{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MDZM7PSWD32LWPINYCQCA2KJR5","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":"9a6485e80bd97193bf30259a245f3e735ea9669534f1d77987afe8903ff6b2f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T17:59:48Z","title_canon_sha256":"a76e6957834d439f8372888c17579c6e6b41b4070c7b5a00a024f47e52cf0d3d"},"schema_version":"1.0","source":{"id":"2403.07872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07872","created_at":"2026-07-05T07:55:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07872v1","created_at":"2026-07-05T07:55:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07872","created_at":"2026-07-05T07:55:16Z"},{"alias_kind":"pith_short_12","alias_value":"MDZM7PSWD32L","created_at":"2026-07-05T07:55:16Z"},{"alias_kind":"pith_short_16","alias_value":"MDZM7PSWD32LWPIN","created_at":"2026-07-05T07:55:16Z"},{"alias_kind":"pith_short_8","alias_value":"MDZM7PSW","created_at":"2026-07-05T07:55:16Z"}],"graph_snapshots":[{"event_id":"sha256:ceb105f6e449a7f9e1f737b7b2c1e6da2f89f308a9b3ecff2405aab0efa92cb2","target":"graph","created_at":"2026-07-05T07:55:16Z","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/2403.07872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. Through a comprehensive evaluation of 24 models across 11 benchmarks, we highlight several potential drawbacks of MCQA, for instance, the inconsistency between the MCQA evaluation and the generation of open-ended responses in practical scenarios. In response, we introduce an RWQ-Elo rating system, engaging 24 LLMs such as","authors_text":"Fangyun Wei, Lin Luo, Xi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T17:59:48Z","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07872","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:e5ec0d7028acbf5d4cab7178fd30e97567429976ceed6ca37a06ae781ad21d9e","target":"record","created_at":"2026-07-05T07:55:16Z","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":"9a6485e80bd97193bf30259a245f3e735ea9669534f1d77987afe8903ff6b2f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T17:59:48Z","title_canon_sha256":"a76e6957834d439f8372888c17579c6e6b41b4070c7b5a00a024f47e52cf0d3d"},"schema_version":"1.0","source":{"id":"2403.07872","kind":"arxiv","version":1}},"canonical_sha256":"60f2cfbe561ef4bb3d0dc0a02069498f637109a14c4395934e60410992247e72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60f2cfbe561ef4bb3d0dc0a02069498f637109a14c4395934e60410992247e72","first_computed_at":"2026-07-05T07:55:16.710763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:16.710763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aVgyQ6dK0XktSrRuk6T2qZ6BnxMsz6jbFyte6iWOXnoZq6anGL74FbQXiZMMxd0o1Jay8ISvaEkkBkNhWfnuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:16.711217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5ec0d7028acbf5d4cab7178fd30e97567429976ceed6ca37a06ae781ad21d9e","sha256:ceb105f6e449a7f9e1f737b7b2c1e6da2f89f308a9b3ecff2405aab0efa92cb2"],"state_sha256":"af19fa27039a1e4b19329aec6afdcfe119af83156aba5002a56754b2bc3e11a8"}