{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMIM4373SVOPDTS735GAND2JSN","short_pith_number":"pith:CMIM4373","schema_version":"1.0","canonical_sha256":"1310ce6ffb955cf1ce5fdf4c068f4993574daeaeed574bc42e2a0c687867e8ac","source":{"kind":"arxiv","id":"2411.02451","version":2},"attestation_state":"computed","paper":{"title":"High-performance automated abstract screening with large language model ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrew Soltan, Archie Watt, Arun James Thirunavukarasu, George Nishimura, Hamid Butt, Jessica O'Logbon, Marc El Khoury, Mustafa Mahmood, Rohan Sanghera, Yuqing Chen","submitted_at":"2024-11-03T10:06:14Z","abstract_excerpt":"Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 record"},"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":"2411.02451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-03T10:06:14Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"b9fec88c6b2f7b9e8cd3b03d986db59168dc0beb7d1fb741f5c742ab420af4fe","abstract_canon_sha256":"2e232b2d2b4417e954f6d017cfa2920d1728646e281857b2f70a088dfdb96a86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:09.896789Z","signature_b64":"tg7dhmc1BkrCRDVUMJ6EYi66/CMr/BdnV4vbU+Ey2v3CnQwwzb2WZpwrQWsUch6vpyaZII1/zfRKUodO1FqADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1310ce6ffb955cf1ce5fdf4c068f4993574daeaeed574bc42e2a0c687867e8ac","last_reissued_at":"2026-07-05T09:39:09.896312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:09.896312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-performance automated abstract screening with large language model ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrew Soltan, Archie Watt, Arun James Thirunavukarasu, George Nishimura, Hamid Butt, Jessica O'Logbon, Marc El Khoury, Mustafa Mahmood, Rohan Sanghera, Yuqing Chen","submitted_at":"2024-11-03T10:06:14Z","abstract_excerpt":"Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 record"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02451","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/2411.02451/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":"2411.02451","created_at":"2026-07-05T09:39:09.896380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02451v2","created_at":"2026-07-05T09:39:09.896380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02451","created_at":"2026-07-05T09:39:09.896380+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMIM4373SVOP","created_at":"2026-07-05T09:39:09.896380+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMIM4373SVOPDTS7","created_at":"2026-07-05T09:39:09.896380+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMIM4373","created_at":"2026-07-05T09:39:09.896380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16255","citing_title":"A foundation model for human-AI collaboration in medical literature mining","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN","json":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN.json","graph_json":"https://pith.science/api/pith-number/CMIM4373SVOPDTS735GAND2JSN/graph.json","events_json":"https://pith.science/api/pith-number/CMIM4373SVOPDTS735GAND2JSN/events.json","paper":"https://pith.science/paper/CMIM4373"},"agent_actions":{"view_html":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN","download_json":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN.json","view_paper":"https://pith.science/paper/CMIM4373","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02451&json=true","fetch_graph":"https://pith.science/api/pith-number/CMIM4373SVOPDTS735GAND2JSN/graph.json","fetch_events":"https://pith.science/api/pith-number/CMIM4373SVOPDTS735GAND2JSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN/action/storage_attestation","attest_author":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN/action/author_attestation","sign_citation":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN/action/citation_signature","submit_replication":"https://pith.science/pith/CMIM4373SVOPDTS735GAND2JSN/action/replication_record"}},"created_at":"2026-07-05T09:39:09.896380+00:00","updated_at":"2026-07-05T09:39:09.896380+00:00"}