{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O3LBQP6DBM3DCVUEFPALBR2SHH","short_pith_number":"pith:O3LBQP6D","schema_version":"1.0","canonical_sha256":"76d6183fc30b363156842bc0b0c75239ef2c83becea7b6cdb23d417200289409","source":{"kind":"arxiv","id":"2502.09017","version":2},"attestation_state":"computed","paper":{"title":"Diversity Enhances an LLM's Performance in RAG and Long-context Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Bi, Claire Na Cheng, Sitaram Asur, Yanqi Luo, Zhichao Wang","submitted_at":"2025-02-13T07:11:01Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have highlighted the challenge of context window limitations, primarily due to the quadratic time complexity of the self-attention mechanism (\\(O(N^2)\\), where \\(N\\) denotes the context window length). This constraint impacts tasks such as retrieval-augmented generation (RAG) in question answering (Q\\&A) and long context summarization. A common approach involves selecting content with the highest similarity to the query; however, this often leads to redundancy and the exclusion of diverse yet relevant information. Building on principles fr"},"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":"2502.09017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T07:11:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48376c7fa9fcb6d7bbcf24ecae726eb4409f374976fb81f819d404ebd15b9f28","abstract_canon_sha256":"806621cfb8b3be35d3797446c39529d17dc717bc0cd86cdc4580038a1e24216b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:39.018974Z","signature_b64":"z2qF9L+4yWgmDT8k5vkPKSnIJo0ZwfqhKFRRF0iaTiMURpWqcK+54rpsD//65ITAuAyYp+sLSKAZ8Ux7VFzWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76d6183fc30b363156842bc0b0c75239ef2c83becea7b6cdb23d417200289409","last_reissued_at":"2026-07-05T10:45:39.018440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:39.018440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity Enhances an LLM's Performance in RAG and Long-context Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Bi, Claire Na Cheng, Sitaram Asur, Yanqi Luo, Zhichao Wang","submitted_at":"2025-02-13T07:11:01Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have highlighted the challenge of context window limitations, primarily due to the quadratic time complexity of the self-attention mechanism (\\(O(N^2)\\), where \\(N\\) denotes the context window length). This constraint impacts tasks such as retrieval-augmented generation (RAG) in question answering (Q\\&A) and long context summarization. A common approach involves selecting content with the highest similarity to the query; however, this often leads to redundancy and the exclusion of diverse yet relevant information. Building on principles fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09017","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/2502.09017/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":"2502.09017","created_at":"2026-07-05T10:45:39.018522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09017v2","created_at":"2026-07-05T10:45:39.018522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09017","created_at":"2026-07-05T10:45:39.018522+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3LBQP6DBM3D","created_at":"2026-07-05T10:45:39.018522+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3LBQP6DBM3DCVUE","created_at":"2026-07-05T10:45:39.018522+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3LBQP6D","created_at":"2026-07-05T10:45:39.018522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12789","citing_title":"How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28522","citing_title":"Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21934","citing_title":"Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH","json":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH.json","graph_json":"https://pith.science/api/pith-number/O3LBQP6DBM3DCVUEFPALBR2SHH/graph.json","events_json":"https://pith.science/api/pith-number/O3LBQP6DBM3DCVUEFPALBR2SHH/events.json","paper":"https://pith.science/paper/O3LBQP6D"},"agent_actions":{"view_html":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH","download_json":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH.json","view_paper":"https://pith.science/paper/O3LBQP6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09017&json=true","fetch_graph":"https://pith.science/api/pith-number/O3LBQP6DBM3DCVUEFPALBR2SHH/graph.json","fetch_events":"https://pith.science/api/pith-number/O3LBQP6DBM3DCVUEFPALBR2SHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH/action/storage_attestation","attest_author":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH/action/author_attestation","sign_citation":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH/action/citation_signature","submit_replication":"https://pith.science/pith/O3LBQP6DBM3DCVUEFPALBR2SHH/action/replication_record"}},"created_at":"2026-07-05T10:45:39.018522+00:00","updated_at":"2026-07-05T10:45:39.018522+00:00"}