{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"papers-with-code-truthfulqa","slug":"truthfulqa","name":"TruthfulQA","type":"dataset","url":"https://paperswithcode.com/dataset/truthfulqa","page_url":"https://unfragile.ai/truthfulqa","categories":["testing-quality"],"tags":["benchmark","evaluation","truthfulness","hallucination"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"papers-with-code-truthfulqa__cap_0","uri":"capability://data.processing.analysis.factuality.evaluation.through.misconception.testing","name":"factuality evaluation through misconception testing","description":"TruthfulQA evaluates the factual accuracy of model responses by presenting a set of 817 questions designed to challenge common misconceptions. Each question is crafted to require a truthful answer that contradicts widely held false beliefs, allowing for a clear assessment of a model's ability to discern truth from falsehood. This benchmark employs a systematic approach to categorize responses, identifying models that 'hallucinate' or provide incorrect answers despite sounding confident.","intents":["How can I test my AI model for factual accuracy against common misconceptions?","What benchmark can I use to evaluate the truthfulness of my language model?","I need to identify if my model is prone to hallucinations when answering factual questions."],"best_for":["AI researchers developing models focused on factual accuracy","developers evaluating the truthfulness of conversational agents"],"limitations":["Limited to 817 specific questions, which may not cover all areas of knowledge","Does not provide real-time feedback on model performance"],"requires":["Python 3.7+","Access to the TruthfulQA dataset"],"input_types":["text"],"output_types":["structured data"],"categories":["data-processing-analysis","evaluation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":49,"verified":false,"data_access_risk":"low","permissions":["Python 3.7+","Access to the TruthfulQA dataset"],"failure_modes":["Limited to 817 specific questions, which may not cover all areas of knowledge","Does not provide real-time feedback on model performance","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.8,"quality":0.37,"ecosystem":0.42,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.3,"quality":0.25,"ecosystem":0.1,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:25.060Z","last_scraped_at":"2026-05-03T15:20:49.428Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=truthfulqa","compare_url":"https://unfragile.ai/compare?artifact=truthfulqa"}},"signature":"FtcQUqgeZJOv9BzQpCVN9V0A4Z3ityiqpf+gFlTAZakW45srzx4g5aGdbaSq/mXykiiq6JeQ5x1jBTorAMSDAg==","signedAt":"2026-06-21T14:47:24.024Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/truthfulqa","artifact":"https://unfragile.ai/truthfulqa","verify":"https://unfragile.ai/api/v1/verify?slug=truthfulqa","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}