{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UVWMVAUHUGKVFJRRQNOODXPKSU","short_pith_number":"pith:UVWMVAUH","schema_version":"1.0","canonical_sha256":"a56cca8287a19552a631835ce1ddea952506b631a59aa38c8d02f236e8491b6b","source":{"kind":"arxiv","id":"2310.17526","version":2},"attestation_state":"computed","paper":{"title":"Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Azza Warraitch, Johanna Kappenberg, Kristin Hadfield, Qusai Khraisha, Sophie Put","submitted_at":"2023-10-26T16:18:30Z","abstract_excerpt":"Systematic reviews are vital for guiding practice, research, and policy, yet they are often slow and labour-intensive. Large language models (LLMs) could offer a way to speed up and automate systematic reviews, but their performance in such tasks has not been comprehensively evaluated against humans, and no study has tested GPT-4, the biggest LLM so far. This pre-registered study evaluates GPT-4's capability in title/abstract screening, full-text review, and data extraction across various literature types and languages using a 'human-out-of-the-loop' approach. Although GPT-4 had accuracy on pa"},"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":"2310.17526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T16:18:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9442571bccad11c51dfd0771629fd863402189600e8cec2cfe2bcebb583e2aea","abstract_canon_sha256":"a15f2e7ec4a6e0d2f8ca21dbe9bb6003515662a92f53fd1ba02bdae8090b0d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:25.890890Z","signature_b64":"eWLAUF7z4ljCqsudBqSGvTZ/D363k2sxTPhYqUQ67Rq37WCPVNUEMXgZAW1Ea+E1VpIk8Ww6Fbdf4OsQqreCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56cca8287a19552a631835ce1ddea952506b631a59aa38c8d02f236e8491b6b","last_reissued_at":"2026-07-05T08:06:25.890347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:25.890347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Azza Warraitch, Johanna Kappenberg, Kristin Hadfield, Qusai Khraisha, Sophie Put","submitted_at":"2023-10-26T16:18:30Z","abstract_excerpt":"Systematic reviews are vital for guiding practice, research, and policy, yet they are often slow and labour-intensive. Large language models (LLMs) could offer a way to speed up and automate systematic reviews, but their performance in such tasks has not been comprehensively evaluated against humans, and no study has tested GPT-4, the biggest LLM so far. This pre-registered study evaluates GPT-4's capability in title/abstract screening, full-text review, and data extraction across various literature types and languages using a 'human-out-of-the-loop' approach. Although GPT-4 had accuracy on pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17526","kind":"arxiv","version":2},"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/2310.17526/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":"2310.17526","created_at":"2026-07-05T08:06:25.890410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17526v2","created_at":"2026-07-05T08:06:25.890410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17526","created_at":"2026-07-05T08:06:25.890410+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVWMVAUHUGKV","created_at":"2026-07-05T08:06:25.890410+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVWMVAUHUGKVFJRR","created_at":"2026-07-05T08:06:25.890410+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVWMVAUH","created_at":"2026-07-05T08:06:25.890410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12173","citing_title":"Carry the Tail in Consensus Protocols","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU","json":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU.json","graph_json":"https://pith.science/api/pith-number/UVWMVAUHUGKVFJRRQNOODXPKSU/graph.json","events_json":"https://pith.science/api/pith-number/UVWMVAUHUGKVFJRRQNOODXPKSU/events.json","paper":"https://pith.science/paper/UVWMVAUH"},"agent_actions":{"view_html":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU","download_json":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU.json","view_paper":"https://pith.science/paper/UVWMVAUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17526&json=true","fetch_graph":"https://pith.science/api/pith-number/UVWMVAUHUGKVFJRRQNOODXPKSU/graph.json","fetch_events":"https://pith.science/api/pith-number/UVWMVAUHUGKVFJRRQNOODXPKSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU/action/storage_attestation","attest_author":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU/action/author_attestation","sign_citation":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU/action/citation_signature","submit_replication":"https://pith.science/pith/UVWMVAUHUGKVFJRRQNOODXPKSU/action/replication_record"}},"created_at":"2026-07-05T08:06:25.890410+00:00","updated_at":"2026-07-05T08:06:25.890410+00:00"}