{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUI24YX2L2Q7UTW4UP5HOEYPTI","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":"1f2a3ff4dd8ac097827e25482702f22496994b29f2a7e57fbf05c7c02c6e1bcf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T09:37:40Z","title_canon_sha256":"bbd923eda0e07ec74a4548d1da69014b237399b6d1a2741a2b0b35330b3d27b2"},"schema_version":"1.0","source":{"id":"2408.12249","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12249","created_at":"2026-07-05T11:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12249v2","created_at":"2026-07-05T11:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12249","created_at":"2026-07-05T11:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"BUI24YX2L2Q7","created_at":"2026-07-05T11:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"BUI24YX2L2Q7UTW4","created_at":"2026-07-05T11:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"BUI24YX2","created_at":"2026-07-05T11:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:9bb3c53a5cad609d845fad2331018fc6bfca7a04dc11cb000939843f9ebb3b4b","target":"graph","created_at":"2026-07-05T11:04:39Z","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/2408.12249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly adopted for applications in healthcare, reaching the performance of domain experts on tasks such as question answering and document summarisation. Despite their success on these tasks, it is unclear how well LLMs perform on tasks that are traditionally pursued in the biomedical domain, such as structured information extraction. To bridge this gap, in this paper, we systematically benchmark LLM performance in Medical Classification and Named Entity Recognition (NER) tasks. We aim to disentangle the contribution of different factors to the performanc","authors_text":"Aishik Nagar, Hao Li, Kuluhan Binici, Stefan Winkler, Thanh-Tung Nguyen, Viktor Schlegel, Yuping Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T09:37:40Z","title":"LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12249","kind":"arxiv","version":2},"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":"sha256:00b8c564704e4441bebc4de0a73d896acdb17a246b0bc1049cb0873ce5f711c0","target":"record","created_at":"2026-07-05T11:04:39Z","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":"1f2a3ff4dd8ac097827e25482702f22496994b29f2a7e57fbf05c7c02c6e1bcf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T09:37:40Z","title_canon_sha256":"bbd923eda0e07ec74a4548d1da69014b237399b6d1a2741a2b0b35330b3d27b2"},"schema_version":"1.0","source":{"id":"2408.12249","kind":"arxiv","version":2}},"canonical_sha256":"0d11ae62fa5ea1fa4edca3fa77130f9a2978702c3a097f21d0ae69db58c69c8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d11ae62fa5ea1fa4edca3fa77130f9a2978702c3a097f21d0ae69db58c69c8f","first_computed_at":"2026-07-05T11:04:39.163156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:39.163156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YRmSQMk5jDVF4zUKqnTdtsvSgX3UthFETJhIl5E4wc2vMaCoHHjZWFGpytyy3mIR3JOSt25IyWoVqsvT/aSrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:39.163609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12249","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00b8c564704e4441bebc4de0a73d896acdb17a246b0bc1049cb0873ce5f711c0","sha256:9bb3c53a5cad609d845fad2331018fc6bfca7a04dc11cb000939843f9ebb3b4b"],"state_sha256":"396fb3083b99f30150df1521e1f90635927dddfbb34d842bfa406db01a765404"}