{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MVSLUBYHKYJLEFG4CNMFNWXJZP","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":"62c6c6f69d11c600e942d428a87702fc1788d293d9540269a21757d0f5c31571","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T18:58:09Z","title_canon_sha256":"c1f4484d51c025cd594363fa781894d05663926d8df5bf6b0a85bd9722e7157b"},"schema_version":"1.0","source":{"id":"2505.22787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22787","created_at":"2026-07-05T11:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22787v1","created_at":"2026-07-05T11:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22787","created_at":"2026-07-05T11:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"MVSLUBYHKYJL","created_at":"2026-07-05T11:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"MVSLUBYHKYJLEFG4","created_at":"2026-07-05T11:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"MVSLUBYH","created_at":"2026-07-05T11:11:49Z"}],"graph_snapshots":[{"event_id":"sha256:e24df9debc2b7bfccf4a48bb6c5491a86a15c73c2f5950c9d43765a3038b24d2","target":"graph","created_at":"2026-07-05T11:11:49Z","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/2505.22787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Systematic reviews (SR), in which experts summarize and analyze evidence across individual studies to provide insights on a specialized topic, are a cornerstone for evidence-based clinical decision-making, research, and policy. Given the exponential growth of scientific articles, there is growing interest in using large language models (LLMs) to automate SR generation. However, the ability of LLMs to critically assess evidence and reason across multiple documents to provide recommendations at the same proficiency as domain experts remains poorly characterized. We therefore ask: Can LLMs match ","authors_text":"Alejandro Lozano, Christopher Polzak, James Burgess, Kevin Wu, Min Woo Sun, Serena Yeung-Levy, Yuhui Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T18:58:09Z","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22787","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:e06f982c17411c732c35b15181b925e9199e026bd381ac4e03b5e630bbbb655d","target":"record","created_at":"2026-07-05T11:11:49Z","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":"62c6c6f69d11c600e942d428a87702fc1788d293d9540269a21757d0f5c31571","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T18:58:09Z","title_canon_sha256":"c1f4484d51c025cd594363fa781894d05663926d8df5bf6b0a85bd9722e7157b"},"schema_version":"1.0","source":{"id":"2505.22787","kind":"arxiv","version":1}},"canonical_sha256":"6564ba07075612b214dc135856dae9cbfac1859b25cb2d3ffd493f9a9666b806","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6564ba07075612b214dc135856dae9cbfac1859b25cb2d3ffd493f9a9666b806","first_computed_at":"2026-07-05T11:11:49.961461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:49.961461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RfrNP60FBaDr6fd4rMGpo0pXhC1Co7h3GJ9v5UKsjgK3GpSi6VjnS8r/6Up5zX7BaK52CYqOtWsOdUIDCxmjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:49.961940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e06f982c17411c732c35b15181b925e9199e026bd381ac4e03b5e630bbbb655d","sha256:e24df9debc2b7bfccf4a48bb6c5491a86a15c73c2f5950c9d43765a3038b24d2"],"state_sha256":"6d3817d9eea1bf1cb702ab5bf0e785f47d633bcf67df8caa1e0ce8a0860f9693"}