{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IU7SCXMHNLQF5WAZBQXZOFHXEM","short_pith_number":"pith:IU7SCXMH","schema_version":"1.0","canonical_sha256":"453f215d876ae05ed8190c2f9714f7233730e0f37d6292b7192492c3fc7dbbf9","source":{"kind":"arxiv","id":"2501.05554","version":1},"attestation_state":"computed","paper":{"title":"LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Li Weigang, Yuri Facanha Bezerra","submitted_at":"2025-01-09T20:01:15Z","abstract_excerpt":"We introduce LLMQuoter, a lightweight, distillation-based model designed to enhance Retrieval Augmented Generation (RAG) by extracting the most relevant textual evidence for downstream reasoning tasks. Built on the LLaMA-3B architecture and fine-tuned with Low-Rank Adaptation (LoRA) on a 15,000-sample subset of HotpotQA, LLMQuoter adopts a \"quote-first-then-answer\" strategy, efficiently identifying key quotes before passing curated snippets to reasoning models. This workflow reduces cognitive overhead and outperforms full-context approaches like Retrieval-Augmented Fine-Tuning (RAFT), achievin"},"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":"2501.05554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T20:01:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"619efffc2799bdc4a5a18f250e98274673dd54d5a6dc138e654b46ca77a62c59","abstract_canon_sha256":"a58915eafb6647ebb65a1ffc671309b1152c83fa64a6a795ea7aae3b201d8a9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:24.899967Z","signature_b64":"3oPNSTBfEs71Y956AfgiRQz6o2iRAVCuXATFeGsKnRgGDkU46sLU5VdCy9kFLw2Z/wx+ie4TaaDF23jaakXXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"453f215d876ae05ed8190c2f9714f7233730e0f37d6292b7192492c3fc7dbbf9","last_reissued_at":"2026-07-05T09:59:24.899555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:24.899555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Li Weigang, Yuri Facanha Bezerra","submitted_at":"2025-01-09T20:01:15Z","abstract_excerpt":"We introduce LLMQuoter, a lightweight, distillation-based model designed to enhance Retrieval Augmented Generation (RAG) by extracting the most relevant textual evidence for downstream reasoning tasks. Built on the LLaMA-3B architecture and fine-tuned with Low-Rank Adaptation (LoRA) on a 15,000-sample subset of HotpotQA, LLMQuoter adopts a \"quote-first-then-answer\" strategy, efficiently identifying key quotes before passing curated snippets to reasoning models. This workflow reduces cognitive overhead and outperforms full-context approaches like Retrieval-Augmented Fine-Tuning (RAFT), achievin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05554","kind":"arxiv","version":1},"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/2501.05554/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":"2501.05554","created_at":"2026-07-05T09:59:24.899610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05554v1","created_at":"2026-07-05T09:59:24.899610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05554","created_at":"2026-07-05T09:59:24.899610+00:00"},{"alias_kind":"pith_short_12","alias_value":"IU7SCXMHNLQF","created_at":"2026-07-05T09:59:24.899610+00:00"},{"alias_kind":"pith_short_16","alias_value":"IU7SCXMHNLQF5WAZ","created_at":"2026-07-05T09:59:24.899610+00:00"},{"alias_kind":"pith_short_8","alias_value":"IU7SCXMH","created_at":"2026-07-05T09:59:24.899610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01954","citing_title":"DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM","json":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM.json","graph_json":"https://pith.science/api/pith-number/IU7SCXMHNLQF5WAZBQXZOFHXEM/graph.json","events_json":"https://pith.science/api/pith-number/IU7SCXMHNLQF5WAZBQXZOFHXEM/events.json","paper":"https://pith.science/paper/IU7SCXMH"},"agent_actions":{"view_html":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM","download_json":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM.json","view_paper":"https://pith.science/paper/IU7SCXMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05554&json=true","fetch_graph":"https://pith.science/api/pith-number/IU7SCXMHNLQF5WAZBQXZOFHXEM/graph.json","fetch_events":"https://pith.science/api/pith-number/IU7SCXMHNLQF5WAZBQXZOFHXEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM/action/storage_attestation","attest_author":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM/action/author_attestation","sign_citation":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM/action/citation_signature","submit_replication":"https://pith.science/pith/IU7SCXMHNLQF5WAZBQXZOFHXEM/action/replication_record"}},"created_at":"2026-07-05T09:59:24.899610+00:00","updated_at":"2026-07-05T09:59:24.899610+00:00"}