{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YHPZV5IXRF3GIHEWDFTPQWKAAB","short_pith_number":"pith:YHPZV5IX","schema_version":"1.0","canonical_sha256":"c1df9af5178976641c961966f8594000496af92ff9b0066c7067ad8d484a8e51","source":{"kind":"arxiv","id":"2411.04368","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.04368","created_at":"2026-05-17T23:38:53.221155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04368v1","created_at":"2026-05-17T23:38:53.221155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04368","created_at":"2026-05-17T23:38:53.221155+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHPZV5IXRF3G","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHPZV5IXRF3GIHEW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHPZV5IX","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":34,"internal_anchor_count":34,"sample":[{"citing_arxiv_id":"2506.10060","citing_title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2507.06261","citing_title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21267","citing_title":"Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2509.25868","citing_title":"ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07926","citing_title":"Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2511.02805","citing_title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2507.02592","citing_title":"WebSailor: Navigating Super-human Reasoning for Web Agent","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":98,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03847","citing_title":"DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2512.20182","citing_title":"FaithLens: Detecting and Explaining Faithfulness Hallucination","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2602.07892","citing_title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22480","citing_title":"VeRO: An Evaluation Harness for Agents to Optimize Agents","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04751","citing_title":"Evaluating the Search Agent in a Parallel World","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16091","citing_title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03216","citing_title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03044","citing_title":"JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2506.13585","citing_title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08942","citing_title":"Decomposing and Steering Functional Metacognition in Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10530","citing_title":"Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10401","citing_title":"NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06829","citing_title":"WRAP++: Web discoveRy Amplified Pretraining","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08519","citing_title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07153","citing_title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB","json":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB.json","graph_json":"https://pith.science/api/pith-number/YHPZV5IXRF3GIHEWDFTPQWKAAB/graph.json","events_json":"https://pith.science/api/pith-number/YHPZV5IXRF3GIHEWDFTPQWKAAB/events.json","paper":"https://pith.science/paper/YHPZV5IX"},"agent_actions":{"view_html":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB","download_json":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB.json","view_paper":"https://pith.science/paper/YHPZV5IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04368&json=true","fetch_graph":"https://pith.science/api/pith-number/YHPZV5IXRF3GIHEWDFTPQWKAAB/graph.json","fetch_events":"https://pith.science/api/pith-number/YHPZV5IXRF3GIHEWDFTPQWKAAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/action/storage_attestation","attest_author":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/action/author_attestation","sign_citation":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/action/citation_signature","submit_replication":"https://pith.science/pith/YHPZV5IXRF3GIHEWDFTPQWKAAB/action/replication_record"}},"created_at":"2026-05-17T23:38:53.221155+00:00","updated_at":"2026-05-17T23:38:53.221155+00:00"}