{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RVLXFYW7PDGAWZ6R7DL33A3UDY","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":"7a39647715aa4dba4c246607fb794bdeb75d3b1a7c490ed061bc343ae4d22a95","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T23:09:04Z","title_canon_sha256":"3c1148b53a01b485af5727beab78fd8e2089a72a54322b045c4cec41e7cbc8fa"},"schema_version":"1.0","source":{"id":"2507.15152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15152","created_at":"2026-06-09T01:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15152v1","created_at":"2026-06-09T01:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15152","created_at":"2026-06-09T01:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"RVLXFYW7PDGA","created_at":"2026-06-09T01:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"RVLXFYW7PDGAWZ6R","created_at":"2026-06-09T01:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"RVLXFYW7","created_at":"2026-06-09T01:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:435fc7e8f4d18577312fafcf436eabaca7c56d3245898ddaec419cfee9c054e3","target":"graph","created_at":"2026-06-09T01:04:38Z","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/2507.15152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automating data extraction from full-text randomised controlled trials (RCTs) for meta-analysis remains a significant challenge. This study evaluates the practical performance of three LLMs (Gemini-2.0-flash, Grok-3, GPT-4o-mini) across tasks involving statistical results, risk-of-bias assessments, and study-level characteristics in three medical domains: hypertension, diabetes, and orthopaedics. We tested four distinct prompting strategies (basic prompting, self-reflective prompting, model ensemble, and customised prompts) to determine how to improve extraction quality. All models demonstrate","authors_text":"Anuradha Mathrani, Lingbo Li, Teo Susnjak","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T23:09:04Z","title":"What Level of Automation is \"Good Enough\"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15152","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":"sha256:15046e0f07e294bf626d771f568fbfb800b4445e24ae14504cf9d44e57a20b22","target":"record","created_at":"2026-06-09T01:04:38Z","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":"7a39647715aa4dba4c246607fb794bdeb75d3b1a7c490ed061bc343ae4d22a95","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T23:09:04Z","title_canon_sha256":"3c1148b53a01b485af5727beab78fd8e2089a72a54322b045c4cec41e7cbc8fa"},"schema_version":"1.0","source":{"id":"2507.15152","kind":"arxiv","version":1}},"canonical_sha256":"8d5772e2df78cc0b67d1f8d7bd83741e10aab29e477eaf8194bdedec62613702","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d5772e2df78cc0b67d1f8d7bd83741e10aab29e477eaf8194bdedec62613702","first_computed_at":"2026-06-09T01:04:38.938621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:38.938621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7jq828yk53FsFQZh/puniwey0iwhwoCN4v0Qd/VGOjfAvGWNI3Eup+3aYbRnzVzpKvqH1dLPRkeqFkLY2PKAw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:38.939090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15046e0f07e294bf626d771f568fbfb800b4445e24ae14504cf9d44e57a20b22","sha256:435fc7e8f4d18577312fafcf436eabaca7c56d3245898ddaec419cfee9c054e3"],"state_sha256":"8c20a880b868f505093bafef74738baf135c6f23822c5d83512e94d3d8b0ed36"}