{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YHPZV5IXRF3GIHEWDFTPQWKAAB","short_pith_number":"pith:YHPZV5IX","canonical_record":{"source":{"id":"2411.04368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T01:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"fd6601c4ac8b2d44a8b49a1794e90a34cc658b1e7eb5e0afc3ec76cf8436e8e7","abstract_canon_sha256":"bc6590af27d293a121a6fce13fd12d46a8a316c7aaf3e54b2a59f21071aca0f6"},"schema_version":"1.0"},"canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","source":{"kind":"arxiv","id":"2411.04368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04368","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04368v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04368","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"YHPZV5IXRF3G","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YHPZV5IXRF3GIHEW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YHPZV5IX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YHPZV5IXRF3GIHEWDFTPQWKAAB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T01:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"fd6601c4ac8b2d44a8b49a1794e90a34cc658b1e7eb5e0afc3ec76cf8436e8e7","abstract_canon_sha256":"bc6590af27d293a121a6fce13fd12d46a8a316c7aaf3e54b2a59f21071aca0f6"},"schema_version":"1.0"},"canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.221849Z","signature_b64":"RQR+a7izzTEmWev//1SMSkC5ALx/z+h/+Z2dAfkDoZ5blI67eQdYelOa+9k5F6gmSWCt105yyJsL7/zkjaZ8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","last_reissued_at":"2026-05-17T23:38:53.221012Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.221012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04368","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSnpwFil97d8MpXEMNz+hUaw1NU+hEilYXZcZbhHTzJtUhGg3KY/5rvJhbP5whPOdvATDlQHbLQlhYogGL4FCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T12:57:53.516339Z"},"content_sha256":"0a41978458252d78db15a0fdc1597271be3c8af11fd93bb0d7e2efa1aedab0c9","schema_version":"1.0","event_id":"sha256:0a41978458252d78db15a0fdc1597271be3c8af11fd93bb0d7e2efa1aedab0c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YHPZV5IXRF3GIHEWDFTPQWKAAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring short-form factuality in large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SimpleQA benchmark measures if language models know what they know on short facts.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amelia Glaese, Hyung Won Chung, Jason Wei, John Schulman, Nguyen Karina, Spencer Papay, William Fedus, Yunxin Joy Jiao","submitted_at":"2024-11-07T01:58:42Z","abstract_excerpt":"We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is n"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SimpleQA is a simple, targeted evaluation for whether models 'know what they know,' and our hope is that this benchmark will remain relevant for the next few generations of frontier models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Questions can be created such that there exists only a single, indisputable answer and that adversarial collection against GPT-4 responses produces questions that remain challenging for future models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SimpleQA is a new benchmark of short, single-answer factual questions collected adversarially against GPT-4 to evaluate LLM factuality and confidence calibration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SimpleQA benchmark measures if language models know what they know on short facts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f90715c97f4bf0896a9b640e57e6cbc403e21e7ba9b86a45a790a8bd7c60c7fa"},"source":{"id":"2411.04368","kind":"arxiv","version":1},"verdict":{"id":"d603a5c1-f3a8-4bf9-81c8-f9976ebdcd58","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:41:33.689500Z","strongest_claim":"SimpleQA is a simple, targeted evaluation for whether models 'know what they know,' and our hope is that this benchmark will remain relevant for the next few generations of frontier models.","one_line_summary":"SimpleQA is a new benchmark of short, single-answer factual questions collected adversarially against GPT-4 to evaluate LLM factuality and confidence calibration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Questions can be created such that there exists only a single, indisputable answer and that adversarial collection against GPT-4 responses produces questions that remain challenging for future models.","pith_extraction_headline":"SimpleQA benchmark measures if language models know what they know on short facts."},"references":{"count":19,"sample":[{"doi":"","year":2024,"title":"org/abs/2305.18248","work_id":"9eeaa979-72cb-4989-b9c7-8b50900f3647","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"P. Anthropic. Claude 3 model card, 2024. URL https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf","work_id":"613d427d-70ca-468a-a12f-43da8b7df476","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In Proceedings of the 22nd international conference on Machine learning, pages 89–96","work_id":"27f57922-254f-4edb-9365-44ba354e34b2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","work_id":"f20e62ba-6265-4b97-aa8c-ddefaf2f5762","ref_index":4,"cited_arxiv_id":"1705.03551","is_internal_anchor":true},{"doi":"","year":2022,"title":"Language Models (Mostly) Know What They