{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UEMAUC4ZNCQACEK6OVDJQVEOP7","short_pith_number":"pith:UEMAUC4Z","schema_version":"1.0","canonical_sha256":"a1180a0b9968a001115e754698548e7ffaab8d6c22b0963769690c0eefa38d91","source":{"kind":"arxiv","id":"1903.00161","version":2},"attestation_state":"computed","paper":{"title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dheeru Dua, Gabriel Stanovsky, Matt Gardner, Pradeep Dasigi, Sameer Singh, Yizhong Wang","submitted_at":"2019-03-01T05:32:01Z","abstract_excerpt":"Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work left to be done. We introduce a new English reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs. In this crowdsourced, adversarially-created, 96k-question benchmark, a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as additi"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1903.00161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T05:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"3c0c2cf431f6bc3398d6e77a147fcfdfa5f4a572d8f5a0acb3fe9b7063d3d8ad","abstract_canon_sha256":"58cd353ccf857ef31853c6d6424e75997574cb3650ce958b5ec67ceb9313c426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:19.880223Z","signature_b64":"mYkOlw2fodfqPhBvUXW4Ka8UFcdGFHz2e6bECUW2bAJ4FLaT+ulLn90B8i8SRFR5RSGQuUziF2GicKVf4JcNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1180a0b9968a001115e754698548e7ffaab8d6c22b0963769690c0eefa38d91","last_reissued_at":"2026-05-17T23:48:19.879696Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:19.879696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dheeru Dua, Gabriel Stanovsky, Matt Gardner, Pradeep Dasigi, Sameer Singh, Yizhong Wang","submitted_at":"2019-03-01T05:32:01Z","abstract_excerpt":"Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work left to be done. We introduce a new English reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs. In this crowdsourced, adversarially-created, 96k-question benchmark, a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00161","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.00161","created_at":"2026-05-17T23:48:19.879782+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00161v2","created_at":"2026-05-17T23:48:19.879782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00161","created_at":"2026-05-17T23:48:19.879782+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEMAUC4ZNCQA","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEMAUC4ZNCQACEK6","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEMAUC4Z","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2504.16155","citing_title":"PRIMETIME : Limits of LLMs in Temporal Primitives","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11574","citing_title":"Learning to Configure Agentic AI Systems","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11574","citing_title":"Learning to Configure Agentic AI Systems","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18028","citing_title":"FedSDR: Federated Self-Distillation with Rectification","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2511.05501","citing_title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06133","citing_title":"CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2510.11541","citing_title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2502.11089","citing_title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2405.14782","citing_title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","ref_index":265,"is_internal_anchor":true},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12943","citing_title":"Reinforced Collaboration in Multi-Agent Flow Networks","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15745","citing_title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02737","citing_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05838","citing_title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21495","citing_title":"Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20273","citing_title":"ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09285","citing_title":"SAGE: A Service Agent Graph-guided Evaluation Benchmark","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18738","citing_title":"Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7","json":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7.json","graph_json":"https://pith.science/api/pith-number/UEMAUC4ZNCQACEK6OVDJQVEOP7/graph.json","events_json":"https://pith.science/api/pith-number/UEMAUC4ZNCQACEK6OVDJQVEOP7/events.json","paper":"https://pith.science/paper/UEMAUC4Z"},"agent_actions":{"view_html":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7","download_json":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7.json","view_paper":"https://pith.science/paper/UEMAUC4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00161&json=true","fetch_graph":"https://pith.science/api/pith-number/UEMAUC4ZNCQACEK6OVDJQVEOP7/graph.json","fetch_events":"https://pith.science/api/pith-number/UEMAUC4ZNCQACEK6OVDJQVEOP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7/action/storage_attestation","attest_author":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7/action/author_attestation","sign_citation":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7/action/citation_signature","submit_replication":"https://pith.science/pith/UEMAUC4ZNCQACEK6OVDJQVEOP7/action/replication_record"}},"created_at":"2026-05-17T23:48:19.879782+00:00","updated_at":"2026-05-17T23:48:19.879782+00:00"}