{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7LIH3W5CXQXN44CWRAS6KHSR6H","short_pith_number":"pith:7LIH3W5C","canonical_record":{"source":{"id":"2305.14688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:51:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4937b2d836c219b9fe9dc71e91b18459cdbaf6096368ac5320d5b2452aece9d","abstract_canon_sha256":"d8e3be20a35b46970eac602951f6858bc13e66d0646d80b5183f4853d7f2c0e7"},"schema_version":"1.0"},"canonical_sha256":"fad07ddba2bc2ede70568825e51e51f1dbb6f910293245060ed6ad3de259f0f0","source":{"kind":"arxiv","id":"2305.14688","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14688","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14688v2","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14688","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"7LIH3W5CXQXN","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"7LIH3W5CXQXN44CW","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"7LIH3W5C","created_at":"2026-07-05T10:24:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7LIH3W5CXQXN44CWRAS6KHSR6H","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:51:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4937b2d836c219b9fe9dc71e91b18459cdbaf6096368ac5320d5b2452aece9d","abstract_canon_sha256":"d8e3be20a35b46970eac602951f6858bc13e66d0646d80b5183f4853d7f2c0e7"},"schema_version":"1.0"},"canonical_sha256":"fad07ddba2bc2ede70568825e51e51f1dbb6f910293245060ed6ad3de259f0f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:17.659839Z","signature_b64":"b5RukWlGRKJylGKE45dnoEErhIgKYe1jxY4z34tNS5JVdFSEt06ax/9d6haoLbcjWuZL5S0U5VwoSu9mPjlRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad07ddba2bc2ede70568825e51e51f1dbb6f910293245060ed6ad3de259f0f0","last_reissued_at":"2026-07-05T10:24:17.659414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:17.659414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14688","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:24:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bK71SFpwggLRQJlP+V6B8aXs4YZvM4mp5GH7ards4H/8NUabagSumxlw2z0TJYKtfgKH/L+9p+MibM5WpwA7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:17:01.804051Z"},"content_sha256":"96ed2434f892de26ef9b6b98365897a10fc6dd582d8b2ee6fc81fc70af504c8a","schema_version":"1.0","event_id":"sha256:96ed2434f892de26ef9b6b98365897a10fc6dd582d8b2ee6fc81fc70af504c8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7LIH3W5CXQXN44CWRAS6KHSR6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Yang, Benfeng Xu, Chang Zhou, Junyang Lin, Quan Wang, Yongdong Zhang, Zhendong Mao","submitted_at":"2023-05-24T03:51:31Z","abstract_excerpt":"The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts. In this paper, we propose ExpertPrompting to elicit the potential of LLMs to answer as distinguished experts. We first utilize In-Context Learning to automatically synthesize detailed and customized descriptions of the expert identity for each specific instruction, and then ask LLMs to provide answer conditioned on such agent background. Based on this augmented prompting strategy, we produce a new set of instruction-following data using GPT-3.5, and train a com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14688","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/2305.14688/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":"2026-07-05T10:24:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6lLVdAMrqB2HLY+Ankoi5ZVGA2wF2j7pZf1NEfkewRiY0kZGtYisBTDU8AQvzxB32N1oysv+QWMHew7pSahAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:17:01.804389Z"},"content_sha256":"709fd0aafc8d77d683b78b55d0c3bb8bb7466dcbdfec9a7d5b4b8a44988e1bba","schema_version":"1.0","event_id":"sha256:709fd0aafc8d77d683b78b55d0c3bb8bb7466dcbdfec9a7d5b4b8a44988e1bba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/bundle.json","state_url":"https://pith.science/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/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":"2026-08-04T16:17:01Z","links":{"resolver":"https://pith.science/pith/7LIH3W5CXQXN44CWRAS6KHSR6H","bundle":"https://pith.science/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/bundle.json","state":"https://pith.science/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LIH3W5CXQXN44CWRAS6KHSR6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7LIH3W5CXQXN44CWRAS6KHSR6H","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":"d8e3be20a35b46970eac602951f6858bc13e66d0646d80b5183f4853d7f2c0e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:51:31Z","title_canon_sha256":"d4937b2d836c219b9fe9dc71e91b18459cdbaf6096368ac5320d5b2452aece9d"},"schema_version":"1.0","source":{"id":"2305.14688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14688","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14688v2","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14688","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"7LIH3W5CXQXN","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"7LIH3W5CXQXN44CW","created_at":"2026-07-05T10:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"7LIH3W5C","created_at":"2026-07-05T10:24:17Z"}],"graph_snapshots":[{"event_id":"sha256:709fd0aafc8d77d683b78b55d0c3bb8bb7466dcbdfec9a7d5b4b8a44988e1bba","target":"graph","created_at":"2026-07-05T10:24:17Z","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/2305.14688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts. In this paper, we propose ExpertPrompting to elicit the potential of LLMs to answer as distinguished experts. We first utilize In-Context Learning to automatically synthesize detailed and customized descriptions of the expert identity for each specific instruction, and then ask LLMs to provide answer conditioned on such agent background. Based on this augmented prompting strategy, we produce a new set of instruction-following data using GPT-3.5, and train a com","authors_text":"An Yang, Benfeng Xu, Chang Zhou, Junyang Lin, Quan Wang, Yongdong Zhang, Zhendong Mao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:51:31Z","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14688","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":"sha256:96ed2434f892de26ef9b6b98365897a10fc6dd582d8b2ee6fc81fc70af504c8a","target":"record","created_at":"2026-07-05T10:24:17Z","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":"d8e3be20a35b46970eac602951f6858bc13e66d0646d80b5183f4853d7f2c0e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:51:31Z","title_canon_sha256":"d4937b2d836c219b9fe9dc71e91b18459cdbaf6096368ac5320d5b2452aece9d"},"schema_version":"1.0","source":{"id":"2305.14688","kind":"arxiv","version":2}},"canonical_sha256":"fad07ddba2bc2ede70568825e51e51f1dbb6f910293245060ed6ad3de259f0f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fad07ddba2bc2ede70568825e51e51f1dbb6f910293245060ed6ad3de259f0f0","first_computed_at":"2026-07-05T10:24:17.659414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:17.659414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5RukWlGRKJylGKE45dnoEErhIgKYe1jxY4z34tNS5JVdFSEt06ax/9d6haoLbcjWuZL5S0U5VwoSu9mPjlRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:17.659839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96ed2434f892de26ef9b6b98365897a10fc6dd582d8b2ee6fc81fc70af504c8a","sha256:709fd0aafc8d77d683b78b55d0c3bb8bb7466dcbdfec9a7d5b4b8a44988e1bba"],"state_sha256":"fa861c84b9cf90ea2b62590450f7cf24a6c80af0f7d3ef8e27b97c0e9c8e7c80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQt4icMUsz7/Jd974Ox9mCrhJE04+a0TYR66mjddcMYH2acwDX80M+nmamMSmM+rPpRa0IYg5dYjC009draWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:17:01.807917Z","bundle_sha256":"c5a61319a4c7ac60cfb00f8bf3a79a6be3a8f729c3a15f6b507e26d48575ba54"}}