{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z2B3R4SH5HVFIA4TTOKF5NPD74","short_pith_number":"pith:Z2B3R4SH","schema_version":"1.0","canonical_sha256":"ce83b8f247e9ea5403939b945eb5e3ff11710037c61ae7c3cf3e0fbfc49bb904","source":{"kind":"arxiv","id":"2508.20525","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Health Fact-Checking with LLM-Generated Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiahe Qian, Jingze Zhang, Yifan Peng, Yiliang Zhou","submitted_at":"2025-08-28T08:06:33Z","abstract_excerpt":"Fact-checking for health-related content is challenging due to the limited availability of annotated training data. In this study, we propose a synthetic data generation pipeline that leverages large language models (LLMs) to augment training data for health-related fact checking. In this pipeline, we summarize source documents, decompose the summaries into atomic facts, and use an LLM to construct sentence-fact entailment tables. From the entailment relations in the table, we further generate synthetic text-claim pairs with binary veracity labels. These synthetic data are then combined with t"},"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":"2508.20525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-28T08:06:33Z","cross_cats_sorted":[],"title_canon_sha256":"2d79f508671134c3548c648bdaa3ebde6cccb0fd433b8cda131e20f197a801f6","abstract_canon_sha256":"dbea89137f30935d95f86e9824a26b0f9b8f0a1201178ccefb3605b8ec58a569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:54.229721Z","signature_b64":"AA8zqTjC7Vl/MrgZ7Z3OyPQYS4yheHlWgmrlrDNmiHj2pXxmiXgZZndu6WAUKyxGdSzcsF8un5nxlB8UH+S3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce83b8f247e9ea5403939b945eb5e3ff11710037c61ae7c3cf3e0fbfc49bb904","last_reissued_at":"2026-07-05T12:00:54.229219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:54.229219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Health Fact-Checking with LLM-Generated Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiahe Qian, Jingze Zhang, Yifan Peng, Yiliang Zhou","submitted_at":"2025-08-28T08:06:33Z","abstract_excerpt":"Fact-checking for health-related content is challenging due to the limited availability of annotated training data. In this study, we propose a synthetic data generation pipeline that leverages large language models (LLMs) to augment training data for health-related fact checking. In this pipeline, we summarize source documents, decompose the summaries into atomic facts, and use an LLM to construct sentence-fact entailment tables. From the entailment relations in the table, we further generate synthetic text-claim pairs with binary veracity labels. These synthetic data are then combined with t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20525","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/2508.20525/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":"2508.20525","created_at":"2026-07-05T12:00:54.229278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20525v1","created_at":"2026-07-05T12:00:54.229278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20525","created_at":"2026-07-05T12:00:54.229278+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2B3R4SH5HVF","created_at":"2026-07-05T12:00:54.229278+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2B3R4SH5HVFIA4T","created_at":"2026-07-05T12:00:54.229278+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2B3R4SH","created_at":"2026-07-05T12:00:54.229278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.05308","citing_title":"Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74","json":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74.json","graph_json":"https://pith.science/api/pith-number/Z2B3R4SH5HVFIA4TTOKF5NPD74/graph.json","events_json":"https://pith.science/api/pith-number/Z2B3R4SH5HVFIA4TTOKF5NPD74/events.json","paper":"https://pith.science/paper/Z2B3R4SH"},"agent_actions":{"view_html":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74","download_json":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74.json","view_paper":"https://pith.science/paper/Z2B3R4SH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20525&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2B3R4SH5HVFIA4TTOKF5NPD74/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2B3R4SH5HVFIA4TTOKF5NPD74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74/action/storage_attestation","attest_author":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74/action/author_attestation","sign_citation":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74/action/citation_signature","submit_replication":"https://pith.science/pith/Z2B3R4SH5HVFIA4TTOKF5NPD74/action/replication_record"}},"created_at":"2026-07-05T12:00:54.229278+00:00","updated_at":"2026-07-05T12:00:54.229278+00:00"}