{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F7ILYJOQB4JOF6X5UDP5GEEQXR","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":"39da495eaa47bb90f67031876ba4539527bd03fef5c415304db25b7ae7afdc6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T10:40:55Z","title_canon_sha256":"974f158474d14fd0f306308e6c068231028f0e0eee78b716532d70bdab340aad"},"schema_version":"1.0","source":{"id":"2305.12421","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12421","created_at":"2026-07-05T07:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12421v4","created_at":"2026-07-05T07:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12421","created_at":"2026-07-05T07:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"F7ILYJOQB4JO","created_at":"2026-07-05T07:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"F7ILYJOQB4JOF6X5","created_at":"2026-07-05T07:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"F7ILYJOQ","created_at":"2026-07-05T07:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:24348a21b631e79b3d5ce7fb214869460ea3e37799697f4c605b357cd82b3ccd","target":"graph","created_at":"2026-07-05T07:03:58Z","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/2305.12421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs). Current automatic evaluation methods have shown limitations, indicating that human evaluation still remains the most reliable approach. We introduce a new task, Evaluating QA Evaluation (QA-Eval) and the corresponding dataset EVOUNA, designed to assess the accuracy of AI-generated answers in relation to standard answers within Open-QA. Our evaluation of these methods utilizes human-annotated results to measure their performance. Specifi","authors_text":"Bowen Ding, Cunxiang Wang, Qipeng Guo, Sirui Cheng, Xiangkun Hu, Yidong Wang, Yuanhao Yue, Yue Zhang, Zheng Zhang, Zhikun Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T10:40:55Z","title":"Evaluating Open-QA Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12421","kind":"arxiv","version":4},"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":"sha256:5cf05df44695e7c649fb6d7ee4b0be28e660c5a42dd55d792017f531baa2073e","target":"record","created_at":"2026-07-05T07:03:58Z","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":"39da495eaa47bb90f67031876ba4539527bd03fef5c415304db25b7ae7afdc6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T10:40:55Z","title_canon_sha256":"974f158474d14fd0f306308e6c068231028f0e0eee78b716532d70bdab340aad"},"schema_version":"1.0","source":{"id":"2305.12421","kind":"arxiv","version":4}},"canonical_sha256":"2fd0bc25d00f12e2fafda0dfd31090bc4d5056b9222368adb369f8a7e565e9ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd0bc25d00f12e2fafda0dfd31090bc4d5056b9222368adb369f8a7e565e9ad","first_computed_at":"2026-07-05T07:03:58.862869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:58.862869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bKzkkalxyeT+tscH/2e45VSmKXfZHA6iduMnOPGai0fALt9HsysprfFMV8DCeVRkt15L3dQtH69TRX5IOxi4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:58.863367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12421","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cf05df44695e7c649fb6d7ee4b0be28e660c5a42dd55d792017f531baa2073e","sha256:24348a21b631e79b3d5ce7fb214869460ea3e37799697f4c605b357cd82b3ccd"],"state_sha256":"e09dc2924a893365e169bad1b3a85a0132a12a90c8872101384d29158bd96b08"}