{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3COJXHXTZ72QVBRBB2ZAUSRF6C","short_pith_number":"pith:3COJXHXT","schema_version":"1.0","canonical_sha256":"d89c9b9ef3cff50a86210eb20a4a25f0bdf03b065c18964b11f578c12645a565","source":{"kind":"arxiv","id":"2306.04757","version":3},"attestation_state":"computed","paper":{"title":"INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Pengfei Hong, Soujanya Poria, Yew Ken Chia","submitted_at":"2023-06-07T20:12:29Z","abstract_excerpt":"Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve complex tasks in areas like mathematics, coding, medicine, and law. Despite their impressive capabilities, there is still a lack of comprehensive understanding regarding their full potential, primarily due to the black-box nature of many models and the absence of holistic evaluation studies. To address these challenges, we present INSTRUCTEVAL, a more compreh"},"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":"2306.04757","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T20:12:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"321193fcbdba17e59b1dd632e2f9f536bc12649c83b5575bc08e14c9bbe838b0","abstract_canon_sha256":"6518abfadbf5294dec4dd6adc0367ed59074163901540d3792d572b852f45344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:44.916394Z","signature_b64":"XM+qUxAEqKHIL1NK5KFDdUqNOQNPbDQDEbg5U0H7xV64M1ZX84+dtggN3+N3AoChVPxWJb6nqwxSM9Jr8zp4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d89c9b9ef3cff50a86210eb20a4a25f0bdf03b065c18964b11f578c12645a565","last_reissued_at":"2026-07-05T06:20:44.915952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:44.915952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Pengfei Hong, Soujanya Poria, Yew Ken Chia","submitted_at":"2023-06-07T20:12:29Z","abstract_excerpt":"Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve complex tasks in areas like mathematics, coding, medicine, and law. Despite their impressive capabilities, there is still a lack of comprehensive understanding regarding their full potential, primarily due to the black-box nature of many models and the absence of holistic evaluation studies. To address these challenges, we present INSTRUCTEVAL, a more compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04757","kind":"arxiv","version":3},"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/2306.04757/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":"2306.04757","created_at":"2026-07-05T06:20:44.915999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04757v3","created_at":"2026-07-05T06:20:44.915999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04757","created_at":"2026-07-05T06:20:44.915999+00:00"},{"alias_kind":"pith_short_12","alias_value":"3COJXHXTZ72Q","created_at":"2026-07-05T06:20:44.915999+00:00"},{"alias_kind":"pith_short_16","alias_value":"3COJXHXTZ72QVBRB","created_at":"2026-07-05T06:20:44.915999+00:00"},{"alias_kind":"pith_short_8","alias_value":"3COJXHXT","created_at":"2026-07-05T06:20:44.915999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00093","citing_title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23262","citing_title":"Design and Report Benchmarks for Knowledge Work","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02385","citing_title":"TinyLlama: An Open-Source Small Language Model","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C","json":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C.json","graph_json":"https://pith.science/api/pith-number/3COJXHXTZ72QVBRBB2ZAUSRF6C/graph.json","events_json":"https://pith.science/api/pith-number/3COJXHXTZ72QVBRBB2ZAUSRF6C/events.json","paper":"https://pith.science/paper/3COJXHXT"},"agent_actions":{"view_html":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C","download_json":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C.json","view_paper":"https://pith.science/paper/3COJXHXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04757&json=true","fetch_graph":"https://pith.science/api/pith-number/3COJXHXTZ72QVBRBB2ZAUSRF6C/graph.json","fetch_events":"https://pith.science/api/pith-number/3COJXHXTZ72QVBRBB2ZAUSRF6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C/action/storage_attestation","attest_author":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C/action/author_attestation","sign_citation":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C/action/citation_signature","submit_replication":"https://pith.science/pith/3COJXHXTZ72QVBRBB2ZAUSRF6C/action/replication_record"}},"created_at":"2026-07-05T06:20:44.915999+00:00","updated_at":"2026-07-05T06:20:44.915999+00:00"}