{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICF3QNOFDSESFI557RLU7AWM2I","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":"1464d800e41730e7824f5acc5ec670eb6f3d5dbf213bd051b7f6876597883a26","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:12:19Z","title_canon_sha256":"226104491eff6472f0dfeaa63b3b759b0a930351691d4ae18aca2f440f6ab7a4"},"schema_version":"1.0","source":{"id":"2410.16701","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16701","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16701v2","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16701","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_12","alias_value":"ICF3QNOFDSES","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_16","alias_value":"ICF3QNOFDSESFI55","created_at":"2026-07-05T10:27:17Z"},{"alias_kind":"pith_short_8","alias_value":"ICF3QNOF","created_at":"2026-07-05T10:27:17Z"}],"graph_snapshots":[{"event_id":"sha256:0dbb85c6452d6b5b966c8957e55b660f66218ec57772413ee60e6f93c960173a","target":"graph","created_at":"2026-07-05T10:27:17Z","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/2410.16701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of Large Language Models (LLMs) in climate science has recently gained significant attention. However, a critical issue remains: the lack of a comprehensive evaluation framework capable of assessing the quality and scientific validity of model outputs. To address this issue, we develop ClimaGen (Climate QA Generator), an adaptive learning framework that generates question-answer pairs from graduate textbooks with climate scientists in the loop. As a result, we present ClimaQA-Gold, an expert-annotated benchmark dataset alongside ClimaQA-Silver, a large-scale, comprehensive synthetic QA","authors_text":"Duncan Watson-Parris, Leon Bergen, Rose Yu, Spencer Ho, Srikar Eranky, Taylor Berg-Kirkpatrick, Veeramakali Vignesh Manivannan, Yasaman Jafari, Yian Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:12:19Z","title":"ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16701","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":"sha256:360a38413d3f9a75aed3c93b4f814a89b1187d0e961760c75330fbe860b8c90b","target":"record","created_at":"2026-07-05T10:27:17Z","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":"1464d800e41730e7824f5acc5ec670eb6f3d5dbf213bd051b7f6876597883a26","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T05:12:19Z","title_canon_sha256":"226104491eff6472f0dfeaa63b3b759b0a930351691d4ae18aca2f440f6ab7a4"},"schema_version":"1.0","source":{"id":"2410.16701","kind":"arxiv","version":2}},"canonical_sha256":"408bb835c51c8922a3bdfc574f82ccd20ec80d11bb1e11a0d5ebd23872f0aa95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"408bb835c51c8922a3bdfc574f82ccd20ec80d11bb1e11a0d5ebd23872f0aa95","first_computed_at":"2026-07-05T10:27:17.810393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:17.810393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s4jZHlw5uA1DPADUE68srTkIG4ItkZt0i6CHm16sKZjkqqstv9qwkKAVA2ZPYPdC8/FpViKAoi6ZVSW3ykzHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:17.810868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16701","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:360a38413d3f9a75aed3c93b4f814a89b1187d0e961760c75330fbe860b8c90b","sha256:0dbb85c6452d6b5b966c8957e55b660f66218ec57772413ee60e6f93c960173a"],"state_sha256":"32fc3a4c04d25315fe52a961f6f98422545ac050fc5b1c305d35144b0da3e24f"}