{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K5US7TYMP5PXOY4N3ITVUD62GY","short_pith_number":"pith:K5US7TYM","canonical_record":{"source":{"id":"2311.14966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T08:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"a1fc6d186442753d35dcf9e88640f3b69e17efe6be54eedcca5302ecf0a13316","abstract_canon_sha256":"122694d1b1c5b1aa95693cb86183fd18b1169832a755acfef53efe6d14ddadbf"},"schema_version":"1.0"},"canonical_sha256":"57692fcf0c7f5f77638dda275a0fda36151f2086dfa7fd7fd88bdc4d8bc99c43","source":{"kind":"arxiv","id":"2311.14966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14966","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14966v1","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14966","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"K5US7TYMP5PX","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"K5US7TYMP5PXOY4N","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"K5US7TYM","created_at":"2026-07-05T07:16:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K5US7TYMP5PXOY4N3ITVUD62GY","target":"record","payload":{"canonical_record":{"source":{"id":"2311.14966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T08:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"a1fc6d186442753d35dcf9e88640f3b69e17efe6be54eedcca5302ecf0a13316","abstract_canon_sha256":"122694d1b1c5b1aa95693cb86183fd18b1169832a755acfef53efe6d14ddadbf"},"schema_version":"1.0"},"canonical_sha256":"57692fcf0c7f5f77638dda275a0fda36151f2086dfa7fd7fd88bdc4d8bc99c43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:56.570458Z","signature_b64":"8a8EpbNuV0ZR5Nr0tFmPenCYSMVkNa16kLfz50vzlU+TrkE+/0oFP6XhDOPKnrVonzygm/zfZJjufsDe4YdYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57692fcf0c7f5f77638dda275a0fda36151f2086dfa7fd7fd88bdc4d8bc99c43","last_reissued_at":"2026-07-05T07:16:56.569856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:56.569856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.14966","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUBlr+6HJUT25n7wMFYn31yHwkewCXomUXWNDBMpQbNtIo+oLdXRhg9ZACRXskG7Ot/vGGBNmfpj0I+h7tdfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:18:17.529915Z"},"content_sha256":"44c5500a5858ffa53ac55b49c8a28d7cec612ab8d1cd07bc5ddfbf1944f8b813","schema_version":"1.0","event_id":"sha256:44c5500a5858ffa53ac55b49c8a28d7cec612ab8d1cd07bc5ddfbf1944f8b813"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K5US7TYMP5PXOY4N3ITVUD62GY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Chia-Chien Hung, Lars Bruckner, Lindsay Frost, Wiem Ben Rim","submitted_at":"2023-11-25T08:58:07Z","abstract_excerpt":"High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14966","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/2311.14966/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHcKnsvIQI7SimdPE4tV8Dnuwqf5B1loDNL86OBSYsATGHYHWVFrkK5dSfMUE4cbqMUbNt/bqibzZbNbTtw7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:18:17.530408Z"},"content_sha256":"d8df95c688c490fc62bd539c98b0a5ae7cc1431298f6e81d459a33e0189c90b0","schema_version":"1.0","event_id":"sha256:d8df95c688c490fc62bd539c98b0a5ae7cc1431298f6e81d459a33e0189c90b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5US7TYMP5PXOY4N3ITVUD62GY/bundle.json","state_url":"https://pith.science/pith/K5US7TYMP5PXOY4N3ITVUD62GY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5US7TYMP5PXOY4N3ITVUD62GY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T02:18:17Z","links":{"resolver":"https://pith.science/pith/K5US7TYMP5PXOY4N3ITVUD62GY","bundle":"https://pith.science/pith/K5US7TYMP5PXOY4N3ITVUD62GY/bundle.json","state":"https://pith.science/pith/K5US7TYMP5PXOY4N3ITVUD62GY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5US7TYMP5PXOY4N3ITVUD62GY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K5US7TYMP5PXOY4N3ITVUD62GY","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":"122694d1b1c5b1aa95693cb86183fd18b1169832a755acfef53efe6d14ddadbf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T08:58:07Z","title_canon_sha256":"a1fc6d186442753d35dcf9e88640f3b69e17efe6be54eedcca5302ecf0a13316"},"schema_version":"1.0","source":{"id":"2311.14966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14966","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14966v1","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14966","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"K5US7TYMP5PX","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"K5US7TYMP5PXOY4N","created_at":"2026-07-05T07:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"K5US7TYM","created_at":"2026-07-05T07:16:56Z"}],"graph_snapshots":[{"event_id":"sha256:d8df95c688c490fc62bd539c98b0a5ae7cc1431298f6e81d459a33e0189c90b0","target":"graph","created_at":"2026-07-05T07:16:56Z","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/2311.14966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Furt","authors_text":"Carolin Lawrence, Chia-Chien Hung, Lars Bruckner, Lindsay Frost, Wiem Ben Rim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T08:58:07Z","title":"Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14966","kind":"arxiv","version":1},"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":"sha256:44c5500a5858ffa53ac55b49c8a28d7cec612ab8d1cd07bc5ddfbf1944f8b813","target":"record","created_at":"2026-07-05T07:16:56Z","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":"122694d1b1c5b1aa95693cb86183fd18b1169832a755acfef53efe6d14ddadbf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T08:58:07Z","title_canon_sha256":"a1fc6d186442753d35dcf9e88640f3b69e17efe6be54eedcca5302ecf0a13316"},"schema_version":"1.0","source":{"id":"2311.14966","kind":"arxiv","version":1}},"canonical_sha256":"57692fcf0c7f5f77638dda275a0fda36151f2086dfa7fd7fd88bdc4d8bc99c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57692fcf0c7f5f77638dda275a0fda36151f2086dfa7fd7fd88bdc4d8bc99c43","first_computed_at":"2026-07-05T07:16:56.569856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:56.569856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8a8EpbNuV0ZR5Nr0tFmPenCYSMVkNa16kLfz50vzlU+TrkE+/0oFP6XhDOPKnrVonzygm/zfZJjufsDe4YdYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:56.570458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c5500a5858ffa53ac55b49c8a28d7cec612ab8d1cd07bc5ddfbf1944f8b813","sha256:d8df95c688c490fc62bd539c98b0a5ae7cc1431298f6e81d459a33e0189c90b0"],"state_sha256":"40a895a7a02b8929a643976a30faf794ca3395c6b91f55c56e4b7a40b79d2c62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5ZPeAd6N3PT6pnCh0DTuFJ2WyDhUSSzz621XHXtxeaoArPGr9lJf2Eq/IHGHLoXhKU4YE7PTAVWQZy0XxPHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:18:17.534703Z","bundle_sha256":"c1791d8d9e5b2e9de2595938df1aa3d890e64b0c37e9a2e76efa4aa0cb221d73"}}