{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"papers-with-code-drop","slug":"drop","name":"DROP","type":"dataset","url":"https://paperswithcode.com/dataset/drop","page_url":"https://unfragile.ai/drop","categories":["model-training"],"tags":["benchmark","evaluation","reading-comprehension","reasoning"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"papers-with-code-drop__cap_0","uri":"capability://planning.reasoning.numerical.reasoning.comprehension.assessment","name":"numerical reasoning comprehension assessment","description":"DROP evaluates models' ability to perform numerical reasoning by presenting passages that require discrete reasoning tasks such as counting, sorting, and arithmetic. It uses a structured dataset where each question is tied to specific numerical information in the text, ensuring that models must ground their answers in the provided context. This capability is distinct in its focus on complex reasoning over simple retrieval, challenging models to demonstrate deeper understanding.","intents":["How can I evaluate my model's reading comprehension with a focus on numerical reasoning?","What benchmarks can I use to test discrete reasoning capabilities in language models?","How do I assess my AI's ability to answer arithmetic questions based on textual passages?"],"best_for":["researchers developing and testing reading comprehension models","data scientists evaluating AI performance on reasoning tasks"],"limitations":["Only tests discrete reasoning; does not cover qualitative reasoning or broader comprehension skills","Requires a well-structured passage for accurate question answering"],"requires":["Python 3.6+","Access to the DROP dataset via the provided URL"],"input_types":["text"],"output_types":["structured data"],"categories":["planning-reasoning","evaluation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"papers-with-code-drop__cap_1","uri":"capability://text.generation.language.discrete.reasoning.question.generation","name":"discrete reasoning question generation","description":"DROP includes a mechanism for generating questions that require discrete reasoning based on given passages. This involves analyzing the text to identify numerical data points and crafting questions that challenge models to perform arithmetic or logical operations. The structured approach ensures that questions are not only relevant but also test specific reasoning skills, making it a valuable tool for model training and evaluation.","intents":["How can I generate questions that test numerical reasoning from a text passage?","What methods can I use to create discrete reasoning questions for my AI training dataset?","How do I ensure my generated questions are grounded in the provided text?"],"best_for":["educators creating assessments for students","developers building AI training datasets"],"limitations":["Question generation is limited to the scope of the provided text; may not cover all reasoning types","Requires careful passage selection to ensure question relevance"],"requires":["Python 3.6+","Access to the DROP dataset"],"input_types":["text"],"output_types":["text"],"categories":["text-generation-language","evaluation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":47,"verified":false,"data_access_risk":"low","permissions":["Python 3.6+","Access to the DROP dataset via the provided URL","Access to the DROP dataset"],"failure_modes":["Only tests discrete reasoning; does not cover qualitative reasoning or broader comprehension skills","Requires a well-structured passage for accurate question answering","Question generation is limited to the scope of the provided text; may not cover all reasoning types","Requires careful passage selection to ensure question relevance","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.8,"quality":0.29,"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=drop","compare_url":"https://unfragile.ai/compare?artifact=drop"}},"signature":"nkcu5bsnWSeBmq3n6+gNy+MaTe24LZzZB69GZVmEMhF3L1x3En2CaHGZHpksuaeaV5+E9u8YEWL89O4pM4SaAA==","signedAt":"2026-07-08T03:41:14.417Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/drop","artifact":"https://unfragile.ai/drop","verify":"https://unfragile.ai/api/v1/verify?slug=drop","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"}}