{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P6QRWCKKEZFVIRYIDZLZ7G42BP","short_pith_number":"pith:P6QRWCKK","canonical_record":{"source":{"id":"2403.17752","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T14:43:48Z","cross_cats_sorted":[],"title_canon_sha256":"8d2fd7c2b91ac483de2db6a460788e147d4d7278e37ea9cd02a59dd3603ad57d","abstract_canon_sha256":"b219455e0836f25a898f42ebea357894705038076a0e624e8a43dabf30a4f1f0"},"schema_version":"1.0"},"canonical_sha256":"7fa11b094a264b5447081e579f9b9a0bfa4f6f69d4107595e13b1009b930fbae","source":{"kind":"arxiv","id":"2403.17752","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17752","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17752v3","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17752","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"P6QRWCKKEZFV","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"P6QRWCKKEZFVIRYI","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"P6QRWCKK","created_at":"2026-07-05T08:22:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P6QRWCKKEZFVIRYIDZLZ7G42BP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.17752","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T14:43:48Z","cross_cats_sorted":[],"title_canon_sha256":"8d2fd7c2b91ac483de2db6a460788e147d4d7278e37ea9cd02a59dd3603ad57d","abstract_canon_sha256":"b219455e0836f25a898f42ebea357894705038076a0e624e8a43dabf30a4f1f0"},"schema_version":"1.0"},"canonical_sha256":"7fa11b094a264b5447081e579f9b9a0bfa4f6f69d4107595e13b1009b930fbae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:22.747603Z","signature_b64":"74LPiYRL5hjkpAaRQOUH/5j9Lsres08JPz9pw9k7y0B8ROzH0KHRoovxAaowb3bGK4ppsQkpKVJiyPQt4lIuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa11b094a264b5447081e579f9b9a0bfa4f6f69d4107595e13b1009b930fbae","last_reissued_at":"2026-07-05T08:22:22.747115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:22.747115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.17752","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAmC5pyEyMLNsrUEJ1XTfdxCXxex0MFIc2t3ToKjQXBhSgOqX0QssoW9kQIuyXEFCEnvtuw4dUItHroBr+xmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:40.141789Z"},"content_sha256":"b7dd6a267a3ae5de90db7b486ce5051864412baafaae767bf727a29a83922119","schema_version":"1.0","event_id":"sha256:b7dd6a267a3ae5de90db7b486ce5051864412baafaae767bf727a29a83922119"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P6QRWCKKEZFVIRYIDZLZ7G42BP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liangzhi Li, Noa Garcia, Tong Xiang, Wangyue Li, Wei Deng, Xiao Liu","submitted_at":"2024-03-26T14:43:48Z","abstract_excerpt":"Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM's capabilities, particularly in knowledge-intensive scenarios where long-form generation (LFG) answers are required. The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ's efficacy, which we undertake in this paper by evaluating nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English. We identify a significant iss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17752","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/2403.17752/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":"2026-07-05T08:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B+1d576S6w1HTSaYKOa7jigNHAQM/Yr8bwVVMUH3Vt8gzJtOoZ9l8cp97TzMZhk9zPXGjRdmYLUuVA/2+QXSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:40.142292Z"},"content_sha256":"340e2cb846f7a95d07dd05757595598a8c980d98ec3053e0d5505aa85a86cda3","schema_version":"1.0","event_id":"sha256:340e2cb846f7a95d07dd05757595598a8c980d98ec3053e0d5505aa85a86cda3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/bundle.json","state_url":"https://pith.science/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/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":"2026-08-09T04:56:40Z","links":{"resolver":"https://pith.science/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP","bundle":"https://pith.science/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/bundle.json","state":"https://pith.science/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6QRWCKKEZFVIRYIDZLZ7G42BP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P6QRWCKKEZFVIRYIDZLZ7G42BP","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":"b219455e0836f25a898f42ebea357894705038076a0e624e8a43dabf30a4f1f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T14:43:48Z","title_canon_sha256":"8d2fd7c2b91ac483de2db6a460788e147d4d7278e37ea9cd02a59dd3603ad57d"},"schema_version":"1.0","source":{"id":"2403.17752","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17752","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17752v3","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17752","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"P6QRWCKKEZFV","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"P6QRWCKKEZFVIRYI","created_at":"2026-07-05T08:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"P6QRWCKK","created_at":"2026-07-05T08:22:22Z"}],"graph_snapshots":[{"event_id":"sha256:340e2cb846f7a95d07dd05757595598a8c980d98ec3053e0d5505aa85a86cda3","target":"graph","created_at":"2026-07-05T08:22:22Z","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/2403.17752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM's capabilities, particularly in knowledge-intensive scenarios where long-form generation (LFG) answers are required. The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ's efficacy, which we undertake in this paper by evaluating nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English. We identify a significant iss","authors_text":"Liangzhi Li, Noa Garcia, Tong Xiang, Wangyue Li, Wei Deng, Xiao Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T14:43:48Z","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17752","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:b7dd6a267a3ae5de90db7b486ce5051864412baafaae767bf727a29a83922119","target":"record","created_at":"2026-07-05T08:22:22Z","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":"b219455e0836f25a898f42ebea357894705038076a0e624e8a43dabf30a4f1f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T14:43:48Z","title_canon_sha256":"8d2fd7c2b91ac483de2db6a460788e147d4d7278e37ea9cd02a59dd3603ad57d"},"schema_version":"1.0","source":{"id":"2403.17752","kind":"arxiv","version":3}},"canonical_sha256":"7fa11b094a264b5447081e579f9b9a0bfa4f6f69d4107595e13b1009b930fbae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fa11b094a264b5447081e579f9b9a0bfa4f6f69d4107595e13b1009b930fbae","first_computed_at":"2026-07-05T08:22:22.747115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:22.747115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"74LPiYRL5hjkpAaRQOUH/5j9Lsres08JPz9pw9k7y0B8ROzH0KHRoovxAaowb3bGK4ppsQkpKVJiyPQt4lIuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:22.747603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17752","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7dd6a267a3ae5de90db7b486ce5051864412baafaae767bf727a29a83922119","sha256:340e2cb846f7a95d07dd05757595598a8c980d98ec3053e0d5505aa85a86cda3"],"state_sha256":"d08d7d3ce3d407b2167cee62c283c407784e0631f5c5f9c67512995dcc94c317"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYuozASNMj2BtL2rLX8LIEzJWpHkXTEBXmr9yuX7tGgwu0WVnMdaycXouDueUlrdczy/avR10TSOuLQxxZ70Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:56:40.145656Z","bundle_sha256":"97c079a7e599903001918b20551033fad3034133e3fc53cec4bb8e5475bf392a"}}