{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AO6YY34D7LFCCEIKSC2SEBLGOE","short_pith_number":"pith:AO6YY34D","schema_version":"1.0","canonical_sha256":"03bd8c6f83faca21110a90b52205667118022678dc2481ee802aee2f4bafb897","source":{"kind":"arxiv","id":"2504.11197","version":2},"attestation_state":"computed","paper":{"title":"Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Fan Wu, Guihai Chen, Jie Wu, Shangyu Liu, Xiaoyao Huang, Zhenzhe Zheng","submitted_at":"2025-04-15T13:53:08Z","abstract_excerpt":"Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model performance by integrating external databases, without requiring intensive on-device model retraining. However, large-scale public databases and user-specific private contextual documents are typically located on the cloud and the device separately, while existing RAG implementations are primarily centralized. To bridge this gap, we propose DRAGON, a distribute"},"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":"2504.11197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T13:53:08Z","cross_cats_sorted":["cs.AI","cs.DC","cs.IR"],"title_canon_sha256":"9dcad35da24d5ee7e9d629823527ee52406e550e0408402fa1bede2f268cd2f2","abstract_canon_sha256":"8f5cf81f026f9f1680152465eb2a18897c5f089883e8d71c03ce43e937a711fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:54.098930Z","signature_b64":"CYLizCMJjOVcLkyb4Ko0EaF8Z2wEngpgosZUmfgwspG+LWdhyI1cuIlxPug6drGlSX2OWHApalL2g88d/ZIEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03bd8c6f83faca21110a90b52205667118022678dc2481ee802aee2f4bafb897","last_reissued_at":"2026-07-05T10:49:54.098470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:54.098470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Fan Wu, Guihai Chen, Jie Wu, Shangyu Liu, Xiaoyao Huang, Zhenzhe Zheng","submitted_at":"2025-04-15T13:53:08Z","abstract_excerpt":"Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model performance by integrating external databases, without requiring intensive on-device model retraining. However, large-scale public databases and user-specific private contextual documents are typically located on the cloud and the device separately, while existing RAG implementations are primarily centralized. To bridge this gap, we propose DRAGON, a distribute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11197","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/2504.11197/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":"2504.11197","created_at":"2026-07-05T10:49:54.098528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11197v2","created_at":"2026-07-05T10:49:54.098528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11197","created_at":"2026-07-05T10:49:54.098528+00:00"},{"alias_kind":"pith_short_12","alias_value":"AO6YY34D7LFC","created_at":"2026-07-05T10:49:54.098528+00:00"},{"alias_kind":"pith_short_16","alias_value":"AO6YY34D7LFCCEIK","created_at":"2026-07-05T10:49:54.098528+00:00"},{"alias_kind":"pith_short_8","alias_value":"AO6YY34D","created_at":"2026-07-05T10:49:54.098528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE","json":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE.json","graph_json":"https://pith.science/api/pith-number/AO6YY34D7LFCCEIKSC2SEBLGOE/graph.json","events_json":"https://pith.science/api/pith-number/AO6YY34D7LFCCEIKSC2SEBLGOE/events.json","paper":"https://pith.science/paper/AO6YY34D"},"agent_actions":{"view_html":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE","download_json":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE.json","view_paper":"https://pith.science/paper/AO6YY34D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11197&json=true","fetch_graph":"https://pith.science/api/pith-number/AO6YY34D7LFCCEIKSC2SEBLGOE/graph.json","fetch_events":"https://pith.science/api/pith-number/AO6YY34D7LFCCEIKSC2SEBLGOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE/action/storage_attestation","attest_author":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE/action/author_attestation","sign_citation":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE/action/citation_signature","submit_replication":"https://pith.science/pith/AO6YY34D7LFCCEIKSC2SEBLGOE/action/replication_record"}},"created_at":"2026-07-05T10:49:54.098528+00:00","updated_at":"2026-07-05T10:49:54.098528+00:00"}