{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5UTAHKQ7KH7ZC55QWGINM3M2I","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":"4541f51c52b74b88fc030d0b35540fdb4cbd1840e15da64f402c0d806d531b8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T07:41:34Z","title_canon_sha256":"44020d287c4e8f04222698a0f7df0f4cf35fd52ab65cc09abb3ddfb30b041793"},"schema_version":"1.0","source":{"id":"2411.09255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09255","created_at":"2026-07-05T09:35:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09255v1","created_at":"2026-07-05T09:35:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09255","created_at":"2026-07-05T09:35:23Z"},{"alias_kind":"pith_short_12","alias_value":"Y5UTAHKQ7KH7","created_at":"2026-07-05T09:35:23Z"},{"alias_kind":"pith_short_16","alias_value":"Y5UTAHKQ7KH7ZC55","created_at":"2026-07-05T09:35:23Z"},{"alias_kind":"pith_short_8","alias_value":"Y5UTAHKQ","created_at":"2026-07-05T09:35:23Z"}],"graph_snapshots":[{"event_id":"sha256:25b2a0594b4dbfa41ec52255123a03b1f9924ff2240b910a7fabdef2b790f08c","target":"graph","created_at":"2026-07-05T09:35:23Z","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/2411.09255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DAHL, a benchmark dataset and automated evaluation system designed to assess hallucination in long-form text generation, specifically within the biomedical domain. Our benchmark dataset, meticulously curated from biomedical research papers, consists of 8,573 questions across 29 categories. DAHL evaluates fact-conflicting hallucinations in Large Language Models (LLMs) by deconstructing responses into atomic units, each representing a single piece of information. The accuracy of these responses is averaged to produce the DAHL Score, offering a more in-depth evaluation of hallucinati","authors_text":"Dongjun Jang, Hyopil Shin, Jean Seo, Jongwon Lim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T07:41:34Z","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09255","kind":"arxiv","version":1},"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":"sha256:9c5bb528fbecb54ecc7b256e518dea688ea2024b730f717dc93bc034cacc84f9","target":"record","created_at":"2026-07-05T09:35:23Z","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":"4541f51c52b74b88fc030d0b35540fdb4cbd1840e15da64f402c0d806d531b8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T07:41:34Z","title_canon_sha256":"44020d287c4e8f04222698a0f7df0f4cf35fd52ab65cc09abb3ddfb30b041793"},"schema_version":"1.0","source":{"id":"2411.09255","kind":"arxiv","version":1}},"canonical_sha256":"c769301d50fa8ffc8bbd858c86b36cd2317a9211bc39a50ff22aaceca71fa529","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c769301d50fa8ffc8bbd858c86b36cd2317a9211bc39a50ff22aaceca71fa529","first_computed_at":"2026-07-05T09:35:23.398616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:23.398616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pXZxQ9t4mLWoBkyziIEhzeq82PhmQt2WGx4M68gAJa1CxYbxeG7Lo6gXwhEuN83eLuOx3T5X/nc9mzEFhghwAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:23.399219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c5bb528fbecb54ecc7b256e518dea688ea2024b730f717dc93bc034cacc84f9","sha256:25b2a0594b4dbfa41ec52255123a03b1f9924ff2240b910a7fabdef2b790f08c"],"state_sha256":"76b062b90d46e5759e098871843ba0cc9c0340d1ed4719e219ed088cd9fcc202"}