{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RF65H7HQWXPVHQOST4I6WQKCXE","short_pith_number":"pith:RF65H7HQ","schema_version":"1.0","canonical_sha256":"897dd3fcf0b5df53c1d29f11eb4142b92b1b6e853073e87c6017d399a5476ba3","source":{"kind":"arxiv","id":"2308.04215","version":3},"attestation_state":"computed","paper":{"title":"Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CL","authors_text":"Camille Couturier, Guoqing Zheng, Menglin Xia, Saravan Rajmohan, Victor Ruhle, Xuchao Zhang","submitted_at":"2023-08-08T12:27:20Z","abstract_excerpt":"Large language models (LLMs) enhanced with retrieval augmentation has shown great performance in many applications. However, the computational demands for these models pose a challenge when applying them to real-time tasks, such as composition assistance. To address this, we propose Hybrid Retrieval-Augmented Composition Assistance (Hybrid-RACA), a novel system for real-time text prediction that efficiently combines a cloud-based LLM with a smaller client-side model through retrieval augmented memory. This integration enables the client model to generate better responses, benefiting from the L"},"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":"2308.04215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-08T12:27:20Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"d2dd88dd88038d25c32d6b8ca44acc756cb1710e8d3a8d00e3639408d0c682ff","abstract_canon_sha256":"541c1bcbda5fc76a3e672196cf7e4232d54167528a0b194b8d1f4b6ffd890491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:24.065338Z","signature_b64":"kwqCh5arSyIgoLvGAbEdLC+AVQA0wQ/2FDcDdnAsU7JALiwnwqlmzloT2ZrVMy1IxVROh8Bp20/b9ov6dWCQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"897dd3fcf0b5df53c1d29f11eb4142b92b1b6e853073e87c6017d399a5476ba3","last_reissued_at":"2026-07-05T09:19:24.064892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:24.064892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CL","authors_text":"Camille Couturier, Guoqing Zheng, Menglin Xia, Saravan Rajmohan, Victor Ruhle, Xuchao Zhang","submitted_at":"2023-08-08T12:27:20Z","abstract_excerpt":"Large language models (LLMs) enhanced with retrieval augmentation has shown great performance in many applications. However, the computational demands for these models pose a challenge when applying them to real-time tasks, such as composition assistance. To address this, we propose Hybrid Retrieval-Augmented Composition Assistance (Hybrid-RACA), a novel system for real-time text prediction that efficiently combines a cloud-based LLM with a smaller client-side model through retrieval augmented memory. This integration enables the client model to generate better responses, benefiting from the L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04215","kind":"arxiv","version":3},"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/2308.04215/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":"2308.04215","created_at":"2026-07-05T09:19:24.064947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04215v3","created_at":"2026-07-05T09:19:24.064947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04215","created_at":"2026-07-05T09:19:24.064947+00:00"},{"alias_kind":"pith_short_12","alias_value":"RF65H7HQWXPV","created_at":"2026-07-05T09:19:24.064947+00:00"},{"alias_kind":"pith_short_16","alias_value":"RF65H7HQWXPVHQOS","created_at":"2026-07-05T09:19:24.064947+00:00"},{"alias_kind":"pith_short_8","alias_value":"RF65H7HQ","created_at":"2026-07-05T09:19:24.064947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.15701","citing_title":"Political Events using RAG with LLMs","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE","json":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE.json","graph_json":"https://pith.science/api/pith-number/RF65H7HQWXPVHQOST4I6WQKCXE/graph.json","events_json":"https://pith.science/api/pith-number/RF65H7HQWXPVHQOST4I6WQKCXE/events.json","paper":"https://pith.science/paper/RF65H7HQ"},"agent_actions":{"view_html":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE","download_json":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE.json","view_paper":"https://pith.science/paper/RF65H7HQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04215&json=true","fetch_graph":"https://pith.science/api/pith-number/RF65H7HQWXPVHQOST4I6WQKCXE/graph.json","fetch_events":"https://pith.science/api/pith-number/RF65H7HQWXPVHQOST4I6WQKCXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE/action/storage_attestation","attest_author":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE/action/author_attestation","sign_citation":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE/action/citation_signature","submit_replication":"https://pith.science/pith/RF65H7HQWXPVHQOST4I6WQKCXE/action/replication_record"}},"created_at":"2026-07-05T09:19:24.064947+00:00","updated_at":"2026-07-05T09:19:24.064947+00:00"}