{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3COJXHXTZ72QVBRBB2ZAUSRF6C","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":"6518abfadbf5294dec4dd6adc0367ed59074163901540d3792d572b852f45344","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T20:12:29Z","title_canon_sha256":"321193fcbdba17e59b1dd632e2f9f536bc12649c83b5575bc08e14c9bbe838b0"},"schema_version":"1.0","source":{"id":"2306.04757","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04757","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04757v3","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04757","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"3COJXHXTZ72Q","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"3COJXHXTZ72QVBRB","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"3COJXHXT","created_at":"2026-07-05T06:20:44Z"}],"graph_snapshots":[{"event_id":"sha256:ff4f8ebf164004ac4b3db119d04867ab034abd98bd02b2c1ab4f3c5ec8728877","target":"graph","created_at":"2026-07-05T06:20:44Z","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/2306.04757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lidong Bing, Pengfei Hong, Soujanya Poria, Yew Ken Chia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T20:12:29Z","title":"INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04757","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:ae4f1603aa2919234c797ee56648ffcadf158fc9a305c6e1f50b9ee8e054e212","target":"record","created_at":"2026-07-05T06:20:44Z","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":"6518abfadbf5294dec4dd6adc0367ed59074163901540d3792d572b852f45344","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T20:12:29Z","title_canon_sha256":"321193fcbdba17e59b1dd632e2f9f536bc12649c83b5575bc08e14c9bbe838b0"},"schema_version":"1.0","source":{"id":"2306.04757","kind":"arxiv","version":3}},"canonical_sha256":"d89c9b9ef3cff50a86210eb20a4a25f0bdf03b065c18964b11f578c12645a565","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d89c9b9ef3cff50a86210eb20a4a25f0bdf03b065c18964b11f578c12645a565","first_computed_at":"2026-07-05T06:20:44.915952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:44.915952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XM+qUxAEqKHIL1NK5KFDdUqNOQNPbDQDEbg5U0H7xV64M1ZX84+dtggN3+N3AoChVPxWJb6nqwxSM9Jr8zp4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:44.916394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04757","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae4f1603aa2919234c797ee56648ffcadf158fc9a305c6e1f50b9ee8e054e212","sha256:ff4f8ebf164004ac4b3db119d04867ab034abd98bd02b2c1ab4f3c5ec8728877"],"state_sha256":"257d83c7321f40486c6d6fe47b1b092a9883800548449faed102f7c7c79f0055"}