Know","work_id":"8ca58a10-da41-4f70-baae-7e449512e345","ref_index":5,"cited_arxiv_id":"2207.05221","is_internal_anchor":true}],"resolved_work":19,"snapshot_sha256":"a63a5b722d18f18394072fab950867951a3b3b95e5eb6d9f5d19859c8a0de3e0","internal_anchors":4},"formal_canon":{"evidence_count":3,"snapshot_sha256":"7f1c924b744a9cf07262c238dd2aaf290fe366799f332ffd18b4278061cdd1ce"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d603a5c1-f3a8-4bf9-81c8-f9976ebdcd58"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNikCHxRJb/F8ftYjBtD5n+X/cZtJ+Inz7the3ugZymDdQGOxjnfCts2HghDRTIIOW+00O2yco4IiZtp6oSJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T12:57:53.516941Z"},"content_sha256":"b7f6f81c7e90851199fa25eba8246160fabc36ec62931cc871cbf1c167ab75af","schema_version":"1.0","event_id":"sha256:b7f6f81c7e90851199fa25eba8246160fabc36ec62931cc871cbf1c167ab75af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/bundle.json","state_url":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/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":"2026-05-19T12:57:53Z","links":{"resolver":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB","bundle":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/bundle.json","state":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YHPZV5IXRF3GIHEWDFTPQWKAAB","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":"bc6590af27d293a121a6fce13fd12d46a8a316c7aaf3e54b2a59f21071aca0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T01:58:42Z","title_canon_sha256":"fd6601c4ac8b2d44a8b49a1794e90a34cc658b1e7eb5e0afc3ec76cf8436e8e7"},"schema_version":"1.0","source":{"id":"2411.04368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04368","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04368v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04368","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"YHPZV5IXRF3G","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YHPZV5IXRF3GIHEW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YHPZV5IX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b7f6f81c7e90851199fa25eba8246160fabc36ec62931cc871cbf1c167ab75af","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"SimpleQA is a simple, targeted evaluation for whether models 'know what they know,' and our hope is that this benchmark will remain relevant for the next few generations of frontier models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Questions can be created such that there exists only a single, indisputable answer and that adversarial collection against GPT-4 responses produces questions that remain challenging for future models."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SimpleQA is a new benchmark of short, single-answer factual questions collected adversarially against GPT-4 to evaluate LLM factuality and confidence calibration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SimpleQA benchmark measures if language models know what they know on short facts."}],"snapshot_sha256":"f90715c97f4bf0896a9b640e57e6cbc403e21e7ba9b86a45a790a8bd7c60c7fa"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"7f1c924b744a9cf07262c238dd2aaf290fe366799f332ffd18b4278061cdd1ce"},"paper":{"abstract_excerpt":"We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is n","authors_text":"Amelia Glaese, Hyung Won Chung, Jason Wei, John Schulman, Nguyen Karina, Spencer Papay, William Fedus, Yunxin Joy Jiao","cross_cats":[],"headline":"SimpleQA benchmark measures if language models know what they know on short facts.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T01:58:42Z","title":"Measuring short-form factuality in large language models"},"references":{"count":19,"internal_anchors":4,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"org/abs/2305.18248","work_id":"9eeaa979-72cb-4989-b9c7-8b50900f3647","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"P. Anthropic. Claude 3 model card, 2024. URL https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf","work_id":"613d427d-70ca-468a-a12f-43da8b7df476","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In Proceedings of the 22nd international conference on Machine learning, pages 89–96","work_id":"27f57922-254f-4edb-9365-44ba354e34b2","year":2023},{"cited_arxiv_id":"1705.03551","doi":"","is_internal_anchor":true,"ref_index":4,"title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","work_id":"f20e62ba-6265-4b97-aa8c-ddefaf2f5762","year":2017},{"cited_arxiv_id":"2207.05221","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Language Models (Mostly) Know What They Know","work_id":"8ca58a10-da41-4f70-baae-7e449512e345","year":2022}],"snapshot_sha256":"a63a5b722d18f18394072fab950867951a3b3b95e5eb6d9f5d19859c8a0de3e0"},"source":{"id":"2411.04368","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T06:41:33.689500Z","id":"d603a5c1-f3a8-4bf9-81c8-f9976ebdcd58","model_set":{"reader":"grok-4.3"},"one_line_summary":"SimpleQA is a new benchmark of short, single-answer factual questions collected adversarially against GPT-4 to evaluate LLM factuality and confidence calibration.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SimpleQA benchmark measures if language models know what they know on short facts.","strongest_claim":"SimpleQA is a simple, targeted evaluation for whether models 'know what they know,' and our hope is that this benchmark will remain relevant for the next few generations of frontier models.","weakest_assumption":"Questions can be created such that there exists only a single, indisputable answer and that adversarial collection against GPT-4 responses produces questions that remain challenging for future models."}},"verdict_id":"d603a5c1-f3a8-4bf9-81c8-f9976ebdcd58"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a41978458252d78db15a0fdc1597271be3c8af11fd93bb0d7e2efa1aedab0c9","target":"record","created_at":"2026-05-17T23:38:53Z","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":"bc6590af27d293a121a6fce13fd12d46a8a316c7aaf3e54b2a59f21071aca0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T01:58:42Z","title_canon_sha256":"fd6601c4ac8b2d44a8b49a1794e90a34cc658b1e7eb5e0afc3ec76cf8436e8e7"},"schema_version":"1.0","source":{"id":"2411.04368","kind":"arxiv","version":1}},"canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","first_computed_at":"2026-05-17T23:38:53.221012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.221012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RQR+a7izzTEmWev//1SMSkC5ALx/z+h/+Z2dAfkDoZ5blI67eQdYelOa+9k5F6gmSWCt105yyJsL7/zkjaZ8Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.221849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a41978458252d78db15a0fdc1597271be3c8af11fd93bb0d7e2efa1aedab0c9","sha256:b7f6f81c7e90851199fa25eba8246160fabc36ec62931cc871cbf1c167ab75af"],"state_sha256":"5811313e8d9eaaf71729c5b41dbfb8ec1e09d8c13037973eb326c378aa933d14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xT75msIH8PKaAkjvEDVF8p9IB/FuLGZoMkRPBHeoYHpGU/+AKn+tvJlR/UdkiFPefHVx3QmWOK+tU0fe1X8rDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T12:57:53.519240Z","bundle_sha256":"19f0e1846cde33184307de31eb4f3bf97fd0f31e078e46afbc8ca4326b3bccec"}}