV9MB5678Vi/HJh1Zj2iE1E8Fp/9fLyKfHWUn9LWOhHbeclXIkyVN7zbOFTDHp2PFFAXSx8qOnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:56.239984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d31322ebe1d72e9c8de159979fc201e6e493a489cb66db98a1841747a399ff0","sha256:e9000a17eea762ef6d594c7f50367a56850a19951e028a871f9f342469d3e2a9"],"state_sha256":"766c537186809f07cdccd8a15ec222e5bcd87e9031e4aedfdf22ca49e623065e"}