{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A55ZKWT5SNWCURMK6FGQUT5EDJ","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":"809dfc271b70806fcb63a0ace541e3f868f550a128d1d11b7e8f2aef16f8f4f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-22T15:58:17Z","title_canon_sha256":"90abaeab4c8bbdff996dec30dedf1e523f054064522a6590b6a837186c4516c2"},"schema_version":"1.0","source":{"id":"2307.12114","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12114","created_at":"2026-07-05T08:29:16Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12114v3","created_at":"2026-07-05T08:29:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12114","created_at":"2026-07-05T08:29:16Z"},{"alias_kind":"pith_short_12","alias_value":"A55ZKWT5SNWC","created_at":"2026-07-05T08:29:16Z"},{"alias_kind":"pith_short_16","alias_value":"A55ZKWT5SNWCURMK","created_at":"2026-07-05T08:29:16Z"},{"alias_kind":"pith_short_8","alias_value":"A55ZKWT5","created_at":"2026-07-05T08:29:16Z"}],"graph_snapshots":[{"event_id":"sha256:46c41da3bad7b2e9ba5ba56923157695cd3f338ca7d82a42b98ba5695261cca9","target":"graph","created_at":"2026-07-05T08:29:16Z","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/2307.12114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate four state-of-the-art instruction-tuned large language models (LLMs) -- ChatGPT, Flan-T5 UL2, Tk-Instruct, and Alpaca -- on a set of 13 real-world clinical and biomedical natural language processing (NLP) tasks in English, such as named-entity recognition (NER), question-answering (QA), relation extraction (RE), etc. Our overall results demonstrate that the evaluated LLMs begin to approach performance of state-of-the-art models in zero- and few-shot scenarios for most tasks, and particularly well for the QA task, even though they have never seen examples from these tasks before. Ho","authors_text":"Mickael Rouvier, Richard Dufour, Yanis Labrak","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-22T15:58:17Z","title":"A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12114","kind":"arxiv","version":3},"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:bd817d1b1a6f1e7c547a2d348750d32999c905f3aefad8dd377b5466cd99dafd","target":"record","created_at":"2026-07-05T08:29:16Z","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":"809dfc271b70806fcb63a0ace541e3f868f550a128d1d11b7e8f2aef16f8f4f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-22T15:58:17Z","title_canon_sha256":"90abaeab4c8bbdff996dec30dedf1e523f054064522a6590b6a837186c4516c2"},"schema_version":"1.0","source":{"id":"2307.12114","kind":"arxiv","version":3}},"canonical_sha256":"077b955a7d936c2a458af14d0a4fa41a6be131c6aee51e400024b09cd25e20e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077b955a7d936c2a458af14d0a4fa41a6be131c6aee51e400024b09cd25e20e2","first_computed_at":"2026-07-05T08:29:16.580053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:16.580053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fnlD8LTdLxKV2VzBrqm32O9Tzayiz1erc9VjaV8aHCbzr/FCO+B13spsKQCg+ORJ34Hc4l4FlJjD9R5AVWZTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:16.580600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12114","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd817d1b1a6f1e7c547a2d348750d32999c905f3aefad8dd377b5466cd99dafd","sha256:46c41da3bad7b2e9ba5ba56923157695cd3f338ca7d82a42b98ba5695261cca9"],"state_sha256":"e22678fe4a388d3cc70ac9d5e9b418a3c175119e600e836458e05601f86a5f26"}