{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C6QJAJVXOQ4DFTKP2TIMOUTFLC","short_pith_number":"pith:C6QJAJVX","schema_version":"1.0","canonical_sha256":"17a09026b7743832cd4fd4d0c7526558b6d1db98c725947b351c8cc2ea82fe66","source":{"kind":"arxiv","id":"2308.06610","version":1},"attestation_state":"computed","paper":{"title":"Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdullah Pandor, Ambrose Robinson, Ben P. Wu, Mark Stevenson, Munira Essat, William Thorne, Xingyi Song","submitted_at":"2023-08-12T16:56:55Z","abstract_excerpt":"Medical systematic reviews can be very costly and resource intensive. We explore how Large Language Models (LLMs) can support and be trained to perform literature screening when provided with a detailed set of selection criteria. Specifically, we instruction tune LLaMA and Guanaco models to perform abstract screening for medical systematic reviews. Our best model, Bio-SIEVE, outperforms both ChatGPT and trained traditional approaches, and generalises better across medical domains. However, there remains the challenge of adapting the model to safety-first scenarios. We also explore the impact o"},"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":"2308.06610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-12T16:56:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a450dd288f58b41ae36360707a0632b0f3d95838288a183e4511e0f63a9dc9f","abstract_canon_sha256":"c19b226ee7e5b4e4c3def9a57900276987aec924ced23da897c7112676162514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:42.742657Z","signature_b64":"zlpzOohX7yPYliFxYKPyFmLxYXiRM82E81mp0BZ0bfJlNZmc3EcGlAeXiV43vwbUUqOr1HSdxs27KShDrXANCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a09026b7743832cd4fd4d0c7526558b6d1db98c725947b351c8cc2ea82fe66","last_reissued_at":"2026-07-05T06:40:42.742178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:42.742178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdullah Pandor, Ambrose Robinson, Ben P. Wu, Mark Stevenson, Munira Essat, William Thorne, Xingyi Song","submitted_at":"2023-08-12T16:56:55Z","abstract_excerpt":"Medical systematic reviews can be very costly and resource intensive. We explore how Large Language Models (LLMs) can support and be trained to perform literature screening when provided with a detailed set of selection criteria. Specifically, we instruction tune LLaMA and Guanaco models to perform abstract screening for medical systematic reviews. Our best model, Bio-SIEVE, outperforms both ChatGPT and trained traditional approaches, and generalises better across medical domains. However, there remains the challenge of adapting the model to safety-first scenarios. We also explore the impact o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06610","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/2308.06610/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":"2308.06610","created_at":"2026-07-05T06:40:42.742231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06610v1","created_at":"2026-07-05T06:40:42.742231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06610","created_at":"2026-07-05T06:40:42.742231+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6QJAJVXOQ4D","created_at":"2026-07-05T06:40:42.742231+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6QJAJVXOQ4DFTKP","created_at":"2026-07-05T06:40:42.742231+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6QJAJVX","created_at":"2026-07-05T06:40:42.742231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.12635","citing_title":"LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC","json":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC.json","graph_json":"https://pith.science/api/pith-number/C6QJAJVXOQ4DFTKP2TIMOUTFLC/graph.json","events_json":"https://pith.science/api/pith-number/C6QJAJVXOQ4DFTKP2TIMOUTFLC/events.json","paper":"https://pith.science/paper/C6QJAJVX"},"agent_actions":{"view_html":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC","download_json":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC.json","view_paper":"https://pith.science/paper/C6QJAJVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06610&json=true","fetch_graph":"https://pith.science/api/pith-number/C6QJAJVXOQ4DFTKP2TIMOUTFLC/graph.json","fetch_events":"https://pith.science/api/pith-number/C6QJAJVXOQ4DFTKP2TIMOUTFLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC/action/storage_attestation","attest_author":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC/action/author_attestation","sign_citation":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC/action/citation_signature","submit_replication":"https://pith.science/pith/C6QJAJVXOQ4DFTKP2TIMOUTFLC/action/replication_record"}},"created_at":"2026-07-05T06:40:42.742231+00:00","updated_at":"2026-07-05T06:40:42.742231+00:00"}