{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKIKLUL7LJSZOBWLXUJRRQZYYY","short_pith_number":"pith:YKIKLUL7","schema_version":"1.0","canonical_sha256":"c290a5d17f5a659706cbbd1318c338c633265646fc712f46046076bb58d3538b","source":{"kind":"arxiv","id":"2404.02103","version":2},"attestation_state":"computed","paper":{"title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avirup Sil, Radu Florian, Salim Roukos, Sara Rosenthal","submitted_at":"2024-04-02T17:00:11Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has become a popular application for large language models. It is preferable that successful RAG systems provide accurate answers that are supported by being grounded in a passage without any hallucinations. While considerable work is required for building a full RAG pipeline, being able to benchmark performance is also necessary. We present ClapNQ, a benchmark Long-form Question Answering dataset for the full RAG pipeline. ClapNQ includes long answers with grounded gold passages from Natural Questions (NQ) and a corpus to perform either retrieval, generati"},"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":"2404.02103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T17:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"aed35fae4600a1c5167f6da8dc6b528389e93512f9308a4198d8d05e9ef70bbc","abstract_canon_sha256":"276c0dec4227abcbafbab9ac4c6bce4ef7b73fd1ac922651e527f4bc9c745731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:00.312306Z","signature_b64":"4ZTj9gYuNslD9sCqFGMzgVOUBoPILdW9SiYbd1Z09+5w3+bueU3wAP9tObOJyY7xHKjD9lHGGXJGFmp3OxA4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c290a5d17f5a659706cbbd1318c338c633265646fc712f46046076bb58d3538b","last_reissued_at":"2026-07-05T09:53:00.311894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:00.311894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avirup Sil, Radu Florian, Salim Roukos, Sara Rosenthal","submitted_at":"2024-04-02T17:00:11Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has become a popular application for large language models. It is preferable that successful RAG systems provide accurate answers that are supported by being grounded in a passage without any hallucinations. While considerable work is required for building a full RAG pipeline, being able to benchmark performance is also necessary. We present ClapNQ, a benchmark Long-form Question Answering dataset for the full RAG pipeline. ClapNQ includes long answers with grounded gold passages from Natural Questions (NQ) and a corpus to perform either retrieval, generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02103","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.02103/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2404.02103","created_at":"2026-07-05T09:53:00.311947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02103v2","created_at":"2026-07-05T09:53:00.311947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02103","created_at":"2026-07-05T09:53:00.311947+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKIKLUL7LJSZ","created_at":"2026-07-05T09:53:00.311947+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKIKLUL7LJSZOBWL","created_at":"2026-07-05T09:53:00.311947+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKIKLUL7","created_at":"2026-07-05T09:53:00.311947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY","json":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY.json","graph_json":"https://pith.science/api/pith-number/YKIKLUL7LJSZOBWLXUJRRQZYYY/graph.json","events_json":"https://pith.science/api/pith-number/YKIKLUL7LJSZOBWLXUJRRQZYYY/events.json","paper":"https://pith.science/paper/YKIKLUL7"},"agent_actions":{"view_html":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY","download_json":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY.json","view_paper":"https://pith.science/paper/YKIKLUL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02103&json=true","fetch_graph":"https://pith.science/api/pith-number/YKIKLUL7LJSZOBWLXUJRRQZYYY/graph.json","fetch_events":"https://pith.science/api/pith-number/YKIKLUL7LJSZOBWLXUJRRQZYYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY/action/storage_attestation","attest_author":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY/action/author_attestation","sign_citation":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY/action/citation_signature","submit_replication":"https://pith.science/pith/YKIKLUL7LJSZOBWLXUJRRQZYYY/action/replication_record"}},"created_at":"2026-07-05T09:53:00.311947+00:00","updated_at":"2026-07-05T09:53:00.311947+00:00"}