{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MY4MWD4JNBUN24YXYPCPV56M2W","short_pith_number":"pith:MY4MWD4J","schema_version":"1.0","canonical_sha256":"6638cb0f896868dd7317c3c4faf7ccd5b40d7fc005eb6764ac4e915b9c1c2700","source":{"kind":"arxiv","id":"2410.18050","version":2},"attestation_state":"computed","paper":{"title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daren Zha, Jie Tang, Qingfei Zhao, Ruobing Wang, Shicheng Tan, Yukuo Cen, Yuxiao Dong","submitted_at":"2024-10-23T17:24:58Z","abstract_excerpt":"Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the \"lost in the middle\" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a genera"},"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":"2410.18050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T17:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"67a4e64a64d2ea1331f71fe431852699d318a4ae867b6c62bb51aa7bc3a40200","abstract_canon_sha256":"3d76784d76481b54868205c29619ffc370cd2201f23c5b0e9d1626ab45809beb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:34.550418Z","signature_b64":"w4IcZ09DKiRIQTnE1Li+ZjcA1CA3jTYbCMX6BgZxGhMjYphJPmiGIuJa60Jn11rX3RWaKVccEl2LzMv1e0HFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6638cb0f896868dd7317c3c4faf7ccd5b40d7fc005eb6764ac4e915b9c1c2700","last_reissued_at":"2026-07-05T09:29:34.549956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:34.549956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daren Zha, Jie Tang, Qingfei Zhao, Ruobing Wang, Shicheng Tan, Yukuo Cen, Yuxiao Dong","submitted_at":"2024-10-23T17:24:58Z","abstract_excerpt":"Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the \"lost in the middle\" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18050","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/2410.18050/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":"2410.18050","created_at":"2026-07-05T09:29:34.550010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18050v2","created_at":"2026-07-05T09:29:34.550010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18050","created_at":"2026-07-05T09:29:34.550010+00:00"},{"alias_kind":"pith_short_12","alias_value":"MY4MWD4JNBUN","created_at":"2026-07-05T09:29:34.550010+00:00"},{"alias_kind":"pith_short_16","alias_value":"MY4MWD4JNBUN24YX","created_at":"2026-07-05T09:29:34.550010+00:00"},{"alias_kind":"pith_short_8","alias_value":"MY4MWD4J","created_at":"2026-07-05T09:29:34.550010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00449","citing_title":"GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W","json":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W.json","graph_json":"https://pith.science/api/pith-number/MY4MWD4JNBUN24YXYPCPV56M2W/graph.json","events_json":"https://pith.science/api/pith-number/MY4MWD4JNBUN24YXYPCPV56M2W/events.json","paper":"https://pith.science/paper/MY4MWD4J"},"agent_actions":{"view_html":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W","download_json":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W.json","view_paper":"https://pith.science/paper/MY4MWD4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18050&json=true","fetch_graph":"https://pith.science/api/pith-number/MY4MWD4JNBUN24YXYPCPV56M2W/graph.json","fetch_events":"https://pith.science/api/pith-number/MY4MWD4JNBUN24YXYPCPV56M2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W/action/storage_attestation","attest_author":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W/action/author_attestation","sign_citation":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W/action/citation_signature","submit_replication":"https://pith.science/pith/MY4MWD4JNBUN24YXYPCPV56M2W/action/replication_record"}},"created_at":"2026-07-05T09:29:34.550010+00:00","updated_at":"2026-07-05T09:29:34.550010+00:00"}