{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UEF42IBYA7SIKQT7L5ERJMD4P3","short_pith_number":"pith:UEF42IBY","schema_version":"1.0","canonical_sha256":"a10bcd203807e485427f5f4914b07c7ed0f00659c6c348a8d084ca32596ff57a","source":{"kind":"arxiv","id":"2607.09932","version":1},"attestation_state":"computed","paper":{"title":"Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Robert Williams","submitted_at":"2026-07-10T19:29:26Z","abstract_excerpt":"Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark evaluation framework for measuring the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences. The framework consists of 200 stratified trials drawn from the Aggregate Analysis of ClinicalTrials.gov database, evaluated using audience-specific prompt templates and a six-dimension faithfulness annotation schema. Base"},"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":"2607.09932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T19:29:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64c2ac96150aa523a77ed5312ca3e17bb76c8d9cd12548ac54fa962a7fde6e0b","abstract_canon_sha256":"68084af135089ecc00bad40d23140a9e0f3331edf3afcc141ce124b2c46c39aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:43.732506Z","signature_b64":"sHPT7n9EO4ji6J/g0Vbe6BcC2S0EfiJ9MvM8xVX3RwwqmC7sdwCPNdM76gsHmPjzuxDX8CzUPcyyXAl5bgFWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a10bcd203807e485427f5f4914b07c7ed0f00659c6c348a8d084ca32596ff57a","last_reissued_at":"2026-07-14T00:18:43.731645Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:43.731645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Robert Williams","submitted_at":"2026-07-10T19:29:26Z","abstract_excerpt":"Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark evaluation framework for measuring the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences. The framework consists of 200 stratified trials drawn from the Aggregate Analysis of ClinicalTrials.gov database, evaluated using audience-specific prompt templates and a six-dimension faithfulness annotation schema. Base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09932","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/2607.09932/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":"2607.09932","created_at":"2026-07-14T00:18:43.732090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09932v1","created_at":"2026-07-14T00:18:43.732090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09932","created_at":"2026-07-14T00:18:43.732090+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEF42IBYA7SI","created_at":"2026-07-14T00:18:43.732090+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEF42IBYA7SIKQT7","created_at":"2026-07-14T00:18:43.732090+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEF42IBY","created_at":"2026-07-14T00:18:43.732090+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/UEF42IBYA7SIKQT7L5ERJMD4P3","json":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3.json","graph_json":"https://pith.science/api/pith-number/UEF42IBYA7SIKQT7L5ERJMD4P3/graph.json","events_json":"https://pith.science/api/pith-number/UEF42IBYA7SIKQT7L5ERJMD4P3/events.json","paper":"https://pith.science/paper/UEF42IBY"},"agent_actions":{"view_html":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3","download_json":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3.json","view_paper":"https://pith.science/paper/UEF42IBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09932&json=true","fetch_graph":"https://pith.science/api/pith-number/UEF42IBYA7SIKQT7L5ERJMD4P3/graph.json","fetch_events":"https://pith.science/api/pith-number/UEF42IBYA7SIKQT7L5ERJMD4P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3/action/storage_attestation","attest_author":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3/action/author_attestation","sign_citation":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3/action/citation_signature","submit_replication":"https://pith.science/pith/UEF42IBYA7SIKQT7L5ERJMD4P3/action/replication_record"}},"created_at":"2026-07-14T00:18:43.732090+00:00","updated_at":"2026-07-14T00:18:43.732090+00:00"}