{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCTEA2V76KGCIKMFGZUXOM4FLI","short_pith_number":"pith:XCTEA2V7","schema_version":"1.0","canonical_sha256":"b8a6406abff28c24298536697733855a300f6988b0edff8f3dad477ce435a493","source":{"kind":"arxiv","id":"2506.18819","version":1},"attestation_state":"computed","paper":{"title":"RWESummary: A Framework and Test for Choosing Large Language Models to Summarize Real-World Evidence (RWE) Studies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arjun Mukerji, Jason Jones, Michael L. Jackson, Neil Sanghavi","submitted_at":"2025-06-23T16:28:03Z","abstract_excerpt":"Large Language Models (LLMs) have been extensively evaluated for general summarization tasks as well as medical research assistance, but they have not been specifically evaluated for the task of summarizing real-world evidence (RWE) from structured output of RWE studies. We introduce RWESummary, a proposed addition to the MedHELM framework (Bedi, Cui, Fuentes, Unell et al., 2025) to enable benchmarking of LLMs for this task. RWESummary includes one scenario and three evaluations covering major types of errors observed in summarization of medical research studies and was developed using Atropos"},"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":"2506.18819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T16:28:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1f7049106e6b265c96175ce475bdfa824f521aadfd5b21f1ea600284d445401","abstract_canon_sha256":"3b9b5d290e34884ad3face8b49e0e4229922284713a8e9e8331b5e9a350f578b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:56.522704Z","signature_b64":"tPKQHwRjuXKvvCiiHD4WY3ZgnukTrg5rSgYFFm5xmd3xlzbGeVw54Hin4sbviYTNE5IaBjnJIhtMkt0RpnDTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a6406abff28c24298536697733855a300f6988b0edff8f3dad477ce435a493","last_reissued_at":"2026-07-05T11:25:56.522248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:56.522248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RWESummary: A Framework and Test for Choosing Large Language Models to Summarize Real-World Evidence (RWE) Studies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arjun Mukerji, Jason Jones, Michael L. Jackson, Neil Sanghavi","submitted_at":"2025-06-23T16:28:03Z","abstract_excerpt":"Large Language Models (LLMs) have been extensively evaluated for general summarization tasks as well as medical research assistance, but they have not been specifically evaluated for the task of summarizing real-world evidence (RWE) from structured output of RWE studies. We introduce RWESummary, a proposed addition to the MedHELM framework (Bedi, Cui, Fuentes, Unell et al., 2025) to enable benchmarking of LLMs for this task. RWESummary includes one scenario and three evaluations covering major types of errors observed in summarization of medical research studies and was developed using Atropos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18819","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/2506.18819/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":"2506.18819","created_at":"2026-07-05T11:25:56.522306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18819v1","created_at":"2026-07-05T11:25:56.522306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18819","created_at":"2026-07-05T11:25:56.522306+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCTEA2V76KGC","created_at":"2026-07-05T11:25:56.522306+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCTEA2V76KGCIKMF","created_at":"2026-07-05T11:25:56.522306+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCTEA2V7","created_at":"2026-07-05T11:25:56.522306+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/XCTEA2V76KGCIKMFGZUXOM4FLI","json":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI.json","graph_json":"https://pith.science/api/pith-number/XCTEA2V76KGCIKMFGZUXOM4FLI/graph.json","events_json":"https://pith.science/api/pith-number/XCTEA2V76KGCIKMFGZUXOM4FLI/events.json","paper":"https://pith.science/paper/XCTEA2V7"},"agent_actions":{"view_html":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI","download_json":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI.json","view_paper":"https://pith.science/paper/XCTEA2V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18819&json=true","fetch_graph":"https://pith.science/api/pith-number/XCTEA2V76KGCIKMFGZUXOM4FLI/graph.json","fetch_events":"https://pith.science/api/pith-number/XCTEA2V76KGCIKMFGZUXOM4FLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI/action/storage_attestation","attest_author":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI/action/author_attestation","sign_citation":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI/action/citation_signature","submit_replication":"https://pith.science/pith/XCTEA2V76KGCIKMFGZUXOM4FLI/action/replication_record"}},"created_at":"2026-07-05T11:25:56.522306+00:00","updated_at":"2026-07-05T11:25:56.522306+00:00"}