{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y5UTAHKQ7KH7ZC55QWGINM3M2I","short_pith_number":"pith:Y5UTAHKQ","schema_version":"1.0","canonical_sha256":"c769301d50fa8ffc8bbd858c86b36cd2317a9211bc39a50ff22aaceca71fa529","source":{"kind":"arxiv","id":"2411.09255","version":1},"attestation_state":"computed","paper":{"title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongjun Jang, Hyopil Shin, Jean Seo, Jongwon Lim","submitted_at":"2024-11-14T07:41:34Z","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"},"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":"2411.09255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T07:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"44020d287c4e8f04222698a0f7df0f4cf35fd52ab65cc09abb3ddfb30b041793","abstract_canon_sha256":"4541f51c52b74b88fc030d0b35540fdb4cbd1840e15da64f402c0d806d531b8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:23.399219Z","signature_b64":"pXZxQ9t4mLWoBkyziIEhzeq82PhmQt2WGx4M68gAJa1CxYbxeG7Lo6gXwhEuN83eLuOx3T5X/nc9mzEFhghwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c769301d50fa8ffc8bbd858c86b36cd2317a9211bc39a50ff22aaceca71fa529","last_reissued_at":"2026-07-05T09:35:23.398616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:23.398616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongjun Jang, Hyopil Shin, Jean Seo, Jongwon Lim","submitted_at":"2024-11-14T07:41:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09255","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/2411.09255/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":"2411.09255","created_at":"2026-07-05T09:35:23.398682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09255v1","created_at":"2026-07-05T09:35:23.398682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09255","created_at":"2026-07-05T09:35:23.398682+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5UTAHKQ7KH7","created_at":"2026-07-05T09:35:23.398682+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5UTAHKQ7KH7ZC55","created_at":"2026-07-05T09:35:23.398682+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5UTAHKQ","created_at":"2026-07-05T09:35:23.398682+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/Y5UTAHKQ7KH7ZC55QWGINM3M2I","json":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I.json","graph_json":"https://pith.science/api/pith-number/Y5UTAHKQ7KH7ZC55QWGINM3M2I/graph.json","events_json":"https://pith.science/api/pith-number/Y5UTAHKQ7KH7ZC55QWGINM3M2I/events.json","paper":"https://pith.science/paper/Y5UTAHKQ"},"agent_actions":{"view_html":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I","download_json":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I.json","view_paper":"https://pith.science/paper/Y5UTAHKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09255&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5UTAHKQ7KH7ZC55QWGINM3M2I/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5UTAHKQ7KH7ZC55QWGINM3M2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I/action/storage_attestation","attest_author":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I/action/author_attestation","sign_citation":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I/action/citation_signature","submit_replication":"https://pith.science/pith/Y5UTAHKQ7KH7ZC55QWGINM3M2I/action/replication_record"}},"created_at":"2026-07-05T09:35:23.398682+00:00","updated_at":"2026-07-05T09:35:23.398682+00:00"}